refactor(projman): extract skills and consolidate commands

Major refactoring of projman plugin architecture:

Skills Extraction (17 new files):
- Extracted reusable knowledge from commands and agents into skills/
- branch-security, dependency-management, git-workflow, input-detection
- issue-conventions, lessons-learned, mcp-tools-reference, planning-workflow
- progress-tracking, repo-validation, review-checklist, runaway-detection
- setup-workflows, sprint-approval, task-sizing, test-standards, wiki-conventions

Command Consolidation (17 → 12 commands):
- /setup: consolidates initial-setup, project-init, project-sync (--full/--quick/--sync)
- /debug: consolidates debug-report, debug-review (report/review modes)
- /test: consolidates test-check, test-gen (run/gen modes)
- /sprint-status: absorbs sprint-diagram via --diagram flag

Architecture Cleanup:
- Remove plugin-level mcp-servers/ symlinks (6 plugins)
- Remove plugin README.md files (12 files, ~2000 lines)
- Update all documentation to reflect new command structure
- Fix documentation drift in CONFIGURATION.md, COMMANDS-CHEATSHEET.md

Commands are now thin dispatchers (~20-50 lines) that reference skills.
Agents reference skills for domain knowledge instead of inline content.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2026-01-30 15:02:16 -05:00
parent 8fe685037e
commit 2e65b60725
70 changed files with 3450 additions and 8887 deletions

View File

@@ -4,7 +4,9 @@ description: Clear plugin cache to force fresh configuration reload after market
# Clear Cache
Clear plugin cache to force fresh configuration reload. Run this after marketplace updates.
## Purpose
Clear plugin cache to force fresh configuration reload after marketplace updates.
## When to Use
@@ -12,17 +14,21 @@ Clear plugin cache to force fresh configuration reload. Run this after marketpla
- When MCP servers show stale configuration
- When plugin changes don't take effect
## What It Does
## Workflow
1. Clears `~/.claude/plugins/cache/leo-claude-mktplace/`
2. Forces Claude Code to re-read `.mcp.json` files on next session
## Instructions
Run this command, then **restart your Claude Code session** for changes to take effect.
Execute cache clear:
```bash
rm -rf ~/.claude/plugins/cache/leo-claude-mktplace/
```
After clearing, inform the user: "Cache cleared. Restart Claude Code for changes to take effect."
Then inform user: "Cache cleared. Restart Claude Code for changes to take effect."
## Visual Output
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ Clear Cache ║
╚══════════════════════════════════════════════════════════════════╝
```

View File

@@ -1,701 +0,0 @@
---
description: Run diagnostics and create structured issue in marketplace repository
---
# Debug Report
Create structured issues in the marketplace repository - either from automated diagnostic tests OR from user-reported problems.
## Prerequisites
Your project `.env` must have:
```env
PROJMAN_MARKETPLACE_REPO=personal-projects/leo-claude-mktplace
```
If not configured, ask the user for the marketplace repository path.
## CRITICAL: Execution Steps
You MUST follow these steps in order. Do NOT skip any step.
### Step 0: Select Report Mode
Use AskUserQuestion to determine what the user wants to report:
```
What would you like to report?
[ ] Run automated diagnostics - Test MCP tools and report failures
[ ] Report an issue I experienced - Describe a problem with any plugin command
```
Store the selection as `REPORT_MODE`:
- "automated" → Continue to Step 1
- "user-reported" → Skip to Step 0.1
---
### Step 0.1: Gather User Feedback (User-Reported Mode Only)
If `REPORT_MODE` is "user-reported", gather structured feedback.
**Question 1: What were you trying to do?**
Use AskUserQuestion:
```
Which plugin/command were you using?
[ ] projman (sprint planning, issues, labels)
[ ] git-flow (commits, branches)
[ ] pr-review (pull request review)
[ ] cmdb-assistant (NetBox integration)
[ ] doc-guardian (documentation)
[ ] code-sentinel (security, refactoring)
[ ] Other - I'll describe it
```
Store as `AFFECTED_PLUGIN`.
Then ask for the specific command (free text):
```
What command or tool were you using? (e.g., /sprint-plan, virt_update_vm)
```
Store as `AFFECTED_COMMAND`.
**Question 2: What was your goal?**
```
Briefly describe what you were trying to accomplish:
```
Store as `USER_GOAL`.
**Question 3: What went wrong?**
Use AskUserQuestion:
```
What type of problem did you encounter?
[ ] Error message - Command failed with an error
[ ] Missing feature - Tool doesn't support what I need
[ ] Unexpected behavior - It worked but did the wrong thing
[ ] Documentation issue - Instructions were unclear or wrong
[ ] Other - I'll describe it
```
Store as `PROBLEM_TYPE`.
Then ask for details (free text):
```
Describe what happened. Include any error messages if applicable:
```
Store as `PROBLEM_DESCRIPTION`.
**Question 4: Expected vs Actual**
```
What did you expect to happen?
```
Store as `EXPECTED_BEHAVIOR`.
**Question 5: Workaround (optional)**
```
Did you find a workaround? If so, describe it (or skip):
```
Store as `WORKAROUND` (may be empty).
After gathering feedback, continue to Step 1 for context gathering, then skip to Step 5.1.
---
### Step 1: Gather Project Context
Run these Bash commands to capture project information:
```bash
# Get git remote URL
git remote get-url origin
# Get current branch
git branch --show-current
# Get working directory
pwd
```
Parse the git remote to extract `REPO_NAME` in `owner/repo` format.
Store all values:
- `PROJECT_REPO`: The detected owner/repo
- `GIT_REMOTE`: Full git remote URL
- `CURRENT_BRANCH`: Current branch name
- `WORKING_DIR`: Current working directory
### Step 1.5: Detect Sprint Context
Determine if this debug issue should be associated with an active sprint.
**1. Check for active sprint milestone:**
```
mcp__plugin_projman_gitea__list_milestones(repo=PROJECT_REPO, state="open")
```
Store the first open milestone as `ACTIVE_SPRINT` (if any).
**2. Analyze branch context:**
| Branch Pattern | Context |
|----------------|---------|
| `feat/*`, `fix/*`, `issue-*` | Sprint work - likely related to current sprint |
| `main`, `master`, `development` | Production/standalone - not sprint-related |
| Other | Unknown - ask user |
**3. Determine sprint association:**
```
IF ACTIVE_SPRINT exists AND CURRENT_BRANCH matches sprint pattern (feat/*, fix/*, issue-*):
→ SPRINT_CONTEXT = "detected"
→ Ask user: "Active sprint detected: [SPRINT_NAME]. Is this bug related to sprint work?"
Options:
- Yes, add to sprint (will associate with milestone)
- No, standalone fix (no milestone)
→ Store choice as ASSOCIATE_WITH_SPRINT (true/false)
ELSE IF ACTIVE_SPRINT exists AND CURRENT_BRANCH is main/development:
→ SPRINT_CONTEXT = "production"
→ ASSOCIATE_WITH_SPRINT = false (standalone fix, no question needed)
ELSE:
→ SPRINT_CONTEXT = "none"
→ ASSOCIATE_WITH_SPRINT = false
```
### Step 2: Read Marketplace Configuration
```bash
grep PROJMAN_MARKETPLACE_REPO .env
```
Store as `MARKETPLACE_REPO`. If not found, ask the user.
### Step 3: Run Diagnostic Suite (Automated Mode Only)
**Skip this step if `REPORT_MODE` is "user-reported"** → Go to Step 5.1
Run each MCP tool with explicit `repo` parameter. Record success/failure and full response.
**Test 1: validate_repo_org**
```
mcp__plugin_projman_gitea__validate_repo_org(repo=PROJECT_REPO)
```
Expected: `{is_organization: true/false}`
**Test 2: get_labels**
```
mcp__plugin_projman_gitea__get_labels(repo=PROJECT_REPO)
```
Expected: `{organization: [...], repository: [...], total_count: N}`
**Test 3: list_issues**
```
mcp__plugin_projman_gitea__list_issues(repo=PROJECT_REPO, state="open")
```
Expected: Array of issues
**Test 4: list_milestones**
```
mcp__plugin_projman_gitea__list_milestones(repo=PROJECT_REPO)
```
Expected: Array of milestones
**Test 5: suggest_labels**
```
mcp__plugin_projman_gitea__suggest_labels(context="Test bug fix for authentication")
```
Expected: Array of label names matching repo's format
For each test, record:
- Tool name
- Exact parameters used
- Status: PASS or FAIL
- Response or error message
### Step 4: Analyze Results (Automated Mode Only)
**Skip this step if `REPORT_MODE` is "user-reported"** → Go to Step 5.1
Count failures and categorize errors:
| Category | Indicators |
|----------|------------|
| Parameter Format | "owner/repo format", "missing parameter" |
| Authentication | "401", "403", "unauthorized" |
| Not Found | "404", "not found" |
| Network | "connection", "timeout", "ECONNREFUSED" |
| Logic | Unexpected response format, wrong data |
For each failure, write a hypothesis about the likely cause.
### Step 5: Generate Smart Labels (Automated Mode Only)
**Skip this step if `REPORT_MODE` is "user-reported"** → Go to Step 5.1
Generate appropriate labels based on the diagnostic results.
**1. Build context string for label suggestion:**
```
LABEL_CONTEXT = "Bug fix: " + [summary of main failure] + ". " +
"Failed tools: " + [list of failed tool names] + ". " +
"Error category: " + [detected error category from Step 4]
```
**2. Get suggested labels:**
```
mcp__plugin_projman_gitea__suggest_labels(
repo=PROJECT_REPO,
context=LABEL_CONTEXT
)
```
**3. Merge with base labels:**
```
BASE_LABELS = ["Type: Bug", "Source: Diagnostic", "Agent: Claude"]
SUGGESTED_LABELS = [result from suggest_labels]
# Combine, avoiding duplicates
FINAL_LABELS = BASE_LABELS + [label for label in SUGGESTED_LABELS if label not in BASE_LABELS]
```
The final label set should include:
- **Always**: `Type: Bug`, `Source: Diagnostic`, `Agent: Claude`
- **If detected**: `Component: *`, `Complexity: *`, `Risk: *`, `Priority: *`
After generating labels, continue to Step 6.
---
### Step 5.1: Generate Labels (User-Reported Mode Only)
**Only execute this step if `REPORT_MODE` is "user-reported"**
**1. Map problem type to labels:**
| PROBLEM_TYPE | Labels |
|--------------|--------|
| Error message | `Type: Bug` |
| Missing feature | `Type: Enhancement` |
| Unexpected behavior | `Type: Bug` |
| Documentation issue | `Type: Documentation` |
| Other | `Type: Bug` (default) |
**2. Map plugin to component:**
| AFFECTED_PLUGIN | Component Label |
|-----------------|-----------------|
| projman | `Component: Commands` |
| git-flow | `Component: Commands` |
| pr-review | `Component: Commands` |
| cmdb-assistant | `Component: API` |
| doc-guardian | `Component: Commands` |
| code-sentinel | `Component: Commands` |
| Other | *(no component label)* |
**3. Build final labels:**
```
BASE_LABELS = ["Source: User-Reported", "Agent: Claude"]
TYPE_LABEL = [mapped from PROBLEM_TYPE]
COMPONENT_LABEL = [mapped from AFFECTED_PLUGIN, if any]
FINAL_LABELS = BASE_LABELS + TYPE_LABEL + COMPONENT_LABEL
```
After generating labels, continue to Step 6.1.
---
### Step 6: Generate Issue Content (Automated Mode Only)
**Skip this step if `REPORT_MODE` is "user-reported"** → Go to Step 6.1
Use this exact template:
```markdown
## Diagnostic Report
**Generated**: [ISO timestamp]
**Command Tested**: [What the user was trying to run, or "general diagnostic"]
**Reporter**: Claude Code via /debug-report
## Project Context
| Field | Value |
|-------|-------|
| Repository | `[PROJECT_REPO]` |
| Git Remote | `[GIT_REMOTE]` |
| Working Directory | `[WORKING_DIR]` |
| Current Branch | `[CURRENT_BRANCH]` |
## Diagnostic Results
### Test 1: validate_repo_org
**Call**: `validate_repo_org(repo="[PROJECT_REPO]")`
**Status**: [PASS/FAIL]
**Response**:
```json
[full response or error]
```
### Test 2: get_labels
**Call**: `get_labels(repo="[PROJECT_REPO]")`
**Status**: [PASS/FAIL]
**Response**:
```json
[full response or error - truncate if very long]
```
[... repeat for each test ...]
## Summary
- **Total Tests**: 5
- **Passed**: [N]
- **Failed**: [N]
### Failed Tools
[List each failed tool with its error]
### Error Category
[Check applicable categories]
### Hypothesis
[Your analysis of what's wrong and why]
### Suggested Investigation
1. [First file/function to check]
2. [Second file/function to check]
3. [etc.]
## Reproduction Steps
1. Navigate to `[WORKING_DIR]`
2. Run `[command that was being tested]`
3. Observe error at step [X]
---
*Generated by /debug-report (automated) - Labels: Type: Bug, Source: Diagnostic, Agent: Claude*
```
After generating content, continue to Step 7.
---
### Step 6.1: Generate Issue Content (User-Reported Mode Only)
**Only execute this step if `REPORT_MODE` is "user-reported"**
Use this template for user-reported issues:
```markdown
## User-Reported Issue
**Reported**: [ISO timestamp]
**Reporter**: Claude Code via /debug-report (user feedback)
## Context
| Field | Value |
|-------|-------|
| Plugin | `[AFFECTED_PLUGIN]` |
| Command/Tool | `[AFFECTED_COMMAND]` |
| Repository | `[PROJECT_REPO]` |
| Working Directory | `[WORKING_DIR]` |
| Branch | `[CURRENT_BRANCH]` |
## Problem Description
### Goal
[USER_GOAL]
### What Happened
**Problem Type**: [PROBLEM_TYPE]
[PROBLEM_DESCRIPTION]
### Expected Behavior
[EXPECTED_BEHAVIOR]
## Workaround
[WORKAROUND if provided, otherwise "None identified"]
## Investigation Hints
Based on the affected plugin/command, relevant files to check:
[Generate based on AFFECTED_PLUGIN:]
**projman:**
- `plugins/projman/commands/[AFFECTED_COMMAND].md`
- `mcp-servers/gitea/mcp_server/tools/*.py`
**git-flow:**
- `plugins/git-flow/commands/[AFFECTED_COMMAND].md`
**pr-review:**
- `plugins/pr-review/commands/[AFFECTED_COMMAND].md`
- `mcp-servers/gitea/mcp_server/tools/pull_requests.py`
**cmdb-assistant:**
- `plugins/cmdb-assistant/commands/[AFFECTED_COMMAND].md`
- `mcp-servers/netbox/mcp_server/tools/*.py`
- `mcp-servers/netbox/mcp_server/server.py` (tool schemas)
**doc-guardian / code-sentinel:**
- `plugins/[plugin]/commands/[AFFECTED_COMMAND].md`
- `plugins/[plugin]/hooks/*.md`
---
*Generated by /debug-report (user feedback) - Labels: [FINAL_LABELS]*
```
After generating content, continue to Step 7.
---
### Step 7: Create Issue in Marketplace
**IMPORTANT:** Always use curl to create issues in the marketplace repo. This avoids branch protection restrictions and MCP context issues that can block issue creation when working on protected branches.
**1. Load Gitea credentials:**
```bash
if [[ -f ~/.config/claude/gitea.env ]]; then
source ~/.config/claude/gitea.env
echo "Credentials loaded. API URL: $GITEA_API_URL"
else
echo "ERROR: No credentials at ~/.config/claude/gitea.env"
fi
```
**2. Fetch label IDs from marketplace repo:**
Labels depend on `REPORT_MODE`:
**Automated mode:**
- `Source/Diagnostic` (always)
- `Type/Bug` (always)
**User-reported mode:**
- `Source/User-Reported` (always)
- Type label from Step 5.1 (Bug, Enhancement, or Documentation)
- Component label from Step 5.1 (if applicable)
```bash
# Fetch all labels from marketplace repo
LABELS_JSON=$(curl -s "${GITEA_API_URL}/repos/${MARKETPLACE_REPO}/labels" \
-H "Authorization: token ${GITEA_API_TOKEN}")
# Extract label IDs based on FINAL_LABELS from Step 5 or 5.1
# Build LABEL_IDS array with IDs of labels that exist in the repo
# Example for automated mode:
SOURCE_ID=$(echo "$LABELS_JSON" | jq -r '.[] | select(.name == "Source/Diagnostic") | .id')
TYPE_ID=$(echo "$LABELS_JSON" | jq -r '.[] | select(.name == "Type/Bug") | .id')
# Example for user-reported mode (adjust based on FINAL_LABELS):
# SOURCE_ID=$(echo "$LABELS_JSON" | jq -r '.[] | select(.name == "Source/User-Reported") | .id')
# TYPE_ID=$(echo "$LABELS_JSON" | jq -r '.[] | select(.name == "[TYPE_LABEL]") | .id')
# Build label array from found IDs
LABEL_IDS="[$(echo "$SOURCE_ID,$TYPE_ID" | sed 's/,,*/,/g; s/^,//; s/,$//')]"
echo "Label IDs to apply: $LABEL_IDS"
```
**3. Create issue with labels via curl:**
**Title format depends on `REPORT_MODE`:**
- Automated: `[Diagnostic] [summary of main failure]`
- User-reported: `[AFFECTED_PLUGIN] [brief summary of PROBLEM_DESCRIPTION]`
```bash
# Create temp files with restrictive permissions
DIAG_TITLE=$(mktemp -t diag-title.XXXXXX)
DIAG_BODY=$(mktemp -t diag-body.XXXXXX)
DIAG_PAYLOAD=$(mktemp -t diag-payload.XXXXXX)
# Save title (format depends on REPORT_MODE)
# Automated: "[Diagnostic] [summary of main failure]"
# User-reported: "[AFFECTED_PLUGIN] [brief summary]"
echo "[Title based on REPORT_MODE]" > "$DIAG_TITLE"
# Save body (paste Step 6 or 6.1 content) - heredoc delimiter prevents shell expansion
cat > "$DIAG_BODY" << 'DIAGNOSTIC_EOF'
[Paste the full issue content from Step 6 or 6.1 here]
DIAGNOSTIC_EOF
# Build JSON payload with labels using jq
jq -n \
--rawfile title "$DIAG_TITLE" \
--rawfile body "$DIAG_BODY" \
--argjson labels "$LABEL_IDS" \
'{title: ($title | rtrimstr("\n")), body: $body, labels: $labels}' > "$DIAG_PAYLOAD"
# Create issue using the JSON file
RESULT=$(curl -s -X POST "${GITEA_API_URL}/repos/${MARKETPLACE_REPO}/issues" \
-H "Authorization: token ${GITEA_API_TOKEN}" \
-H "Content-Type: application/json" \
-d @"$DIAG_PAYLOAD")
# Extract and display the issue URL
echo "$RESULT" | jq -r '.html_url // "Error: " + (.message // "Unknown error")'
# Secure cleanup
rm -f "$DIAG_TITLE" "$DIAG_BODY" "$DIAG_PAYLOAD"
```
**4. If no credentials found, save report locally:**
```bash
REPORT_FILE=$(mktemp -t diagnostic-report-XXXXXX.md)
cat > "$REPORT_FILE" << 'DIAGNOSTIC_EOF'
[Paste the full issue content from Step 6 here]
DIAGNOSTIC_EOF
echo "Report saved to: $REPORT_FILE"
```
Then inform the user:
```
No Gitea credentials found at ~/.config/claude/gitea.env.
Diagnostic report saved to: [REPORT_FILE]
To create the issue manually:
1. Configure credentials: See docs/CONFIGURATION.md
2. Or create issue directly at: http://gitea.hotserv.cloud/[MARKETPLACE_REPO]/issues/new
```
### Step 8: Report to User
Display summary based on `REPORT_MODE`:
**Automated Mode:**
```
Debug Report Complete
=====================
Project: [PROJECT_REPO]
Tests Run: 5
Passed: [N]
Failed: [N]
Failed Tools:
- [tool1]: [brief error]
- [tool2]: [brief error]
Issue Created: [issue URL]
Next Steps:
1. Switch to marketplace repo: cd [marketplace path]
2. Run: /debug-review
3. Select issue #[N] to investigate
```
**User-Reported Mode:**
```
Issue Report Complete
=====================
Plugin: [AFFECTED_PLUGIN]
Command: [AFFECTED_COMMAND]
Problem: [PROBLEM_TYPE]
Issue Created: [issue URL]
Your feedback has been captured. The development team will
investigate and may follow up with questions.
Next Steps:
1. Switch to marketplace repo: cd [marketplace path]
2. Run: /debug-review
3. Select issue #[N] to investigate
```
## DO NOT
- **DO NOT** attempt to fix anything - only report
- **DO NOT** create issues if all automated tests pass (unless in user-reported mode)
- **DO NOT** skip any diagnostic test in automated mode
- **DO NOT** call MCP tools without the `repo` parameter
- **DO NOT** skip user questions in user-reported mode - gather complete feedback
- **DO NOT** use MCP tools to create issues in the marketplace - always use curl (avoids branch restrictions)
## If All Tests Pass (Automated Mode Only)
If all 5 tests pass in automated mode, report success without creating an issue:
```
Debug Report Complete
=====================
Project: [PROJECT_REPO]
Tests Run: 5
Passed: 5
Failed: 0
All diagnostics passed. No issues to report.
If you're experiencing a specific problem, run /debug-report again
and select "Report an issue I experienced" to describe it.
```
## Troubleshooting
**PROJMAN_MARKETPLACE_REPO not configured**
- Ask user: "What is the marketplace repository? (e.g., personal-projects/leo-claude-mktplace)"
- Store for this session and remind user to add to .env
**Cannot detect project repository**
- Check if in a git repository: `git rev-parse --git-dir`
- If not a git repo, ask user for the repository path
**Gitea credentials not found**
- Credentials must be at `~/.config/claude/gitea.env`
- If missing, the report will be saved locally for manual submission
- See docs/CONFIGURATION.md for setup instructions
**Labels not applied to issue**
- Verify labels exist in the marketplace repo: `Source/Diagnostic`, `Type/Bug`
- Check the label fetch output in Step 7.2 for errors
- If labels don't exist, create them first with `/labels-sync` in the marketplace repo
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ Debug Report ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the diagnostic workflow.

View File

@@ -1,599 +0,0 @@
---
description: Investigate diagnostic issues and propose fixes with human approval
---
# Debug Review
Investigate diagnostic issues created by `/debug-report`, read relevant code, and propose fixes with human approval at each step.
## CRITICAL: This Command Requires Human Approval
This command has THREE mandatory approval gates. You MUST stop and wait for user confirmation at each gate before proceeding.
## Execution Steps
### Step 1: Detect Repository
Run Bash to get the current repository:
```bash
git remote get-url origin
```
Parse to extract `REPO_NAME` in `owner/repo` format.
### Step 2: Fetch Diagnostic Issues
```
mcp__plugin_projman_gitea__list_issues(
repo=REPO_NAME,
state="open",
labels=["Source: Diagnostic"]
)
```
If no issues with that label, try without label filter and look for issues with "[Diagnostic]" in title.
### Step 3: Display Issue List
Show the user available issues:
```
Debug Review
============
Open Diagnostic Issues:
#80 - [Diagnostic] get_labels fails without repo parameter
Created: 2026-01-21 | Labels: Type: Bug, Source: Diagnostic
#77 - [Diagnostic] MCP tools require explicit repo parameter
Created: 2026-01-21 | Labels: Type: Bug, Source: Diagnostic
No diagnostic issues? Showing recent bugs:
#75 - [Bug] Some other issue
Created: 2026-01-20
```
### Step 4: User Selects Issue
Use AskUserQuestion:
```
Which issue would you like to investigate?
Options: [List issue numbers]
```
Wait for user selection.
### Step 5: Fetch Full Issue Details
```
mcp__plugin_projman_gitea__get_issue(repo=REPO_NAME, issue_number=SELECTED)
```
### Step 6: Parse Diagnostic Report
Extract from the issue body:
1. **Failed Tools**: Which MCP tools failed
2. **Error Messages**: Exact error text
3. **Hypothesis**: Reporter's analysis
4. **Suggested Investigation**: Files to check
5. **Project Context**: Repo, branch, cwd where error occurred
If the issue doesn't follow the diagnostic template, extract what information is available.
### Step 7: Map Errors to Code Files
Use this mapping to identify relevant files:
**By Tool Name:**
| Tool | Primary Files |
|------|---------------|
| `validate_repo_org` | `mcp-servers/gitea/mcp_server/gitea_client.py` |
| `get_labels` | `mcp-servers/gitea/mcp_server/tools/labels.py` |
| `suggest_labels` | `mcp-servers/gitea/mcp_server/tools/labels.py` |
| `list_issues` | `mcp-servers/gitea/mcp_server/tools/issues.py` |
| `create_issue` | `mcp-servers/gitea/mcp_server/tools/issues.py` |
| `list_milestones` | `mcp-servers/gitea/mcp_server/gitea_client.py` |
**By Error Pattern:**
| Error Contains | Check Files |
|----------------|-------------|
| "owner/repo format" | `config.py`, `gitea_client.py` |
| "404" + "orgs" | `gitea_client.py` (is_org_repo method) |
| "401", "403" | `config.py` (token loading) |
| "No repository" | Command `.md` file (repo detection step) |
**By Command:**
| Command | Documentation File |
|---------|-------------------|
| `/labels-sync` | `plugins/projman/commands/labels-sync.md` |
| `/sprint-plan` | `plugins/projman/commands/sprint-plan.md` |
| `/sprint-start` | `plugins/projman/commands/sprint-start.md` |
| `/debug-report` | `plugins/projman/commands/debug-report.md` |
### Step 8: Read Relevant Files (MANDATORY)
You MUST read the identified files before proposing any fix.
For each relevant file:
1. Read the file using the Read tool
2. Find the specific function/method mentioned in the error
3. Understand the code path that leads to the error
4. Note any related code that might be affected
Display snippets of relevant code to the user:
```
Reading relevant files...
┌─ mcp-servers/gitea/mcp_server/tools/labels.py (lines 29-40) ────────┐
│ │
│ async def get_labels(self, repo: Optional[str] = None): │
│ target_repo = repo or self.gitea.repo │
│ if not target_repo or '/' not in target_repo: │
│ raise ValueError("Use 'owner/repo' format...") │
│ │
└──────────────────────────────────────────────────────────────────────┘
```
### Step 9: Present Investigation Summary
Summarize what you found:
```
Investigation Summary
=====================
ISSUE: #80 - get_labels fails without repo parameter
FAILED TOOLS:
• get_labels - "Use 'owner/repo' format"
CODE ANALYSIS:
1. labels.py:get_labels() requires repo parameter
- Line 30: `target_repo = repo or self.gitea.repo`
- Line 31-32: Raises ValueError if no repo
2. labels-sync.md documents Step 1 for repo detection
- Lines 13-26: Instructs to run `git remote get-url origin`
- This step may not be followed by executing Claude
ROOT CAUSE HYPOTHESIS:
The command documentation (labels-sync.md) correctly instructs
repo detection, but the executing Claude may be skipping Step 1
and calling MCP tools directly.
Evidence:
• Error indicates repo parameter was not passed
• labels-sync.md has correct instructions
• MCP server cannot auto-detect (sandboxed environment)
LIKELY FIX:
Option A: Make Step 1 more prominent in labels-sync.md
Option B: Add validation that repo was detected before proceeding
Option C: [Other based on analysis]
```
## APPROVAL GATE 1
```
Does this analysis match your understanding of the problem?
[Y] Yes, proceed to propose fix
[N] No, let me clarify
[R] Read more files first
```
**STOP HERE AND WAIT FOR USER RESPONSE**
Do NOT proceed until user approves.
### Step 9.5: Search Lessons Learned
Before proposing a fix, search for relevant lessons from past fixes.
**1. Extract search tags from the issue:**
```
SEARCH_TAGS = []
# Add tool names
for each failed_tool in issue:
SEARCH_TAGS.append(tool_name) # e.g., "get_labels", "validate_repo_org"
# Add error category
SEARCH_TAGS.append(error_category) # e.g., "parameter-format", "authentication"
# Add component if identifiable
if error relates to MCP server:
SEARCH_TAGS.append("mcp")
if error relates to command:
SEARCH_TAGS.append("command")
```
**2. Search lessons learned:**
```
mcp__plugin_projman_gitea__search_lessons(
repo=REPO_NAME,
tags=SEARCH_TAGS,
limit=5
)
```
**3. Also search by error keywords:**
```
mcp__plugin_projman_gitea__search_lessons(
repo=REPO_NAME,
query=[key error message words],
limit=5
)
```
**4. Display relevant lessons (if any):**
```
Related Lessons Learned
=======================
Found [N] relevant lessons from past fixes:
📚 Lesson: "Sprint 14 - Parameter validation in MCP tools"
Tags: mcp, get_labels, parameter-format
Summary: Always validate repo parameter format before API calls
Prevention: Add format check at function entry
📚 Lesson: "Sprint 12 - Graceful fallback for missing config"
Tags: configuration, fallback
Summary: Commands should work even without .env
Prevention: Check for env vars, use sensible defaults
These lessons may inform your fix approach.
```
If no lessons found, display:
```
No related lessons found. This may be a new type of issue.
```
### Step 10: Propose Fix Approach
Based on the analysis, propose a specific fix:
```
Proposed Fix
============
APPROACH: [A/B/C from above]
CHANGES NEEDED:
1. File: plugins/projman/commands/labels-sync.md
Change: Add warning box after Step 1 emphasizing repo must be detected
2. File: [if applicable]
Change: [description]
RATIONALE:
[Explain why this fix addresses the root cause]
RISKS:
[Any potential issues with this approach]
```
## APPROVAL GATE 2
```
Proceed with this fix approach?
[Y] Yes, implement it
[N] No, try different approach
[M] Modify the approach (tell me what to change)
```
**STOP HERE AND WAIT FOR USER RESPONSE**
Do NOT implement until user approves.
### Step 11: Implement Fix
Only after user approves:
1. Create feature branch:
```bash
git checkout -b fix/issue-[NUMBER]-[brief-description]
```
2. Make the code changes using Edit tool
3. Run relevant tests if they exist:
```bash
cd mcp-servers/gitea && .venv/bin/python -m pytest tests/ -v
```
4. Show the changes to user:
```bash
git diff
```
### Step 12: Present Changes
```
Changes Implemented
===================
Branch: fix/issue-80-labels-sync-instructions
Files Modified:
• plugins/projman/commands/labels-sync.md (+15, -3)
Diff Summary:
[Show git diff output]
Test Results:
• 23 passed, 0 failed (or N/A if no tests)
```
## APPROVAL GATE 3
```
Create PR with these changes?
[Y] Yes, create PR
[N] No, I want to modify something
[D] Discard changes
```
**STOP HERE AND WAIT FOR USER RESPONSE**
Do NOT create PR until user approves.
### Step 13: Create PR
Only after user approves:
1. Commit changes:
```bash
git add -A
git commit -m "fix: [description]
[Longer explanation]
Fixes #[ISSUE_NUMBER]
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>"
```
2. Push branch:
```bash
git push -u origin fix/issue-[NUMBER]-[brief-description]
```
3. Create PR via API or MCP tools
4. **Switch back to development branch** (required for MCP issue operations):
```bash
git checkout development
```
**⚠️ IMPORTANT: Issue will NOT auto-close**
PRs merged to `development` do NOT trigger Gitea's auto-close feature.
Auto-close only works when merging to the default branch (`main`).
You MUST manually close the issue in Step 15 after the PR is merged.
5. Add comment to original issue:
```
mcp__plugin_projman_gitea__add_comment(
repo=REPO_NAME,
issue_number=ISSUE_NUMBER,
comment="Fix proposed in PR #[PR_NUMBER]\n\nChanges:\n- [summary]\n\nPlease test after merge and report back."
)
```
### Step 14: Report Completion
```
Debug Review Complete
=====================
Issue: #80 - get_labels fails without repo parameter
Status: Fix Proposed
PR Created: #81 - fix: improve labels-sync repo detection instructions
URL: http://gitea.hotserv.cloud/.../pulls/81
Next Steps:
1. Review and merge PR #81
2. In test project, pull latest plugin version
3. Run /debug-report to verify fix
4. Come back and run Step 15 to close issue and capture lesson
```
### Step 15: Verify, Close, and Capture Lesson
**This step runs AFTER the user has verified the fix works.**
**⚠️ MANDATORY: You MUST manually close the issue.**
PRs merged to `development` do NOT auto-close issues (Gitea only auto-closes
on merges to the default branch `main`). Always close manually after merge.
When user returns and confirms the fix is working:
**1. Close the issue (REQUIRED - won't auto-close):**
```
mcp__plugin_projman_gitea__update_issue(
repo=REPO_NAME,
issue_number=ISSUE_NUMBER,
state="closed"
)
```
**2. Ask about lesson capture:**
Use AskUserQuestion:
```
This fix addressed [ERROR_TYPE] in [COMPONENT].
Would you like to capture this as a lesson learned?
Options:
- Yes, capture lesson (helps avoid similar issues in future)
- No, skip (trivial fix or already documented)
```
**3. If user chooses Yes, auto-generate lesson content:**
```
LESSON_TITLE = "Sprint [N] - [Brief description of fix]"
# Example: "Sprint 17 - MCP parameter validation"
LESSON_CONTENT = """
## Context
[What was happening when the issue occurred]
- Command/tool being used: [FAILED_TOOL]
- Error encountered: [ERROR_MESSAGE]
## Problem
[Root cause identified during investigation]
## Solution
[What was changed to fix it]
- Files modified: [LIST]
- PR: #[PR_NUMBER]
## Prevention
[How to avoid this in the future]
## Related
- Issue: #[ISSUE_NUMBER]
- PR: #[PR_NUMBER]
"""
LESSON_TAGS = [
tool_name, # e.g., "get_labels"
error_category, # e.g., "parameter-format"
component, # e.g., "mcp", "command"
"bug-fix"
]
```
**4. Show lesson preview and ask for approval:**
```
Lesson Preview
==============
Title: [LESSON_TITLE]
Tags: [LESSON_TAGS]
Content:
[LESSON_CONTENT]
Save this lesson? (Y/N/Edit)
```
**5. If approved, create the lesson:**
```
mcp__plugin_projman_gitea__create_lesson(
repo=REPO_NAME,
title=LESSON_TITLE,
content=LESSON_CONTENT,
tags=LESSON_TAGS,
category="sprints"
)
```
**6. Report completion:**
```
Issue Closed & Lesson Captured
==============================
Issue #[N]: CLOSED
Lesson: "[LESSON_TITLE]" saved to wiki
This lesson will be surfaced in future /debug-review
sessions when similar errors are encountered.
```
## DO NOT
- **DO NOT** skip reading relevant files - this is MANDATORY
- **DO NOT** proceed past approval gates without user confirmation
- **DO NOT** guess at fixes without evidence from code
- **DO NOT** close issues until user confirms fix works (Step 15)
- **DO NOT** commit directly to development or main branches
- **DO NOT** skip the lessons learned search - past fixes inform better solutions
## If Investigation Finds No Bug
Sometimes investigation reveals the issue is:
- User error (didn't follow documented steps)
- Configuration issue (missing .env vars)
- Already fixed in a newer version
In this case:
```
Investigation Summary
=====================
FINDING: This does not appear to be a code bug.
ANALYSIS:
[Explanation of what you found]
RECOMMENDATION:
[ ] Close issue as "not a bug" - user error
[ ] Close issue as "duplicate" of #[X]
[ ] Add documentation to prevent confusion
[ ] Other: [specify]
Would you like me to add a comment explaining this finding?
```
## Error-to-File Quick Reference
```
Error Message → File to Check
─────────────────────────────────────────────────────────────────
"Use 'owner/repo' format" → config.py, gitea_client.py
"404 Client Error.*orgs" → gitea_client.py (_is_organization)
"No repository specified" → Command .md file (Step 1)
"401 Unauthorized" → config.py (token loading)
"labels not found" → labels.py, gitea_client.py
"create local.*file" → Command .md file (DO NOT section)
```
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ Debug Review ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the investigation workflow.

View File

@@ -0,0 +1,162 @@
---
description: Diagnose issues and create reports, or investigate existing diagnostic issues
---
# Debug
## Skills Required
- skills/mcp-tools-reference.md
- skills/lessons-learned.md
- skills/git-workflow.md
## Purpose
Unified debugging command for diagnostics and issue investigation.
## Invocation
```
/debug # Ask which mode
/debug report # Run diagnostics, create issue
/debug review # Investigate existing issues
```
## Mode Selection
If no subcommand provided, ask user:
1. **Report** - Run MCP tool diagnostics and create issue in marketplace
2. **Review** - Investigate existing diagnostic issues and propose fixes
---
## Mode: Report
Create structured issues in the marketplace repository.
### Prerequisites
Project `.env` must have:
```env
PROJMAN_MARKETPLACE_REPO=personal-projects/leo-claude-mktplace
```
### Workflow
#### Step 0: Select Report Type
- **Automated** - Run MCP tool diagnostics and report failures
- **User-Reported** - Gather structured feedback about a problem
#### For User-Reported (Step 0.1)
Gather via AskUserQuestion:
1. Which plugin/command was affected
2. What was the goal
3. What type of problem (error, missing feature, unexpected behavior, docs)
4. Problem description
5. Expected behavior
6. Workaround (optional)
#### Steps 1-2: Context Gathering
1. Gather project context (git remote, branch, pwd)
2. Detect sprint context (active milestone)
3. Read marketplace config
#### Steps 3-4: Diagnostic Suite (Automated Only)
Run MCP tools with explicit `repo` parameter:
- `validate_repo_org`
- `get_labels`
- `list_issues`
- `list_milestones`
- `suggest_labels`
Categorize: Parameter Format, Authentication, Not Found, Network, Logic
#### Steps 5-6: Generate Labels and Issue
**Automated:** `Type/Bug`, `Source/Diagnostic`, `Agent/Claude` + suggested
**User-Reported:** Map problem type to labels
#### Step 7: Create Issue
**Use curl (not MCP)** - avoids branch protection issues
#### Step 8: Report to User
Show summary and link to created issue
### DO NOT (Report Mode)
- Attempt to fix anything - only report
- Create issues if all automated tests pass (unless user-reported)
- Use MCP tools to create issues in marketplace - always use curl
---
## Mode: Review
Investigate diagnostic issues and propose fixes with human approval.
### Workflow with Approval Gates
#### Steps 1-8: Investigation
1. Detect repository (git remote)
2. Fetch diagnostic issues: `list_issues(labels=["Source: Diagnostic"])`
3. Display issue list
4. User selects issue (AskUserQuestion)
5. Fetch full details: `get_issue(issue_number=...)`
6. Parse diagnostic report (failed tools, errors, hypothesis)
7. Map errors to files
8. Read relevant files - **MANDATORY before proposing fix**
#### Step 9: Investigation Summary
Present analysis to user.
**APPROVAL GATE 1:** "Does this analysis match your understanding?"
- STOP and wait for user response
#### Step 9.5: Search Lessons Learned
Search for related past fixes using `search_lessons`.
#### Step 10: Propose Fix
Present specific fix approach with changes and rationale.
**APPROVAL GATE 2:** "Proceed with this fix?"
- STOP and wait for user response
#### Steps 11-12: Implement
1. Create feature branch (`fix/issue-N-description`)
2. Make code changes
3. Run tests
4. Show diff to user
**APPROVAL GATE 3:** "Create PR with these changes?"
- STOP and wait for user response
#### Steps 13-15: Finalize
13. Commit and push
14. Create PR
15. After user verifies fix: Close issue (REQUIRED) and capture lesson
### Error-to-File Quick Reference
| Error Pattern | Check Files |
|---------------|-------------|
| "owner/repo format" | config.py, gitea_client.py |
| "404" + "orgs" | gitea_client.py |
| "401", "403" | config.py (token) |
| "No repository" | Command .md file |
### DO NOT (Review Mode)
- Skip reading relevant files
- Proceed past approval gates without confirmation
- Close issues until user confirms fix works
- Commit directly to development/main
---
## Visual Output
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ 🔧 DEBUG ║
║ [Mode: Report | Review] ║
╚══════════════════════════════════════════════════════════════════╝
```

View File

@@ -1,477 +0,0 @@
---
description: Interactive setup wizard for projman plugin - configures MCP servers, credentials, and project settings
---
# Initial Setup Wizard
This command guides the user through complete projman setup interactively. It handles both first-time marketplace setup and per-project configuration.
## Important Context
- **This command uses Bash, Read, Write, and AskUserQuestion tools** - NOT MCP tools
- **MCP tools won't work until after setup + session restart**
- **Tokens must be entered manually by the user** for security (not typed into chat)
---
## Quick Path Detection
**FIRST**, check if system-level setup is already complete:
```bash
cat ~/.config/claude/gitea.env 2>/dev/null | grep -v "^#" | grep -v "PASTE_YOUR" | grep -v "example.com" | grep "GITEA_API_TOKEN=" && echo "SYSTEM_CONFIGURED" || echo "SYSTEM_NEEDS_SETUP"
```
**If SYSTEM_CONFIGURED:**
The system-level configuration already exists. Offer the user a choice:
Use AskUserQuestion:
- Question: "System configuration found. What would you like to do?"
- Header: "Setup Mode"
- Options:
- "Quick project setup only (Recommended for new projects)"
- "Full setup (re-check everything)"
**If "Quick project setup":**
- Skip directly to **Phase 4: Project-Level Configuration**
- This is equivalent to running `/project-init`
**If "Full setup":**
- Continue with Phase 1 below
**If SYSTEM_NEEDS_SETUP:**
- Continue with Phase 1 (full setup required)
---
## Phase 1: Environment Validation
### Step 1.1: Check Python Version
Run this command to verify Python 3.10+ is available:
```bash
python3 --version
```
**If version is below 3.10:**
- Stop setup and inform user: "Python 3.10 or higher is required. Please install it and run /initial-setup again."
- Provide installation hints based on OS (apt, brew, etc.)
**If successful:** Continue to next step.
---
## Phase 2: MCP Server Setup
### Step 2.1: Locate the Plugin Installation
The plugin is installed somewhere on the system. Find the MCP server directory by resolving the path.
First, identify where this plugin is installed. The MCP server should be accessible via the symlink structure. Look for the gitea MCP server:
```bash
# Find the plugin's mcp-servers directory (search common locations)
find ~/.claude ~/.config/claude -name "mcp_server" -path "*gitea*" 2>/dev/null | head -5
```
If found, extract the parent path (the gitea MCP server root).
**Alternative:** If the user knows the marketplace location, ask them:
Use AskUserQuestion:
- Question: "Where is the Leo Claude Marketplace installed?"
- Options:
- "~/.claude/plugins/leo-claude-mktplace" (default Claude plugins location)
- "Let me find it automatically"
- Other (user provides path)
### Step 2.2: Check if Virtual Environment Exists
Once you have the MCP server path (e.g., `/path/to/mcp-servers/gitea`), check for the venv:
```bash
ls -la /path/to/mcp-servers/gitea/.venv/bin/python 2>/dev/null && echo "VENV_EXISTS" || echo "VENV_MISSING"
```
### Step 2.3: Create Virtual Environment (if missing)
If venv doesn't exist:
```bash
cd /path/to/mcp-servers/gitea && python3 -m venv .venv
```
Then install dependencies:
```bash
cd /path/to/mcp-servers/gitea && source .venv/bin/activate && pip install --upgrade pip && pip install -r requirements.txt && deactivate
```
**If pip install fails:**
- Show the error to the user
- Suggest: "Check your internet connection and try again. You can also manually run: `cd /path/to/mcp-servers/gitea && source .venv/bin/activate && pip install -r requirements.txt`"
### Step 2.4: NetBox MCP Server (Optional)
Check if the user wants to set up the NetBox MCP server (for cmdb-assistant plugin):
Use AskUserQuestion:
- Question: "Do you want to set up the NetBox MCP server for infrastructure management?"
- Options:
- "Yes, set up NetBox MCP"
- "No, skip NetBox (Recommended if not using cmdb-assistant)"
If yes, repeat steps 2.2-2.3 for `/path/to/mcp-servers/netbox`.
---
## Phase 3: System-Level Configuration
System configuration is stored in `~/.config/claude/` and contains credentials that work across all projects.
### Step 3.1: Create Config Directory
```bash
mkdir -p ~/.config/claude
```
### Step 3.2: Check Gitea Configuration
```bash
cat ~/.config/claude/gitea.env 2>/dev/null || echo "FILE_NOT_FOUND"
```
**If file doesn't exist:** Go to Step 3.3 (Create Template)
**If file exists:** Read it and check if values are placeholders (contain "example.com" or "your_" or "token_here"). If placeholders, go to Step 3.4 (Update Existing).
**If file has real values:** Go to Step 3.5 (Validate).
### Step 3.3: Create Gitea Configuration Template
Gather the Gitea server URL from the user.
Use AskUserQuestion:
- Question: "What is your Gitea server URL? (e.g., https://gitea.company.com)"
- Header: "Gitea URL"
- Options:
- "https://gitea.hotserv.cloud" (if this is Leo's setup)
- "Other (I'll provide the URL)"
If "Other", ask the user to type the URL.
Now create the configuration file with a placeholder for the token:
```bash
cat > ~/.config/claude/gitea.env << 'EOF'
# Gitea API Configuration
# Generated by /initial-setup
# Note: GITEA_ORG is configured per-project in .env
GITEA_API_URL=<USER_PROVIDED_URL>
GITEA_API_TOKEN=PASTE_YOUR_TOKEN_HERE
EOF
chmod 600 ~/.config/claude/gitea.env
```
Replace `<USER_PROVIDED_URL>` with the actual value from the user.
### Step 3.4: Token Entry Instructions
**CRITICAL: Do not ask the user to type the token into chat.**
Display these instructions clearly:
---
**Action Required: Add Your Gitea API Token**
I've created the configuration file at `~/.config/claude/gitea.env` but you need to add your API token manually for security.
**Steps:**
1. Open the file in your editor:
```
nano ~/.config/claude/gitea.env
```
Or use any editor you prefer.
2. Generate a Gitea token (if you don't have one):
- Go to your Gitea instance → User Icon → Settings
- Click "Applications" tab
- Under "Manage Access Tokens", click "Generate New Token"
- Name it something like "claude-code"
- Select permissions: `repo` (all), `read:org`, `read:user`
- Click "Generate Token" and copy it immediately
3. Replace `PASTE_YOUR_TOKEN_HERE` with your actual token
4. Save the file
---
Use AskUserQuestion:
- Question: "Have you added your Gitea token to ~/.config/claude/gitea.env?"
- Header: "Token Added?"
- Options:
- "Yes, I've added the token"
- "I need help generating a token"
- "Skip for now (I'll do it later)"
**If "I need help":** Provide detailed instructions for their specific Gitea instance.
**If "Skip":** Warn that MCP tools won't work until configured, but continue with project setup.
### Step 3.5: Validate Gitea Configuration
Read the config file and verify it has non-placeholder values:
```bash
source ~/.config/claude/gitea.env && echo "URL: $GITEA_API_URL" && echo "TOKEN_LENGTH: ${#GITEA_API_TOKEN}"
```
If TOKEN_LENGTH is less than 10 or contains "PASTE" or "your_", the token hasn't been set properly.
**Note:** GITEA_ORG is configured per-project in `.env`, not in the system-level config.
**Test connectivity (optional but recommended):**
```bash
source ~/.config/claude/gitea.env && curl -s -o /dev/null -w "%{http_code}" -H "Authorization: token $GITEA_API_TOKEN" "$GITEA_API_URL/user"
```
- **200:** Success! Credentials are valid.
- **401:** Invalid token.
- **404/Connection error:** Invalid URL or network issue.
Report the result to the user.
### Step 3.6: Git-Flow Configuration (Optional)
Use AskUserQuestion:
- Question: "Do you want to configure git-flow defaults for smart commits?"
- Header: "Git-Flow"
- Options:
- "Yes, use recommended defaults (Recommended)"
- "Yes, let me customize"
- "No, skip git-flow configuration"
If yes with defaults:
```bash
cat > ~/.config/claude/git-flow.env << 'EOF'
# Git-Flow Default Configuration
GIT_WORKFLOW_STYLE=feature-branch
GIT_DEFAULT_BASE=development
GIT_AUTO_DELETE_MERGED=true
GIT_AUTO_PUSH=false
GIT_PROTECTED_BRANCHES=main,master,development,staging,production
GIT_COMMIT_STYLE=conventional
GIT_CO_AUTHOR=true
EOF
chmod 600 ~/.config/claude/git-flow.env
```
If customize, use AskUserQuestion for each setting.
---
## Phase 4: Project-Level Configuration
Project configuration is stored in `.env` in the current project root.
### Step 4.1: Verify Current Directory
Confirm we're in the right place:
```bash
pwd && git rev-parse --show-toplevel 2>/dev/null || echo "NOT_A_GIT_REPO"
```
If not a git repo, ask the user:
Use AskUserQuestion:
- Question: "The current directory doesn't appear to be a git repository. Where should I create the project configuration?"
- Options:
- "This directory is correct, continue anyway"
- "Let me navigate to the right directory first"
### Step 4.2: Check Existing Project Configuration
```bash
cat .env 2>/dev/null || echo "FILE_NOT_FOUND"
```
If `.env` exists and has `GITEA_REPO=` set to a non-placeholder value, skip to Phase 5.
### Step 4.3: Infer Organization and Repository from Git Remote
Try to detect org and repo name automatically:
```bash
git remote get-url origin 2>/dev/null
```
Parse the output to extract both organization and repository:
- `git@gitea.example.com:org/repo-name.git` → org: `org`, repo: `repo-name`
- `https://gitea.example.com/org/repo-name.git` → org: `org`, repo: `repo-name`
Extract organization:
```bash
git remote get-url origin 2>/dev/null | sed 's/.*[:/]\([^/]*\)\/[^/]*$/\1/'
```
Extract repository:
```bash
git remote get-url origin 2>/dev/null | sed 's/.*[:/]\([^/]*\)\.git$/\1/' | sed 's/.*\/\([^/]*\)$/\1/'
```
### Step 4.4: Validate Repository via Gitea API
**Before asking for confirmation**, verify the repository exists and is accessible:
```bash
source ~/.config/claude/gitea.env
curl -s -o /dev/null -w "%{http_code}" -H "Authorization: token $GITEA_API_TOKEN" "$GITEA_API_URL/repos/<detected-org>/<detected-repo>"
```
**Based on response:**
| HTTP Code | Meaning | Action |
|-----------|---------|--------|
| **200** | Repository exists and accessible | **Auto-fill without asking** - skip to Step 4.7 |
| **404** | Repository not found | Ask user to confirm/correct (Step 4.5) |
| **401/403** | Token issue or no access | Warn about permissions, ask to confirm |
| **Other** | Network/server issue | Warn, ask to confirm manually |
**If 200 OK:** Display confirmation message and skip to Step 4.7:
"Verified: Repository '<detected-org>/<detected-repo>' exists and is accessible."
### Step 4.5: Confirm Organization (only if API validation failed)
Use AskUserQuestion:
- Question: "Repository '<detected-org>/<detected-repo>' was not found. Is '<detected-org>' the correct organization?"
- Header: "Organization"
- Options:
- "Yes, that's correct"
- "No, let me specify the correct organization"
If no, ask user to provide the correct organization name.
### Step 4.6: Confirm Repository Name (only if API validation failed)
Use AskUserQuestion:
- Question: "Is '<detected-repo-name>' the correct Gitea repository name?"
- Header: "Repository"
- Options:
- "Yes, that's correct"
- "No, let me specify the correct name"
If no, ask user to provide the correct name.
**After user provides corrections, re-validate via API (Step 4.4)** to ensure the corrected values are valid.
### Step 4.7: Create Project Configuration
```bash
cat > .env << 'EOF'
# Project Configuration for projman
# Generated by /initial-setup
GITEA_ORG=<ORG_NAME>
GITEA_REPO=<REPO_NAME>
EOF
```
Replace `<REPO_NAME>` with the confirmed value.
**Important:** Check if `.env` is in `.gitignore`:
```bash
grep -q "^\.env$" .gitignore 2>/dev/null && echo "GITIGNORE_OK" || echo "GITIGNORE_MISSING"
```
If not in `.gitignore`, warn the user:
"Warning: `.env` is not in your `.gitignore`. Consider adding it to prevent accidentally committing credentials."
---
## Phase 5: Final Validation and Next Steps
### Step 5.1: Summary Report
Display a summary of what was configured:
```
╔══════════════════════════════════════════════════════════════╗
║ SETUP COMPLETE ║
╠══════════════════════════════════════════════════════════════╣
║ MCP Server (Gitea): ✓ Installed ║
║ System Config: ✓ ~/.config/claude/gitea.env ║
║ Project Config: ✓ ./.env ║
║ Gitea Connection: ✓ Verified (or ⚠ Not tested) ║
╚══════════════════════════════════════════════════════════════╝
```
### Step 5.2: Session Restart Notice
**IMPORTANT:** Display this notice clearly:
---
**⚠️ Session Restart Required**
The MCP server has been configured but won't be available until you restart your Claude Code session.
**To complete setup:**
1. Exit this Claude Code session (type `/exit` or close the terminal)
2. Start a new Claude Code session in this project
3. The Gitea MCP tools will now be available
**After restart, you can:**
- Run `/labels-sync` to sync your label taxonomy
- Run `/sprint-plan` to start planning
- Use MCP tools like `list_issues`, `create_issue`, etc.
---
### Step 5.3: Troubleshooting Checklist
If something isn't working after restart, check:
1. **MCP server not found:** Verify venv exists at the expected path
2. **Authentication failed:** Re-check token in `~/.config/claude/gitea.env`
3. **Wrong repository:** Verify `GITEA_REPO` in `./.env` matches Gitea exactly
4. **Network error:** Ensure Gitea URL is accessible from this machine
---
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ ⚙️ SETUP ║
║ Initial Setup Wizard ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the setup workflow.
## Re-Running This Command
This command is safe to run multiple times:
- Existing venvs are skipped (not recreated)
- Existing config files are checked for validity
- Only missing or placeholder values are updated
- Project config can be regenerated for new projects
---
## Quick Reference: Files Created
| File | Purpose | Contains |
|------|---------|----------|
| `~/.config/claude/gitea.env` | System credentials | URL, token, org |
| `~/.config/claude/git-flow.env` | Git defaults | Workflow settings |
| `./.env` | Project settings | Repository name |
| `<mcp-server>/.venv/` | Python environment | Dependencies |

View File

@@ -2,179 +2,52 @@
description: Fetch and validate label taxonomy from Gitea, create missing required labels
---
# Sync Label Taxonomy from Gitea
# Sync Label Taxonomy
This command fetches the current label taxonomy from Gitea (organization + repository labels), validates that required labels exist, and creates any missing ones.
## Skills Required
## CRITICAL: Execution Steps
- skills/mcp-tools-reference.md
- skills/repo-validation.md
- skills/label-taxonomy/labels-reference.md
You MUST follow these steps in order. Do NOT skip any step.
## Purpose
### Step 1: Detect Repository from Git Remote
Fetch current label taxonomy from Gitea, validate required labels exist, and create any missing ones.
Run this Bash command to get the git remote URL:
## Invocation
```bash
git remote get-url origin
```
Run `/labels-sync` when setting up the plugin or after taxonomy updates.
Parse the output to extract `owner/repo`:
- SSH format `ssh://git@host:port/owner/repo.git` → extract `owner/repo`
- SSH short `git@host:owner/repo.git` → extract `owner/repo`
- HTTPS `https://host/owner/repo.git` → extract `owner/repo`
## Workflow
Store this as `REPO_NAME` for all subsequent MCP calls.
1. **Detect Repository** - Parse `git remote get-url origin` to get `owner/repo`
2. **Validate Repository** - Use `validate_repo_org` to check if org-owned
3. **Fetch Labels** - Use `get_labels(repo=...)` to get org + repo labels
4. **Display Taxonomy** - Show labels grouped by category
5. **Check Required Labels** - Verify Type/*, Priority/*, Complexity/*, Effort/* exist
6. **Create Missing** - Use `create_label_smart` which auto-detects org vs repo level
7. **Report Results** - Summarize what was found and created
### Step 2: Validate Repository Organization
## Required Label Categories
Call MCP tool with the detected repo:
```
mcp__plugin_projman_gitea__validate_repo_org(repo=REPO_NAME)
```
This determines if the owner is an organization or user account.
### Step 3: Fetch Labels from Gitea
Call MCP tool with the detected repo:
```
mcp__plugin_projman_gitea__get_labels(repo=REPO_NAME)
```
This returns both organization labels (if org-owned) and repository labels.
### Step 4: Display Current Taxonomy
Show the user:
- Total organization labels count
- Total repository labels count
- Labels grouped by category (Type/*, Priority/*, etc.)
### Step 5: Check Required Labels
Verify these required label categories exist:
- **Type/***: Bug, Feature, Refactor, Documentation, Test, Chore
- **Priority/***: Low, Medium, High, Critical
- **Complexity/***: Simple, Medium, Complex
- **Effort/***: XS, S, M, L, XL (note: may be "Effort" or "Efforts")
### Step 6: Create Missing Labels (if any)
Use `create_label_smart` which automatically creates labels at the correct level:
- **Organization level**: Type/*, Priority/*, Complexity/*, Effort/*, Risk/*, Source/*, Agent/*
- **Repository level**: Component/*, Tech/*
```
mcp__plugin_projman_gitea__create_label_smart(repo=REPO_NAME, name="Type/Bug", color="d73a4a")
```
This automatically detects whether to create at org or repo level based on the category.
**Alternative (explicit control):**
- Org labels: `create_org_label(org="org-name", name="Type/Bug", color="d73a4a")`
- Repo labels: `create_label(repo=REPO_NAME, name="Component/Backend", color="5319e7")`
Use the label format that matches existing labels in the repo (slash `/` or colon-space `: `).
### Step 7: Report Results
Summarize what was found and created.
| Category | Required Labels |
|----------|-----------------|
| Type/* | Bug, Feature, Refactor, Documentation, Test, Chore |
| Priority/* | Low, Medium, High, Critical |
| Complexity/* | Simple, Medium, Complex |
| Efforts/* | XS, S, M, L, XL |
## DO NOT
- **DO NOT** call MCP tools without the `repo` parameter - they will fail
- **DO NOT** create any local files - this command only interacts with Gitea
- **DO NOT** ask the user questions - execute autonomously
- **DO NOT** create a "labels reference file" - labels are fetched dynamically from Gitea
## MCP Tools Used
All tools require the `repo` parameter in `owner/repo` format:
| Tool | Purpose |
|------|---------|
| `validate_repo_org(repo=...)` | Check if owner is organization or user |
| `get_labels(repo=...)` | Fetch all labels (org + repo) |
| `create_label(repo=..., name=..., color=...)` | Create missing labels |
## Expected Output
```
Label Taxonomy Sync
===================
Detecting repository from git remote...
Repository: personal-projects/your-repo-name
Owner type: Organization
Fetching labels from Gitea...
Current Label Taxonomy:
- Organization Labels: 27
- Repository Labels: 16
- Total: 43 labels
Organization Labels by Category:
Type/*: 6 labels
Priority/*: 4 labels
Complexity/*: 3 labels
Effort/*: 5 labels
...
Repository Labels by Category:
Component/*: 9 labels
Tech/*: 7 labels
Required Labels Check:
Type/*: 6/6 present ✓
Priority/*: 4/4 present ✓
Complexity/*: 3/3 present ✓
Effort/*: 5/5 present ✓
All required labels present. Label taxonomy is ready for use.
```
## Label Format Detection
Labels may use different naming conventions:
- Slash format: `Type/Bug`, `Priority/High`
- Colon-space format: `Type: Bug`, `Priority: High`
When creating missing labels, match the format used by existing labels in the repository.
## Troubleshooting
**Error: Use 'owner/repo' format**
- You forgot to pass the `repo` parameter to the MCP tool
- Go back to Step 1 and detect the repo from git remote
**Empty organization labels**
- If owner is a user account (not org), organization labels will be empty
- This is expected - user accounts only have repository-level labels
**Git remote not found**
- Ensure you're running in a directory with a git repository
- Check that the `origin` remote is configured
- Call MCP tools without the `repo` parameter
- Create local files - this command only interacts with Gitea
- Ask user questions - execute autonomously
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ Labels Sync ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the sync workflow.
## When to Run
Run `/labels-sync` when:
- Setting up the plugin for the first time
- You notice missing labels in suggestions
- New labels are added to Gitea
- After major taxonomy updates

View File

@@ -1,232 +0,0 @@
---
description: Quick project setup - configures only project-level settings (assumes system setup is complete)
---
# Project Initialization
Fast setup for a new project when system-level configuration is already complete.
**Use this when:**
- You've already run `/initial-setup` on this machine
- You're starting work on a new project/repository
- You just need to create the project `.env` file
**Use `/initial-setup` instead if:**
- This is your first time using the plugin
- MCP tools aren't working (might need system setup)
---
## Pre-Flight Check
### Step 1: Verify System Configuration Exists
Quickly verify system setup is complete:
```bash
cat ~/.config/claude/gitea.env 2>/dev/null | grep -v "^#" | grep -v "PASTE_YOUR" | grep "GITEA_API_TOKEN=" && echo "SYSTEM_OK" || echo "SYSTEM_MISSING"
```
**If SYSTEM_MISSING:**
Display this message and stop:
---
**System configuration not found or incomplete.**
It looks like the system-level setup hasn't been completed yet. Please run:
```
/initial-setup
```
This will configure both system credentials and this project.
---
**If SYSTEM_OK:** Continue to project setup.
---
## Project Setup
### Step 2: Verify Current Directory
```bash
pwd && git rev-parse --show-toplevel 2>/dev/null || echo "NOT_A_GIT_REPO"
```
If not a git repo, ask:
Use AskUserQuestion:
- Question: "This doesn't appear to be a git repository. Continue anyway?"
- Header: "Directory"
- Options:
- "Yes, continue here"
- "No, I'll navigate to the correct directory"
### Step 3: Check for Existing Configuration
```bash
cat .env 2>/dev/null | grep "GITEA_REPO=" || echo "NOT_CONFIGURED"
```
**If already configured:**
Use AskUserQuestion:
- Question: "This project already has GITEA_ORG and GITEA_REPO configured. What would you like to do?"
- Header: "Existing"
- Options:
- "Keep existing configuration"
- "Reconfigure (replace current settings)"
**If "Keep":** End with success message.
### Step 4: Detect Organization and Repository
Try to auto-detect from git remote:
```bash
git remote get-url origin 2>/dev/null
```
Extract organization:
```bash
git remote get-url origin 2>/dev/null | sed 's/.*[:/]\([^/]*\)\/[^/]*$/\1/'
```
Extract repository:
```bash
git remote get-url origin 2>/dev/null | sed 's/.*[:/]\([^/]*\)\.git$/\1/' | sed 's/.*\/\([^/]*\)$/\1/'
```
### Step 5: Validate Repository via Gitea API
Verify the repository exists and is accessible:
```bash
source ~/.config/claude/gitea.env
curl -s -o /dev/null -w "%{http_code}" -H "Authorization: token $GITEA_API_TOKEN" "$GITEA_API_URL/repos/<detected-org>/<detected-repo>"
```
| HTTP Code | Action |
|-----------|--------|
| **200** | Auto-fill - display "Verified: <org>/<repo> exists" and skip to Step 8 |
| **404** | Repository not found - proceed to Step 6 |
| **401/403** | Permission issue - warn and proceed to Step 6 |
### Step 6: Confirm Organization (only if API validation failed)
Use AskUserQuestion:
- Question: "Repository not found. Is '<detected-org>' the correct organization?"
- Header: "Organization"
- Options:
- "Yes, that's correct"
- "No, let me specify"
If "No", ask user to type the correct organization name.
### Step 7: Confirm Repository Name (only if API validation failed)
Use AskUserQuestion:
- Question: "Is '<detected-repo-name>' the correct repository name?"
- Header: "Repository"
- Options:
- "Yes, that's correct"
- "No, let me specify"
If "No", ask user to type the correct name.
**After corrections, re-validate via API (Step 5).**
### Step 8: Create/Update Project Configuration
**If `.env` exists:**
Check if it already has other content and append:
```bash
echo "" >> .env
echo "# Added by /project-init" >> .env
echo "GITEA_ORG=<ORG_NAME>" >> .env
echo "GITEA_REPO=<REPO_NAME>" >> .env
```
**If `.env` doesn't exist:**
```bash
cat > .env << 'EOF'
# Project Configuration for projman
# Generated by /project-init
GITEA_ORG=<ORG_NAME>
GITEA_REPO=<REPO_NAME>
EOF
```
### Step 9: Check .gitignore
```bash
grep -q "^\.env$" .gitignore 2>/dev/null && echo "GITIGNORE_OK" || echo "GITIGNORE_MISSING"
```
**If GITIGNORE_MISSING:**
Use AskUserQuestion:
- Question: "`.env` is not in `.gitignore`. Add it to prevent committing secrets?"
- Header: "gitignore"
- Options:
- "Yes, add .env to .gitignore (Recommended)"
- "No, I'll handle it manually"
If yes:
```bash
echo ".env" >> .gitignore
```
---
## Complete
Display success message:
```
╔══════════════════════════════════════════════════════════════╗
║ PROJECT CONFIGURED ║
╠══════════════════════════════════════════════════════════════╣
║ Organization: <ORG_NAME> ║
║ Repository: <REPO_NAME> ║
║ Config file: ./.env ║
╚══════════════════════════════════════════════════════════════╝
You're ready to use projman commands:
• /sprint-plan - Start sprint planning
• /sprint-status - Check progress
• /labels-sync - Sync label taxonomy
```
---
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ ⚙️ SETUP ║
║ Project Initialization ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the project setup workflow.
## Troubleshooting
**MCP tools not working?**
- Run `/initial-setup` for full setup including MCP server
- Restart your Claude Code session after setup
**Wrong repository configured?**
- Edit `.env` directly: `nano .env`
- Or run `/project-init` again and choose "Reconfigure"

View File

@@ -1,210 +0,0 @@
---
description: Sync project configuration with current git remote - use after changing repository location or organization
---
# Project Sync
Updates project configuration when the git remote URL has changed (repository moved, renamed, or organization changed).
**Use this when:**
- You moved the repository to a different organization
- You renamed the repository
- You changed the git remote URL
- The SessionStart hook detected a mismatch
---
## Step 1: Verify System Configuration
```bash
cat ~/.config/claude/gitea.env 2>/dev/null | grep -v "^#" | grep -v "PASTE_YOUR" | grep "GITEA_API_TOKEN=" && echo "SYSTEM_OK" || echo "SYSTEM_MISSING"
```
**If SYSTEM_MISSING:** Stop and instruct user to run `/initial-setup` first.
---
## Step 2: Read Current Configuration
Read the current .env values:
```bash
cat .env 2>/dev/null
```
Extract current values:
- `CURRENT_ORG` from `GITEA_ORG=...`
- `CURRENT_REPO` from `GITEA_REPO=...`
**If .env doesn't exist or has no GITEA values:** Redirect to `/project-init`.
---
## Step 3: Detect Git Remote Values
Get the current git remote:
```bash
git remote get-url origin 2>/dev/null
```
Extract organization:
```bash
git remote get-url origin 2>/dev/null | sed 's/.*[:/]\([^/]*\)\/[^/]*$/\1/'
```
Extract repository:
```bash
git remote get-url origin 2>/dev/null | sed 's/.*[:/]\([^/]*\)\.git$/\1/' | sed 's/.*\/\([^/]*\)$/\1/'
```
---
## Step 4: Compare Values
Compare current .env values with detected git remote values:
| Scenario | Action |
|----------|--------|
| **Both match** | Display "Configuration is in sync" and exit |
| **Organization changed** | Proceed to Step 5 |
| **Repository changed** | Proceed to Step 5 |
| **Both changed** | Proceed to Step 5 |
**If already in sync:**
```
╔══════════════════════════════════════════════════════════════╗
║ CONFIGURATION IN SYNC ║
╠══════════════════════════════════════════════════════════════╣
║ Organization: <ORG_NAME> ║
║ Repository: <REPO_NAME> ║
║ Git Remote: matches .env ║
╚══════════════════════════════════════════════════════════════╝
```
Exit here if in sync.
---
## Step 5: Show Detected Changes
Display the detected changes to the user:
```
╔══════════════════════════════════════════════════════════════╗
║ REPOSITORY CHANGE DETECTED ║
╠══════════════════════════════════════════════════════════════╣
║ Current .env │ Git Remote ║
║ Organization: <OLD_ORG> │ <NEW_ORG> ║
║ Repository: <OLD_REPO> │ <NEW_REPO> ║
╚══════════════════════════════════════════════════════════════╝
```
---
## Step 6: Validate New Repository via Gitea API
Verify the new repository exists and is accessible:
```bash
source ~/.config/claude/gitea.env
curl -s -o /dev/null -w "%{http_code}" -H "Authorization: token $GITEA_API_TOKEN" "$GITEA_API_URL/repos/<NEW_ORG>/<NEW_REPO>"
```
| HTTP Code | Action |
|-----------|--------|
| **200** | Repository verified - proceed to Step 7 |
| **404** | Repository not found - ask user to confirm (Step 6a) |
| **401/403** | Permission issue - warn and ask to confirm |
### Step 6a: Confirm if API Validation Failed
Use AskUserQuestion:
- Question: "The new repository '<NEW_ORG>/<NEW_REPO>' was not found via API. Update configuration anyway?"
- Header: "Not Found"
- Options:
- "Yes, update anyway (I'll fix the remote later)"
- "No, let me fix the git remote first"
- "Let me specify different values"
**If "specify different values":** Ask for correct org and repo, then re-validate.
---
## Step 7: Confirm Update
Use AskUserQuestion:
- Question: "Update project configuration to match git remote?"
- Header: "Confirm"
- Options:
- "Yes, update .env (Recommended)"
- "No, keep current configuration"
**If "No":** Exit without changes.
---
## Step 8: Update Configuration
Update the .env file with new values:
```bash
# Update GITEA_ORG
sed -i 's/^GITEA_ORG=.*/GITEA_ORG=<NEW_ORG>/' .env
# Update GITEA_REPO
sed -i 's/^GITEA_REPO=.*/GITEA_REPO=<NEW_REPO>/' .env
```
Alternatively, if sed doesn't work well, read the file, replace values, and write back.
---
## Step 9: Verify Update
Read the updated .env and display confirmation:
```
╔══════════════════════════════════════════════════════════════╗
║ CONFIGURATION UPDATED ║
╠══════════════════════════════════════════════════════════════╣
║ Organization: <NEW_ORG> ║
║ Repository: <NEW_REPO> ║
║ Status: In sync with git remote ║
╚══════════════════════════════════════════════════════════════╝
Your project configuration has been updated.
MCP tools will now use the new repository.
```
---
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ ⚙️ SETUP ║
║ Project Sync ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the sync workflow.
## Troubleshooting
**"Repository not found" but it exists:**
- Check your Gitea token has access to the new organization
- Verify the repository name matches exactly (case-sensitive)
- Ensure your token has `repo` permissions
**Git remote URL is wrong:**
- Fix it first: `git remote set-url origin <correct-url>`
- Then run `/project-sync` again
**Want to revert the change:**
- Edit `.env` manually: `nano .env`
- Or run `/project-sync` after fixing the git remote

View File

@@ -4,131 +4,46 @@ description: View proposal and implementation hierarchy with status tracking
# Proposal Status
View the status of all change proposals and their implementations in the Gitea Wiki.
## Skills Required
## Overview
- skills/mcp-tools-reference.md
- skills/wiki-conventions.md
This command provides a tree view of:
- All change proposals (`Change VXX.X.X: Proposal`)
- Their implementations (`Change VXX.X.X: Proposal (Implementation N)`)
- Linked issues and lessons learned
## Purpose
View status of all change proposals and their implementations in Gitea Wiki.
## Invocation
```
/proposal-status
/proposal-status --version V04.1.0
/proposal-status --status "In Progress"
```
## Workflow
1. **Fetch All Wiki Pages**
- Use `list_wiki_pages()` to get all wiki pages
- Filter for pages matching `Change V*: Proposal*` pattern
2. **Parse Proposal Structure**
- Group implementations under their parent proposals
- Extract status from page metadata (In Progress, Implemented, Abandoned)
3. **Fetch Linked Artifacts**
- For each implementation, search for issues referencing it
- Search lessons learned that link to the implementation
4. **Display Tree View**
```
Change V04.1.0: Proposal [In Progress]
├── Implementation 1 [In Progress] - 2026-01-26
│ ├── Issues: #161, #162, #163, #164
│ └── Lessons: (pending)
└── Implementation 2 [Not Started]
Change V04.0.0: Proposal [Implemented]
└── Implementation 1 [Implemented] - 2026-01-20
├── Issues: #150, #151
└── Lessons: v4.0.0-impl-1-lessons
```
## MCP Tools Used
- `list_wiki_pages()` - List all wiki pages
- `get_wiki_page(page_name)` - Get page content for status extraction
- `list_issues(state, labels)` - Find linked issues
- `search_lessons(query, tags)` - Find linked lessons
1. **Fetch Wiki Pages** - Use `list_wiki_pages()` to get all pages
2. **Filter Proposals** - Match `Change V*: Proposal*` pattern
3. **Parse Structure** - Group implementations under parent proposals
4. **Extract Status** - Read page metadata (In Progress, Implemented, Abandoned)
5. **Fetch Linked Artifacts** - Find issues and lessons referencing each implementation
6. **Display Tree View** - Show hierarchy with status and links
## Status Definitions
| Status | Meaning |
|--------|---------|
| **Pending** | Proposal created but no implementation started |
| **In Progress** | At least one implementation is active |
| **Implemented** | All planned implementations complete |
| **Abandoned** | Proposal was cancelled or superseded |
## Filtering Options
The command accepts optional filters:
```
/proposal-status # Show all proposals
/proposal-status --version V04.1.0 # Show specific version
/proposal-status --status "In Progress" # Filter by status
```
## Example Output
```
Proposal Status Report
======================
Change V04.1.0: Wiki-Based Planning Workflow [In Progress]
├── Implementation 1 [In Progress] - Started: 2026-01-26
│ ├── Issues: #161 (closed), #162 (closed), #163 (closed), #164 (open)
│ └── Lessons: (pending - sprint not closed)
└── (No additional implementations planned)
Change V04.0.0: MCP Server Consolidation [Implemented]
├── Implementation 1 [Implemented] - 2026-01-15 to 2026-01-20
│ ├── Issues: #150 (closed), #151 (closed), #152 (closed)
│ └── Lessons:
│ • Sprint 15 - MCP Server Symlink Best Practices
│ • Sprint 15 - Venv Path Resolution in Plugins
└── (Complete)
Change V03.2.0: Label Taxonomy Sync [Implemented]
└── Implementation 1 [Implemented] - 2026-01-10 to 2026-01-12
├── Issues: #140 (closed), #141 (closed)
└── Lessons:
• Sprint 14 - Organization vs Repository Labels
Summary:
- Total Proposals: 3
- In Progress: 1
- Implemented: 2
- Pending: 0
```
## Implementation Notes
**Page Name Parsing:**
- Proposals: `Change VXX.X.X: Proposal` or `Change Sprint-NN: Proposal`
- Implementations: `Change VXX.X.X: Proposal (Implementation N)`
**Status Extraction:**
- Parse the `> **Status:**` line from page metadata
- Default to "Unknown" if not found
**Issue Linking:**
- Search for issues containing wiki link in body
- Or search for issues with `[Sprint XX]` prefix matching implementation
**Lesson Linking:**
- Search lessons with implementation link in metadata
- Or search by version/sprint tags
| Pending | Proposal created, no implementation started |
| In Progress | At least one implementation is active |
| Implemented | All planned implementations complete |
| Abandoned | Proposal cancelled or superseded |
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ Proposal Status ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the status report.

View File

@@ -1,83 +1,47 @@
---
name: review
description: Pre-sprint-close code quality review
agent: code-reviewer
---
# Code Review for Sprint Close
Review the recent code changes for quality issues before closing the sprint.
## Skills Required
## Review Checklist
- skills/review-checklist.md
Analyze the changes and report on:
## Purpose
### 1. Debug Artifacts
- [ ] TODO/FIXME comments that should be resolved or converted to issues
- [ ] Console.log, print(), debug statements left in code
- [ ] Commented-out code blocks
Review recent code changes for quality issues before closing the sprint.
### 2. Code Quality
- [ ] Functions exceeding 50 lines (complexity smell)
- [ ] Deeply nested conditionals (>3 levels)
- [ ] Duplicate code patterns
- [ ] Missing docstrings/comments on public functions
## Invocation
### 3. Security Scan (Lightweight)
- [ ] Hardcoded strings that look like secrets (API keys, passwords, tokens)
- [ ] SQL strings with concatenation (injection risk)
- [ ] Disabled SSL verification
- [ ] Overly permissive file permissions in code
Run `/review` before `/sprint-close` to catch issues.
### 4. Error Handling
- [ ] Bare except/catch blocks
- [ ] Swallowed exceptions (catch with pass/empty block)
- [ ] Missing null/undefined checks on external data
## Workflow
## Output Format
1. **Determine Scope** - Sprint files or recent commits (`git diff --name-only HEAD~5`)
2. **Read Files** - Use Read tool for each file in scope
3. **Scan for Patterns** - Check each category from review checklist
4. **Compile Findings** - Group by severity (Critical, Warning, Recommendation)
5. **Report Verdict** - READY / NEEDS ATTENTION / BLOCK
Provide a structured report:
## Review Categories
```
## Sprint Review Summary
See `skills/review-checklist.md` for complete patterns:
- Debug artifacts (TODO, console.log, commented code)
- Code quality (long functions, deep nesting, duplication)
- Security (hardcoded secrets, SQL injection, disabled SSL)
- Error handling (bare except, swallowed exceptions)
### Critical Issues (Block Sprint Close)
- [file:line] Description
## DO NOT
### Warnings (Should Address)
- [file:line] Description
### Recommendations (Nice to Have)
- [file:line] Description
### Clean Files
- List of files with no issues found
```
## Scope
If sprint context is available from projman, limit review to files touched in current sprint.
Otherwise, review staged changes or changes in the last 5 commits.
## How to Determine Scope
1. **Check for sprint context**: Look for `.projman/current-sprint.json` or similar
2. **Fall back to git changes**: Use `git diff --name-only HEAD~5` or staged files
3. **Filter by file type**: Focus on code files (.py, .js, .ts, .go, .rs, etc.)
## Execution Steps
1. Determine scope (sprint files or recent commits)
2. For each file in scope:
- Read the file content
- Scan for patterns in each category
- Record findings with file:line references
3. Compile findings into the structured report
4. Provide recommendation: READY / NEEDS ATTENTION / BLOCK
- Rewrite or refactor code automatically
- Make changes without explicit approval
- Review files outside sprint/change scope
- Spend excessive time on style issues
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
@@ -85,12 +49,3 @@ When executing this command, display the plugin header:
║ Code Review ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the review workflow.
## Do NOT
- Rewrite or refactor code automatically
- Make changes without explicit approval
- Review files outside the sprint/change scope
- Spend excessive time on style issues (assume formatters handle this)

View File

@@ -0,0 +1,90 @@
---
description: Configure projman - full setup, quick project init, or sync after repo move
---
# Setup
## Skills Required
- skills/mcp-tools-reference.md
- skills/repo-validation.md
- skills/setup-workflows.md
## Purpose
Unified setup command for all configuration needs.
**Important:**
- Uses Bash, Read, Write, AskUserQuestion - NOT MCP tools
- MCP tools won't work until after setup + session restart
- Tokens must be entered manually for security
## Invocation
```
/setup # Auto-detect appropriate mode
/setup --full # Full wizard (MCP + system + project)
/setup --quick # Project-only setup
/setup --sync # Update after repo move
```
## Mode Detection
If no argument provided, auto-detect:
1. Check `~/.config/claude/gitea.env`
- Missing → **full** mode
2. Check project `.env`
- Missing → **quick** mode
3. Compare `.env` with git remote
- Mismatch → **sync** mode
- Match → offer reconfigure or exit
## Mode: Full
Execute `skills/setup-workflows.md` → Full Setup Workflow
Phases:
1. Environment validation (Python 3.10+)
2. MCP server setup (venv + requirements)
3. System-level config (`~/.config/claude/gitea.env`)
4. Project-level config (`.env`)
5. Final validation
## Mode: Quick
Execute `skills/setup-workflows.md` → Quick Setup Workflow
Steps:
1. Verify system config exists
2. Verify git repository
3. Check existing `.env`
4. Detect org/repo from git remote
5. Validate via API
6. Create/update `.env`
7. Check `.gitignore`
## Mode: Sync
Execute `skills/setup-workflows.md` → Sync Workflow
Steps:
1. Read current config
2. Detect git remote
3. Compare values
4. Show changes
5. Validate new values
6. Update `.env`
7. Confirm
## Visual Output
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ ⚙️ SETUP ║
║ [Mode: Full | Quick | Sync] ║
╚══════════════════════════════════════════════════════════════════╝
```

View File

@@ -1,293 +1,46 @@
---
description: Complete sprint and capture lessons learned to Gitea Wiki
agent: orchestrator
---
# Close Sprint and Capture Lessons Learned
This command completes the sprint and captures lessons learned to Gitea Wiki. **This is critical** - after 15 sprints without lesson capture, repeated mistakes occurred (e.g., Claude Code infinite loops 2-3 times on similar issues).
## Skills Required
## Why Lessons Learned Matter
- skills/mcp-tools-reference.md
- skills/lessons-learned.md
- skills/wiki-conventions.md
- skills/progress-tracking.md
- skills/git-workflow.md
**Problem:** Without systematic lesson capture, teams repeat the same mistakes:
- Claude Code infinite loops on similar issues (happened 2-3 times)
- Same architectural mistakes (multiple occurrences)
- Forgotten optimizations (re-discovered each time)
## Purpose
**Solution:** Mandatory lessons learned capture at sprint close, searchable at sprint start.
Complete the sprint, capture lessons learned to Gitea Wiki, and update documentation. This is critical for preventing repeated mistakes across sprints.
## Sprint Close Workflow
## Invocation
The orchestrator agent will guide you through:
Run `/sprint-close` when sprint work is complete.
1. **Review Sprint Completion**
- Use `list_issues` to verify all issues are closed or moved to backlog
- Check milestone completion status
- Check for incomplete work needing carryover
- Review overall sprint goals vs. actual completion
## Workflow
2. **Capture Lessons Learned**
- What went wrong and why
- What went right and should be repeated
- Preventable repetitions to avoid in future sprints
- Technical insights and gotchas discovered
Execute the sprint close workflow:
3. **Tag for Discoverability**
- Apply relevant tags: technology, component, type of lesson
- Ensure future sprints can find these lessons via search
- Use consistent tagging for patterns
1. **Review Sprint Completion** - Verify issues closed or moved to backlog
2. **Capture Lessons Learned** - Interview user about challenges and insights
3. **Tag for Discoverability** - Apply technology, component, and pattern tags
4. **Save to Gitea Wiki** - Use `create_lesson` with metadata and implementation link
5. **Update Wiki Implementation Page** - Change status to Implemented/Partial/Failed
6. **Update Wiki Proposal Page** - Update overall status if all implementations complete
7. **New Command Verification** - Remind user new commands require session restart
8. **Update CHANGELOG** (MANDATORY) - Add changes to `[Unreleased]` section
9. **Version Check** - Run `/suggest-version` to recommend version bump
10. **Git Operations** - Commit, merge, tag, clean up branches
11. **Close Milestone** - Update milestone state to closed
4. **Save to Gitea Wiki**
- Use `create_lesson` to save lessons to Gitea Wiki
- Create lessons in project wiki under `lessons-learned/sprints/`
- Make lessons searchable for future sprints
5. **Update Wiki Implementation Page**
- Use `get_wiki_page` to fetch the current implementation page
- Update status from "In Progress" to "Implemented" (or "Partial"/"Failed")
- Add completion date
- Link to lessons learned created in step 4
- Use `update_wiki_page` to save changes
6. **Update Wiki Proposal Page**
- Check if all implementations for this proposal are complete
- If all complete: Update proposal status to "Implemented"
- If partial: Keep status as "In Progress", note completed implementations
- Add summary of what was accomplished
7. **New Command Verification** (if applicable)
- Check if this sprint added new commands or skills
- **IMPORTANT:** New commands are NOT discoverable until session restart
- If new commands were added:
- List them in sprint close notes
- Remind user: "New commands require session restart to test"
- Create verification task in next sprint or backlog
- **WHY:** Claude Code discovers skills at session start; commands added during a session won't work until restart
8. **Update CHANGELOG** (MANDATORY)
- Add all sprint changes to `[Unreleased]` section in CHANGELOG.md
- Categorize: Added, Changed, Fixed, Removed, Deprecated
- Include plugin prefix (e.g., `- **projman:** New feature`)
9. **Version Check**
- Run `/suggest-version` to analyze changes and recommend version bump
- If release warranted: run `./scripts/release.sh X.Y.Z`
- Ensures version numbers stay in sync across files
10. **Git Operations**
- Commit any remaining work (including CHANGELOG updates)
- Merge feature branches if needed
- Clean up merged branches
- Tag sprint completion (if release created)
11. **Close Milestone**
- Use `update_milestone` to close the sprint milestone
- Document final completion status
## MCP Tools Available
**Gitea Tools:**
- `list_issues` - Review sprint issues (completed and incomplete)
- `get_issue` - Get detailed issue information for retrospective
- `update_issue` - Move incomplete issues to next sprint
**Milestone Tools:**
- `get_milestone` - Get milestone status
- `update_milestone` - Close milestone
**Lessons Learned Tools (Gitea Wiki):**
- `create_lesson` - Create lessons learned entry
- `search_lessons` - Check for similar existing lessons
- `list_wiki_pages` - Check existing lessons learned
- `get_wiki_page` - Read existing lessons or implementation pages
- `update_wiki_page` - Update implementation/proposal status
## Lesson Structure
Lessons should follow this structure:
```markdown
# Sprint X - [Lesson Title]
## Metadata
- **Implementation:** [Change VXX.X.X (Impl N)](wiki-link)
- **Issues:** #45, #46, #47
- **Sprint:** Sprint X
## Context
[What were you trying to do? What was the sprint goal?]
## Problem
[What went wrong? What insight emerged? What challenge did you face?]
## Solution
[How did you solve it? What approach worked?]
## Prevention
[How can this be avoided or optimized in the future? What should future sprints know?]
## Tags
[Comma-separated tags for search: technology, component, type]
```
**IMPORTANT:** Always include the Implementation link in the Metadata section. This enables bidirectional traceability between lessons and the work that generated them.
## Example Lessons Learned
**Example 1: Technical Gotcha**
```markdown
# Sprint 16 - Claude Code Infinite Loop on Validation Errors
## Metadata
- **Implementation:** [Change V1.2.0 (Impl 1)](https://gitea.example.com/org/repo/wiki/Change-V1.2.0%3A-Proposal-(Implementation-1))
- **Issues:** #45, #46
- **Sprint:** Sprint 16
## Context
Implementing input validation for authentication API endpoints.
## Problem
Claude Code entered an infinite loop when pytest validation tests failed.
The loop occurred because the error message didn't change between attempts,
causing Claude to retry the same fix repeatedly.
## Solution
Added more descriptive error messages to validation tests that specify
exactly what value failed and why. This gave Claude clear feedback
to adjust the approach rather than retrying the same fix.
## Prevention
- Always write validation test errors with specific values and expectations
- If Claude loops, check if error messages provide unique information per failure
- Add a "loop detection" check in test output (fail after 3 identical errors)
## Tags
testing, claude-code, validation, python, pytest, debugging
```
**Example 2: Architectural Decision**
```markdown
# Sprint 14 - Extracting Services Too Early
## Metadata
- **Implementation:** [Change V2.0.0 (Impl 1)](https://gitea.example.com/org/repo/wiki/Change-V2.0.0%3A-Proposal-(Implementation-1))
- **Issues:** #32, #33, #34
- **Sprint:** Sprint 14
## Context
Planning to extract Intuit Engine service from monolith.
## Problem
Initial plan was to extract immediately without testing the API boundaries
first. This would have caused integration issues discovered late.
## Solution
Added a sprint phase to:
1. Define clear API contracts first
2. Add integration tests for the boundaries
3. THEN extract the service
Delayed extraction by one sprint but avoided major rework.
## Prevention
- Always define API contracts before service extraction
- Write integration tests FIRST, extraction SECOND
- Don't rush architectural changes - test boundaries first
## Tags
architecture, service-extraction, refactoring, api-design, planning
```
## Tagging Strategy
Use consistent tags for discoverability:
**By Technology:**
- `python`, `javascript`, `docker`, `postgresql`, `redis`, `vue`, `fastapi`
**By Component:**
- `backend`, `frontend`, `api`, `database`, `auth`, `deploy`, `testing`, `docs`
**By Type:**
- `bug`, `feature`, `refactor`, `architecture`, `performance`, `security`
**By Issue:**
- `claude-code`, `validation`, `testing`, `debugging`, `deployment`, `configuration`
**By Pattern:**
- `infinite-loop`, `edge-case`, `integration`, `boundaries`, `dependencies`
## Orchestrator's Role
The orchestrator agent will:
1. Ask probing questions about the sprint
2. Identify preventable mistakes vs. expected challenges
3. Structure lessons in the proper format
4. Suggest appropriate tags
5. Create lessons in Gitea Wiki using `create_lesson`
6. Ensure lessons are discoverable for future sprints
7. Handle git operations and milestone closure
## Example Sprint Close Session
```
User: /sprint-close
Orchestrator: Let's close the sprint and capture lessons learned.
First, let me review the sprint completion...
[Uses list_issues to check sprint status]
Sprint 18 Summary:
- 8 issues planned
- 7 completed (87.5%)
- 1 moved to backlog (#52: Deploy auth service - blocked by infra)
Great progress! Now, let's capture lessons learned.
What challenges did you face this sprint?
User: Claude Code got stuck in a loop when pytest validation tests failed
Orchestrator: That's a valuable lesson - this prevents future frustration.
Let me ask some clarifying questions:
1. What caused the loop? (Same error message repeated?)
2. How did you break out of it?
3. What would prevent this in future sprints?
[After gathering details]
I'll create this lesson with tags: testing, claude-code, validation, python, pytest, debugging
[Uses create_lesson to save to Gitea Wiki]
Lesson created: "Sprint 18 - Claude Code Infinite Loop on Validation Errors"
Saved to Gitea Wiki with appropriate tags.
Any other lessons from this sprint?
User: Yes, we discovered that JWT token refresh needs special handling
Orchestrator: Excellent - let's capture that too...
[Continues capturing lessons]
All lessons captured! They'll be searchable when planning future sprints.
Would you like me to handle git operations?
- Commit any remaining changes
- Merge feature branches to development
- Tag sprint completion (v0.18.0)
- Clean up merged branches
- Close milestone
[Y/n]
```
**Don't skip lessons learned!** Future sprints will benefit from captured insights.
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
@@ -295,18 +48,3 @@ When executing this command, display the plugin header:
║ [Sprint Name] ║
╚══════════════════════════════════════════════════════════════════╝
```
Replace `[Sprint Name]` with the actual sprint/milestone name.
Then proceed with the sprint close workflow.
## Getting Started
Simply run `/sprint-close` when your sprint is complete. The orchestrator will guide you through:
1. Sprint review
2. Lessons learned capture
3. Gitea Wiki updates
4. Git operations
5. Milestone closure
**Don't skip this step!** Future sprints will thank you for capturing these insights.

View File

@@ -1,193 +0,0 @@
---
description: Generate Mermaid diagram of sprint issues with dependencies and status
---
# Sprint Diagram
This command generates a visual Mermaid diagram showing the current sprint's issues, their dependencies, and execution flow.
## What This Command Does
1. **Fetch Sprint Issues** - Gets all issues for the current sprint milestone
2. **Fetch Dependencies** - Retrieves dependency relationships between issues
3. **Generate Mermaid Syntax** - Creates flowchart showing issue flow
4. **Apply Status Styling** - Colors nodes based on issue state (open/closed/in-progress)
5. **Show Execution Order** - Visualizes parallel batches and critical path
## Usage
```
/sprint-diagram
/sprint-diagram --milestone "Sprint 4"
```
## MCP Tools Used
**Issue Tools:**
- `list_issues(state="all")` - Fetch all sprint issues
- `list_milestones()` - Find current sprint milestone
**Dependency Tools:**
- `list_issue_dependencies(issue_number)` - Get dependencies for each issue
- `get_execution_order(issue_numbers)` - Get parallel execution batches
## Implementation Steps
1. **Get Current Milestone:**
```
milestones = list_milestones(state="open")
current_sprint = milestones[0] # Most recent open milestone
```
2. **Fetch Sprint Issues:**
```
issues = list_issues(state="all", milestone=current_sprint.title)
```
3. **Fetch Dependencies for Each Issue:**
```python
dependencies = {}
for issue in issues:
deps = list_issue_dependencies(issue.number)
dependencies[issue.number] = deps
```
4. **Generate Mermaid Diagram:**
```mermaid
flowchart TD
subgraph Sprint["Sprint 4 - Commands"]
241["#241: sprint-diagram"]
242["#242: confidence threshold"]
243["#243: pr-diff"]
241 --> 242
242 --> 243
end
classDef completed fill:#90EE90,stroke:#228B22
classDef inProgress fill:#FFD700,stroke:#DAA520
classDef open fill:#ADD8E6,stroke:#4682B4
classDef blocked fill:#FFB6C1,stroke:#DC143C
class 241 completed
class 242 inProgress
class 243 open
```
## Expected Output
```
Sprint Diagram: Sprint 4 - Commands
===================================
```mermaid
flowchart TD
subgraph batch1["Batch 1 - No Dependencies"]
241["#241: sprint-diagram<br/>projman"]
242["#242: confidence threshold<br/>pr-review"]
244["#244: data-quality<br/>data-platform"]
247["#247: chart-export<br/>viz-platform"]
250["#250: dependency-graph<br/>contract-validator"]
251["#251: changelog-gen<br/>doc-guardian"]
254["#254: config-diff<br/>config-maintainer"]
256["#256: cmdb-topology<br/>cmdb-assistant"]
end
subgraph batch2["Batch 2 - After Batch 1"]
243["#243: pr-diff<br/>pr-review"]
245["#245: lineage-viz<br/>data-platform"]
248["#248: color blind<br/>viz-platform"]
252["#252: doc-coverage<br/>doc-guardian"]
255["#255: linting<br/>config-maintainer"]
257["#257: change-audit<br/>cmdb-assistant"]
end
subgraph batch3["Batch 3 - Final"]
246["#246: dbt-test<br/>data-platform"]
249["#249: responsive<br/>viz-platform"]
253["#253: stale-docs<br/>doc-guardian"]
258["#258: IP conflict<br/>cmdb-assistant"]
end
batch1 --> batch2
batch2 --> batch3
classDef completed fill:#90EE90,stroke:#228B22
classDef inProgress fill:#FFD700,stroke:#DAA520
classDef open fill:#ADD8E6,stroke:#4682B4
class 241,242 completed
class 243,244 inProgress
```
## Status Legend
| Status | Color | Description |
|--------|-------|-------------|
| Completed | Green | Issue closed |
| In Progress | Yellow | Currently being worked on |
| Open | Blue | Ready to start |
| Blocked | Red | Waiting on dependencies |
## Diagram Types
### Default: Dependency Flow
Shows how issues depend on each other with arrows indicating blockers.
### Batch View (--batch)
Groups issues by execution batch for parallel work visualization.
### Plugin View (--by-plugin)
Groups issues by plugin for component-level overview.
## When to Use
- **Sprint Planning**: Visualize scope and dependencies
- **Daily Standups**: Show progress at a glance
- **Documentation**: Include in wiki pages
- **Stakeholder Updates**: Visual progress reports
## Integration
The generated Mermaid diagram can be:
- Pasted into GitHub/Gitea issues
- Rendered in wiki pages
- Included in PRs for context
- Used in sprint retrospectives
## Example
```
User: /sprint-diagram
Generating sprint diagram...
Milestone: Sprint 4 - Commands (18 issues)
Fetching dependencies...
Building diagram...
```mermaid
flowchart LR
241[sprint-diagram] --> |enables| 242[confidence]
242 --> 243[pr-diff]
style 241 fill:#90EE90
style 242 fill:#ADD8E6
style 243 fill:#ADD8E6
```
Open: 16 | In Progress: 1 | Completed: 1
```
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ Sprint Diagram ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed to generate the diagram.

View File

@@ -1,413 +1,56 @@
---
description: Start sprint planning with AI-guided architecture analysis and issue creation
agent: planner
---
# Sprint Planning
You are initiating sprint planning. The planner agent will guide you through architecture analysis, ask clarifying questions, and help create well-structured Gitea issues with appropriate labels.
## CRITICAL: Pre-Planning Validations
**BEFORE PLANNING**, the planner agent performs mandatory checks:
### 1. Branch Detection
```bash
git branch --show-current
```
**Branch Requirements:**
- **Development branches** (`development`, `develop`, `feat/*`, `dev/*`): Full planning capabilities
- **Staging branches** (`staging`, `stage/*`): Can create issues to document needed changes, but cannot modify code
- **Production branches** (`main`, `master`, `prod/*`): READ-ONLY - no planning allowed
If you are on a production or staging branch, you MUST stop and ask the user to switch to a development branch.
### 2. Repository Organization Check
Use `validate_repo_org` MCP tool to verify the repository belongs to an organization.
**If NOT an organization repository:**
```
REPOSITORY VALIDATION FAILED
This plugin requires the repository to belong to an organization, not a user.
Please transfer or create the repository under that organization.
```
### 3. Label Taxonomy Validation
Verify all required labels exist using `get_labels`:
**Required label categories:**
- Type/* (Bug, Feature, Refactor, Documentation, Test, Chore)
- Priority/* (Low, Medium, High, Critical)
- Complexity/* (Simple, Medium, Complex)
- Efforts/* (XS, S, M, L, XL)
**If labels are missing:** Use `create_label` to create them.
### 4. Input Source Detection
The planner supports flexible input sources for sprint planning:
| Source | Detection | Action |
|--------|-----------|--------|
| **Local file** | `docs/changes/*.md` exists | Parse frontmatter, migrate to wiki, delete local |
| **Existing wiki** | `Change VXX.X.X: Proposal` exists | Use as-is, create new implementation page |
| **Conversation** | Neither file nor wiki exists | Create wiki from discussion context |
**Input File Format** (if using local file):
```yaml
---
version: "4.1.0" # or "sprint-17" for internal work
title: "Feature Name"
plugin: plugin-name # optional
type: feature # feature | bugfix | refactor | infra
---
# Feature Description
[Free-form content...]
```
**Detection Logic:**
1. Check for `docs/changes/*.md` files
2. Check for existing wiki proposal matching version
3. If neither found, use conversation context
4. If ambiguous, ask user which input to use
## Planning Workflow
The planner agent will:
1. **Understand Sprint Goals**
- Ask clarifying questions about the sprint objectives
- Understand scope, priorities, and constraints
- Never rush - take time to understand requirements fully
2. **Detect Input Source**
- Check for `docs/changes/*.md` files
- Check for existing wiki proposal by version
- If neither: use conversation context
- Ask user if multiple sources found
3. **Search Relevant Lessons Learned**
- Use the `search_lessons` MCP tool to find past experiences
- Search by keywords and tags relevant to the sprint work
- Review patterns and preventable mistakes from previous sprints
4. **Create/Update Wiki Proposal**
- If local file: migrate content to wiki, create proposal page
- If conversation: create proposal from discussion
- If existing wiki: skip creation, use as-is
- **Page naming:** `Change VXX.X.X: Proposal` or `Change Sprint-NN: Proposal`
5. **Create Wiki Implementation Page**
- Create `Change VXX.X.X: Proposal (Implementation N)`
- Include tags: Type, Version, Status=In Progress, Date, Origin
- Update proposal page with link to this implementation
- This page tracks THIS sprint's work on the proposal
6. **Architecture Analysis**
- Think through technical approach and edge cases
- Identify architectural decisions needed
- Consider dependencies and integration points
- Review existing codebase architecture
7. **Create Gitea Issues**
- Use the `create_issue` MCP tool for each planned task
- Apply appropriate labels using `suggest_labels` tool
- **Issue Title Format (MANDATORY):** `[Sprint XX] <type>: <description>`
- **Include wiki reference:** `Implementation: [Change VXX.X.X (Impl N)](wiki-link)`
- Include acceptance criteria and technical notes
8. **Set Up Dependencies**
- Use `create_issue_dependency` to establish task dependencies
- This enables parallel execution planning
9. **Create or Select Milestone**
- Use `create_milestone` to group sprint issues
- Assign issues to the milestone
10. **Cleanup & Summary**
- Delete local input file (wiki is now source of truth)
- Summarize architectural decisions
- List created issues with labels
- Document dependency graph
- Provide sprint overview with wiki links
11. **Request Sprint Approval**
- Present approval request with scope summary
- Capture explicit user approval
- Record approval in milestone description
- Approval scopes what sprint-start can execute
## Sprint Approval (MANDATORY)
**Planning DOES NOT equal execution permission.**
After creating issues, the planner MUST request explicit approval:
```
Sprint 17 Planning Complete
===========================
Created Issues:
- #45: [Sprint 17] feat: JWT token generation
- #46: [Sprint 17] feat: Login endpoint
- #47: [Sprint 17] test: Auth tests
Execution Scope:
- Branches: feat/45-*, feat/46-*, feat/47-*
- Files: auth/*, api/routes/auth.py, tests/test_auth*
- Dependencies: PyJWT, python-jose
⚠️ APPROVAL REQUIRED
Do you approve this sprint for execution?
This grants permission for agents to:
- Create and modify files in the listed scope
- Create branches with the listed prefixes
- Install listed dependencies
Type "approve sprint 17" to authorize execution.
```
**On Approval:**
1. Record approval in milestone description
2. Note timestamp and scope
3. Sprint-start will verify approval exists
**Approval Record Format:**
```markdown
## Sprint Approval
**Approved:** 2026-01-28 14:30
**Approver:** User
**Scope:**
- Branches: feat/45-*, feat/46-*, feat/47-*
- Files: auth/*, api/routes/auth.py, tests/test_auth*
```
## Issue Title Format (MANDATORY)
```
[Sprint XX] <type>: <description>
```
**Types:**
- `feat` - New feature
- `fix` - Bug fix
- `refactor` - Code refactoring
- `docs` - Documentation
- `test` - Test additions/changes
- `chore` - Maintenance tasks
**Examples:**
- `[Sprint 17] feat: Add user email validation`
- `[Sprint 17] fix: Resolve login timeout issue`
- `[Sprint 18] refactor: Extract authentication module`
## Task Sizing Rules (MANDATORY)
**CRITICAL: Tasks sized L or XL MUST be broken down into smaller tasks.**
| Effort | Files | Checklist Items | Max Tool Calls | Agent Scope |
|--------|-------|-----------------|----------------|-------------|
| **XS** | 1 file | 0-2 items | ~30 | Single function/fix |
| **S** | 1 file | 2-4 items | ~50 | Single file feature |
| **M** | 2-3 files | 4-6 items | ~80 | Multi-file feature |
| **L** | MUST BREAK DOWN | - | - | Too large for one agent |
| **XL** | MUST BREAK DOWN | - | - | Way too large |
**Why This Matters:**
- Agents running 400+ tool calls take 1+ hour, with no visibility
- Large tasks lack clear completion criteria
- Debugging failures is extremely difficult
- Small tasks enable parallel execution
**Scoping Checklist:**
1. Can this be completed in one file? → XS or S
2. Does it touch 2-3 files? → M (maximum for single task)
3. Does it touch 4+ files? → MUST break down
4. Would you estimate 50+ tool calls? → MUST break down
5. Does it require complex decision-making mid-task? → MUST break down
**Example Breakdown:**
**BAD (L - too broad):**
```
[Sprint 3] feat: Implement schema diff detection hook
Labels: Efforts/L
- Hook skeleton
- Pattern detection for DROP/ALTER/RENAME
- Warning output formatting
- Integration with hooks.json
```
**GOOD (broken into S tasks):**
```
[Sprint 3] feat: Create schema-diff-check.sh hook skeleton
Labels: Efforts/S
- [ ] Create hook file with standard header
- [ ] Add file type detection for SQL/migrations
- [ ] Exit 0 (non-blocking)
[Sprint 3] feat: Add DROP/ALTER pattern detection
Labels: Efforts/S
- [ ] Detect DROP COLUMN/TABLE/INDEX
- [ ] Detect ALTER TYPE changes
- [ ] Detect RENAME operations
[Sprint 3] feat: Add warning output formatting
Labels: Efforts/S
- [ ] Format breaking change warnings
- [ ] Add hook prefix to output
- [ ] Test output visibility
[Sprint 3] chore: Register hook in hooks.json
Labels: Efforts/XS
- [ ] Add PostToolUse:Edit hook entry
- [ ] Test hook triggers on SQL edits
```
**The planner MUST refuse to create L/XL tasks without breakdown.**
## MCP Tools Available
**Gitea Tools:**
- `list_issues` - Review existing issues
- `get_issue` - Get detailed issue information
- `create_issue` - Create new issue with labels
- `update_issue` - Update issue
- `get_labels` - Fetch current label taxonomy
- `suggest_labels` - Get intelligent label suggestions based on context
- `create_label` - Create missing labels
- `validate_repo_org` - Check if repo is under organization
**Milestone Tools:**
- `list_milestones` - List milestones
- `create_milestone` - Create milestone
- `update_milestone` - Update milestone
**Dependency Tools:**
- `create_issue_dependency` - Create dependency between issues
- `list_issue_dependencies` - List dependencies for an issue
- `get_execution_order` - Get parallel execution batches
**Lessons Learned Tools (Gitea Wiki):**
- `search_lessons` - Search lessons learned from previous sprints
- `list_wiki_pages` - List wiki pages
- `get_wiki_page` - Fetch specific documentation page
- `create_wiki_page` - Create new wiki page (proposals, implementations)
- `update_wiki_page` - Update wiki page content
## Label Taxonomy
The system uses a dynamic 44-label taxonomy (28 org + 16 repo). Always use the `suggest_labels` tool to get appropriate labels based on the issue context.
**Key Label Categories:**
- **Type/***: Bug, Feature, Refactor, Documentation, Test, Chore
- **Priority/***: Low, Medium, High, Critical
- **Complexity/***: Simple, Medium, Complex
- **Efforts/***: XS, S, M, L, XL
- **Component/***: Backend, Frontend, API, Database, Auth, Deploy, Testing, Docs, Infra
- **Tech/***: Python, JavaScript, Docker, PostgreSQL, Redis, Vue, FastAPI
## Planner Personality
The planner agent is thoughtful and methodical:
- Asks clarifying questions before making assumptions
- Thinks through edge cases and architectural implications
- Never rushes planning - quality over speed
- References lessons learned proactively
- Suggests appropriate labels based on context
- Creates well-structured, detailed issues
## Example Planning Session
```
User: I want to plan a sprint for user authentication
Planner: Great! Let me first run pre-planning validations...
[Checks branch, repo org, labels]
All validations passed.
[Checks for input sources]
Found: docs/changes/v1.2.0-user-authentication.md
I'll use this file as the planning input. Let me ask a few questions:
1. What authentication method are you planning? (JWT, OAuth, session-based?)
2. Are there any specific security requirements or compliance needs?
3. Should this integrate with existing user management?
[Uses search_lessons to find past authentication work]
Based on previous experience, I found these relevant lessons:
- Sprint 12: JWT token expiration handling edge cases
- Sprint 8: OAuth integration pitfalls with third-party providers
[Creates wiki proposal and implementation pages]
✓ Created: "Change V1.2.0: Proposal" (wiki)
✓ Created: "Change V1.2.0: Proposal (Implementation 1)" (wiki)
✓ Deleted: docs/changes/v1.2.0-user-authentication.md (migrated to wiki)
Now, let me analyze the architecture and create issues...
[Creates issues with wiki references]
Created 5 issues for the authentication sprint:
- Issue #45: [Sprint 17] feat: Implement JWT token generation
Labels: Type/Feature, Priority/High, Component/Auth, Tech/Python
Implementation: [Change V1.2.0 (Impl 1)](wiki-link)
- Issue #46: [Sprint 17] feat: Build user login endpoint
Labels: Type/Feature, Priority/High, Component/API, Tech/FastAPI
Implementation: [Change V1.2.0 (Impl 1)](wiki-link)
Dependency Graph:
#45 -> #46 -> #47
|
v
#48
Milestone: Sprint 17 - User Authentication (Due: 2025-02-01)
Wiki: https://gitea.example.com/org/repo/wiki/Change-V1.2.0%3A-Proposal
```
## Skills Required
- skills/mcp-tools-reference.md
- skills/branch-security.md
- skills/repo-validation.md
- skills/input-detection.md
- skills/lessons-learned.md
- skills/wiki-conventions.md
- skills/task-sizing.md
- skills/issue-conventions.md
- skills/sprint-approval.md
- skills/planning-workflow.md
- skills/label-taxonomy/labels-reference.md
## Purpose
Initiate sprint planning session. The planner agent validates prerequisites, gathers requirements, searches lessons learned, creates wiki pages, and creates well-structured Gitea issues with proper dependencies and labels.
## Invocation
Provide sprint goals as natural language input, or prepare input via:
- `docs/changes/*.md` file with frontmatter
- Existing wiki proposal page
- Direct conversation
## Workflow
Execute the planning workflow as defined in `skills/planning-workflow.md`.
**Key steps:**
1. Run pre-planning validations (branch, repo org, labels)
2. Detect input source (file, wiki, or conversation)
3. Search relevant lessons learned
4. Create/update wiki proposal and implementation pages
5. Perform architecture analysis
6. Create Gitea issues with wiki references (respecting task sizing rules)
7. Set up dependencies
8. Create or select milestone
9. Request explicit sprint approval
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ 🎯 PLANNING ║
║ Sprint Planning
[Sprint Name]
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the command workflow.
## Getting Started
Invoke the planner agent by providing your sprint goals. The agent will guide you through the planning process.
**Input Options:**
1. Create `docs/changes/vX.Y.Z-feature-name.md` with frontmatter before running
2. Create wiki proposal page manually, then run `/sprint-plan`
3. Just start a conversation - the planner will capture context and create wiki pages
**Example:**
> "I want to plan a sprint for extracting the Intuit Engine service from the monolith"
The planner will then:
1. Run pre-planning validations
2. Detect input source (file, wiki, or conversation)
3. Ask clarifying questions
4. Search lessons learned
5. Create wiki proposal and implementation pages
6. Create issues with wiki references
7. Set up dependencies
8. Create milestone
9. Cleanup and generate planning summary

View File

@@ -1,419 +1,48 @@
---
description: Begin sprint execution with relevant lessons learned from previous sprints
agent: orchestrator
---
# Start Sprint Execution
You are initiating sprint execution. The orchestrator agent will coordinate the work, analyze dependencies for parallel execution, search for relevant lessons learned, and guide you through the implementation process.
## Skills Required
## Sprint Approval Verification (Recommended)
- skills/mcp-tools-reference.md
- skills/branch-security.md
- skills/sprint-approval.md
- skills/dependency-management.md
- skills/lessons-learned.md
- skills/git-workflow.md
- skills/progress-tracking.md
- skills/runaway-detection.md
**RECOMMENDED: Sprint should be approved before execution.**
## Purpose
> **Note:** This is a recommended workflow practice, not code-enforced. The orchestrator
> SHOULD check for approval, but execution will proceed if approval is missing. For
> critical projects, consider making approval mandatory in your workflow.
Initiate sprint execution. The orchestrator agent verifies approval, analyzes dependencies for parallel execution, searches relevant lessons, and coordinates task dispatch.
The orchestrator checks for approval in the milestone description:
## Invocation
```
get_milestone(milestone_id=17)
→ Check description for "## Sprint Approval" section
```
Run `/sprint-start` when ready to begin executing a planned sprint.
**If Approval Missing:**
```
⚠️ SPRINT APPROVAL NOT FOUND (Warning)
## Workflow
Sprint 17 milestone does not contain an approval record.
Execute the sprint start workflow:
Recommended: Run /sprint-plan first to:
1. Review the sprint scope
2. Document the approved execution plan
1. **Verify Sprint Approval** (recommended) - Check milestone for approval record
2. **Detect Checkpoints** - Check for resume points from interrupted sessions
3. **Fetch Sprint Issues** - Get open issues from milestone
4. **Analyze Dependencies** - Use `get_execution_order` for parallel batches
5. **Search Relevant Lessons** - Find applicable past experiences
6. **Dispatch Tasks** - Parallel when safe, sequential when file conflicts exist
Proceeding anyway - consider adding approval for audit trail.
```
**File Conflict Prevention:** Before parallel dispatch, check target files for overlap. Sequentialize tasks that modify the same files.
**If Approval Found:**
```
✓ Sprint Approval Verified
Approved: 2026-01-28 14:30
Scope:
Branches: feat/45-*, feat/46-*, feat/47-*
Files: auth/*, api/routes/auth.py, tests/test_auth*
**Branch Isolation:** Each task runs on its own branch (`feat/<issue>-<desc>`).
Proceeding with execution within approved scope...
```
**Scope Enforcement (when approval exists):**
- Agents SHOULD only create branches matching approved patterns
- Agents SHOULD only modify files within approved paths
- Operations outside scope should trigger re-approval via `/sprint-plan`
## Branch Detection
**CRITICAL:** Before proceeding, check the current git branch:
```bash
git branch --show-current
```
**Branch Requirements:**
- **Development branches** (`development`, `develop`, `feat/*`, `dev/*`): Full execution capabilities
- **Staging branches** (`staging`, `stage/*`): Can create issues to document bugs, but cannot modify code
- **Production branches** (`main`, `master`, `prod/*`): READ-ONLY - no execution allowed
If you are on a production or staging branch, you MUST stop and ask the user to switch to a development branch.
## Sprint Start Workflow
The orchestrator agent will:
1. **Verify Sprint Approval** (Recommended)
- Check milestone description for `## Sprint Approval` section
- If no approval found, WARN user and suggest `/sprint-plan` first
- If approval found, extract scope (branches, files)
- Agents SHOULD operate within approved scope when available
2. **Detect Checkpoints (Resume Support)**
- Check each open issue for `## Checkpoint` comments
- If checkpoint found, offer to resume from that point
- Resume preserves: branch, completed work, pending steps
3. **Fetch Sprint Issues**
- Use `list_issues` to fetch open issues for the sprint
- Identify priorities based on labels (Priority/Critical, Priority/High, etc.)
2. **Analyze Dependencies and Plan Parallel Execution**
- Use `get_execution_order` to build dependency graph
- Identify batches that can be executed in parallel
- Present parallel execution plan
3. **Search Relevant Lessons Learned**
- Use `search_lessons` to find experiences from past sprints
- Search by tags matching the current sprint's technology and components
- Review patterns, gotchas, and preventable mistakes
- Present relevant lessons before starting work
4. **Dispatch Tasks (Parallel When Possible)**
- For independent tasks (same batch), spawn multiple Executor agents in parallel
- For dependent tasks, execute sequentially
- Create proper branch for each task
5. **Track Progress**
- Update issue status as work progresses
- Use `add_comment` to document progress and blockers
- Monitor when dependencies are satisfied and new tasks become unblocked
## Parallel Execution Model
The orchestrator analyzes dependencies and groups issues into parallelizable batches:
```
Parallel Execution Batches:
+---------------------------------------------------------------+
| Batch 1 (can start immediately): |
| #45 [Sprint 18] feat: Implement JWT service |
| #48 [Sprint 18] docs: Update API documentation |
+---------------------------------------------------------------+
| Batch 2 (after batch 1): |
| #46 [Sprint 18] feat: Build login endpoint (needs #45) |
| #49 [Sprint 18] test: Add auth tests (needs #45) |
+---------------------------------------------------------------+
| Batch 3 (after batch 2): |
| #47 [Sprint 18] feat: Create login form (needs #46) |
+---------------------------------------------------------------+
```
**Independent tasks in the same batch run in parallel.**
## File Conflict Prevention (MANDATORY)
**CRITICAL: Before dispatching parallel agents, check for file overlap.**
**Pre-Dispatch Conflict Check:**
1. **Identify target files** for each task in the batch
2. **Check for overlap** - Do any tasks modify the same file?
3. **If overlap detected** - Sequentialize those specific tasks
**Example Conflict Detection:**
```
Batch 1 Analysis:
#45 - Implement JWT service
Files: auth/jwt_service.py, auth/__init__.py, tests/test_jwt.py
#48 - Update API documentation
Files: docs/api.md, README.md
Overlap: NONE → Safe to parallelize
Batch 2 Analysis:
#46 - Build login endpoint
Files: api/routes/auth.py, auth/__init__.py
#49 - Add auth tests
Files: tests/test_auth.py, auth/__init__.py
Overlap: auth/__init__.py → CONFLICT!
Action: Sequentialize #46 and #49 (run #46 first)
```
**Conflict Resolution Rules:**
| Conflict Type | Action |
|---------------|--------|
| Same file in checklist | Sequentialize tasks |
| Same directory | Review if safe, usually OK |
| Shared test file | Sequentialize or assign different test files |
| Shared config | Sequentialize |
**Branch Isolation Protocol:**
Even for parallel tasks, each MUST run on its own branch:
```
Task #45 → feat/45-jwt-service (isolated)
Task #48 → feat/48-api-docs (isolated)
```
**Sequential Merge After Completion:**
```
1. Task #45 completes → merge feat/45-jwt-service to development
2. Task #48 completes → merge feat/48-api-docs to development
3. Never merge simultaneously - always sequential to detect conflicts
```
**If Merge Conflict Occurs:**
1. Stop second task
2. Resolve conflict manually or assign to human
3. Resume/restart second task with updated base
## Branch Naming Convention (MANDATORY)
When creating branches for tasks:
- Features: `feat/<issue-number>-<short-description>`
- Bug fixes: `fix/<issue-number>-<short-description>`
- Debugging: `debug/<issue-number>-<short-description>`
**Examples:**
```bash
git checkout -b feat/45-jwt-service
git checkout -b fix/46-login-timeout
git checkout -b debug/47-investigate-memory-leak
```
**Validation:**
- Issue number MUST be present
- Prefix MUST be `feat/`, `fix/`, or `debug/`
- Description should be kebab-case (lowercase, hyphens)
## MCP Tools Available
**Gitea Tools:**
- `list_issues` - Fetch sprint issues (filter by state, labels, milestone)
- `get_issue` - Get detailed issue information
- `update_issue` - Update issue status, assignee, labels
- `add_comment` - Add progress updates or blocker notes
**Dependency Tools:**
- `list_issue_dependencies` - Get dependencies for an issue
- `get_execution_order` - Get parallel execution batches for sprint issues
**Milestone Tools:**
- `list_milestones` - List milestones
- `get_milestone` - Get milestone details
**Lessons Learned Tools (Gitea Wiki):**
- `search_lessons` - Find relevant lessons from past sprints
- `list_wiki_pages` - List project documentation
- `get_wiki_page` - Fetch specific documentation (e.g., architecture decisions)
## Orchestrator Personality
The orchestrator agent is concise and action-oriented:
- Generates lean execution prompts, not lengthy documents
- Tracks details meticulously (no task forgotten)
- Coordinates parallel execution based on dependencies
- Identifies blockers proactively
- Coordinates Git operations (commit, merge, cleanup)
- Updates documentation as work progresses
## Example Sprint Start Session
```
User: /sprint-start
Orchestrator: Starting sprint execution. Let me analyze the sprint...
[Uses list_issues to fetch sprint backlog]
Found 5 open issues for this sprint.
[Uses get_execution_order to analyze dependencies]
Parallel Execution Batches:
+-----------------------------------------------+
| Batch 1 (can start immediately): |
| #45 - Implement JWT service |
| #48 - Update API documentation |
+-----------------------------------------------+
| Batch 2 (after batch 1): |
| #46 - Build login endpoint (needs #45) |
| #49 - Add auth tests (needs #45) |
+-----------------------------------------------+
| Batch 3 (after batch 2): |
| #47 - Create login form (needs #46) |
+-----------------------------------------------+
[Uses search_lessons to find relevant past experiences]
Relevant lessons learned:
- Sprint 12: "JWT Token Expiration Edge Cases" - Remember to handle token refresh
- Sprint 8: "OAuth Integration Pitfalls" - Test error handling for auth providers
Ready to start? I can dispatch multiple tasks in parallel.
Dispatching Batch 1 (2 tasks in parallel):
Task 1: #45 - Implement JWT service
Branch: feat/45-jwt-service
Executor: Starting...
Task 2: #48 - Update API documentation
Branch: feat/48-api-docs
Executor: Starting...
Both tasks running in parallel. I'll monitor progress.
```
## Lean Execution Prompts
The orchestrator generates concise prompts (NOT verbose documents):
```
Next Task: #45 - [Sprint 18] feat: Implement JWT token generation
Priority: High | Effort: M (1 day) | Unblocked
Branch: feat/45-jwt-service
Quick Context:
- Create backend service for JWT tokens
- Use HS256 algorithm (decision from planning)
- Include user_id, email, expiration in payload
Key Actions:
1. Create auth/jwt_service.py
2. Implement generate_token(user_id, email)
3. Implement verify_token(token)
4. Add token refresh logic (Sprint 12 lesson!)
5. Write unit tests for generation/validation
Acceptance Criteria:
- Tokens generate successfully
- Token verification works
- Refresh prevents expiration issues
- Tests cover edge cases
Relevant Lessons:
Sprint 12: Handle token refresh explicitly to prevent mid-request expiration
Dependencies: None (can start immediately)
```
## Progress Tracking
As work progresses, the orchestrator updates Gitea:
**Add Progress Comment:**
```
add_comment(issue_number=45, body="JWT generation implemented. Running tests now.")
```
**Update Issue Status:**
```
update_issue(issue_number=45, state="closed")
```
**Document Blockers:**
```
add_comment(issue_number=46, body="BLOCKED: Waiting for #45 to complete (dependency)")
```
**Track Parallel Execution:**
```
Parallel Execution Status:
Batch 1:
#45 - JWT service - COMPLETED (12:45)
#48 - API docs - IN PROGRESS (75%)
Batch 2 (now unblocked):
#46 - Login endpoint - READY TO START
#49 - Auth tests - READY TO START
#45 completed! #46 and #49 are now unblocked.
Starting #46 while #48 continues...
```
## Checkpoint Resume Support
If a previous session was interrupted (agent stopped, failure, budget exhausted), checkpoints enable resumption.
**Checkpoint Detection:**
The orchestrator scans issue comments for `## Checkpoint` markers containing:
- Branch name
- Last commit hash
- Completed/pending steps
- Files modified
**Resume Flow:**
```
User: /sprint-start
Orchestrator: Checking for checkpoints...
Found checkpoint for #45 (JWT service):
Branch: feat/45-jwt-service
Last activity: 2 hours ago
Progress: 4/7 steps completed
Pending: Write tests, add refresh, commit
Options:
1. Resume from checkpoint (recommended)
2. Start fresh (lose previous work)
3. Review checkpoint details
User: 1
Orchestrator: Resuming #45 from checkpoint...
✓ Branch exists
✓ Files match checkpoint
✓ Dispatching executor with context
Executor continues from pending steps...
```
**Checkpoint Format:**
Executors save checkpoints after major steps:
```markdown
## Checkpoint
**Branch:** feat/45-jwt-service
**Commit:** abc123
**Phase:** Testing
### Completed Steps
- [x] Step 1
- [x] Step 2
### Pending Steps
- [ ] Step 3
- [ ] Step 4
```
**Sequential Merge:** After completion, merge branches sequentially to detect conflicts.
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
@@ -421,18 +50,3 @@ When executing this command, display the plugin header:
║ [Sprint Name] ║
╚══════════════════════════════════════════════════════════════════╝
```
Replace `[Sprint Name]` with the actual sprint/milestone name from Gitea.
Then proceed with the command workflow.
## Getting Started
Simply invoke `/sprint-start` and the orchestrator will:
1. Review your sprint backlog
2. Analyze dependencies and plan parallel execution
3. Search for relevant lessons
4. Dispatch tasks (parallel when possible)
5. Track progress as you work
The orchestrator keeps you focused, maximizes parallelism, and ensures nothing is forgotten.

View File

@@ -1,247 +1,78 @@
---
description: Check current sprint progress and identify blockers
description: Check current sprint progress, identify blockers, optionally generate dependency diagram
---
# Sprint Status Check
# Sprint Status
This command provides a quick overview of your current sprint progress, including open issues, completed work, dependency status, and potential blockers.
## Skills Required
## What This Command Does
- skills/mcp-tools-reference.md
- skills/progress-tracking.md
- skills/dependency-management.md
1. **Fetch Sprint Issues** - Lists all issues with current sprint labels/milestone
2. **Analyze Dependencies** - Shows dependency graph and blocked/unblocked tasks
3. **Categorize by Status** - Groups issues into: Open, In Progress, Blocked, Completed
4. **Identify Blockers** - Highlights issues with blocker comments or unmet dependencies
5. **Show Progress Summary** - Provides completion percentage and parallel execution status
6. **Highlight Priorities** - Shows critical and high-priority items needing attention
## Purpose
## Usage
Check current sprint progress, identify blockers, and show execution status. Optionally generate a visual dependency diagram.
Simply run `/sprint-status` to get a comprehensive sprint overview.
## MCP Tools Used
This command uses the following Gitea MCP tools:
**Issue Tools:**
- `list_issues(state="open")` - Fetch open issues
- `list_issues(state="closed")` - Fetch completed issues
- `get_issue(number)` - Get detailed issue information for blockers
**Dependency Tools:**
- `list_issue_dependencies(issue_number)` - Get dependencies for each issue
- `get_execution_order(issue_numbers)` - Get parallel execution batches
**Milestone Tools:**
- `get_milestone(milestone_id)` - Get milestone progress
## Expected Output
## Invocation
```
Sprint Status Report
====================
Sprint: Sprint 18 - Authentication System
Milestone: Due 2025-02-01 (5 days remaining)
Date: 2025-01-18
Progress Summary:
- Total Issues: 8
- Completed: 3 (37.5%)
- In Progress: 2 (25%)
- Ready: 2 (25%)
- Blocked: 1 (12.5%)
Dependency Graph:
#45 -> #46 -> #47
|
v
#49 -> #50
Parallel Execution Status:
+-----------------------------------------------+
| Batch 1 (COMPLETED): |
| #45 - Implement JWT service |
| #48 - Update API documentation |
+-----------------------------------------------+
| Batch 2 (IN PROGRESS): |
| #46 - Build login endpoint (75%) |
| #49 - Add auth tests (50%) |
+-----------------------------------------------+
| Batch 3 (BLOCKED): |
| #47 - Create login form (waiting for #46) |
+-----------------------------------------------+
Completed Issues (3):
#45: [Sprint 18] feat: Implement JWT service [Type/Feature, Priority/High]
#48: [Sprint 18] docs: Update API documentation [Type/Docs, Priority/Medium]
#51: [Sprint 18] chore: Update dependencies [Type/Chore, Priority/Low]
In Progress (2):
#46: [Sprint 18] feat: Build login endpoint [Type/Feature, Priority/High]
Status: In Progress | Phase: Implementation | Tool Calls: 45/100
Progress: 3/5 steps | Current: Writing validation logic
#49: [Sprint 18] test: Add auth tests [Type/Test, Priority/Medium]
Status: In Progress | Phase: Testing | Tool Calls: 30/100
Progress: 2/4 steps | Current: Testing edge cases
Ready to Start (2):
#50: [Sprint 18] feat: Integrate OAuth providers [Type/Feature, Priority/Low]
#52: [Sprint 18] feat: Add email verification [Type/Feature, Priority/Medium]
Blocked Issues (1):
#47: [Sprint 18] feat: Create login form [Type/Feature, Priority/High]
Blocked by: #46 (in progress)
Priority Alerts:
1 high-priority item blocked: #47
All critical items completed
Recommendations:
1. Focus on completing #46 (Login endpoint) - unblocks #47
2. Continue parallel work on #49 (Auth tests)
3. #50 and #52 are ready - can start in parallel
/sprint-status # Text-based status report
/sprint-status --diagram # Include Mermaid dependency diagram
```
## Dependency Analysis
## Workflow
The status check analyzes dependencies to show:
1. **Fetch Sprint Issues** - Get all issues for current milestone
2. **Calculate Progress** - Count completed vs total issues
3. **Identify Active Tasks** - Find issues with `Status/In-Progress`
4. **Identify Blockers** - Find issues with `Status/Blocked`
5. **Show Dependency Status** - Which tasks are now unblocked
6. **Parse Progress Comments** - Extract real-time status from structured comments
**Blocked Issues:**
- Issues waiting for other issues to complete
- Shows which issue is blocking and its current status
### If --diagram flag:
**Unblocked Issues:**
- Issues with no pending dependencies
- Ready to be picked up immediately
7. **Fetch Dependencies** - Use `list_issue_dependencies` for each issue
8. **Get Execution Order** - Use `get_execution_order` for batch grouping
9. **Generate Mermaid Syntax** - Create flowchart with status colors
**Parallel Opportunities:**
- Multiple unblocked issues that can run simultaneously
- Maximizes sprint velocity
## Output Format
## Filtering Options
See `skills/progress-tracking.md` for the progress display format.
You can optionally filter the status check:
### Diagram Format (--diagram)
**By Label:**
```
Show only high-priority issues:
list_issues(labels=["Priority/High"])
```mermaid
flowchart TD
subgraph batch1["Batch 1 - No Dependencies"]
241["#241: sprint-diagram"]
242["#242: confidence threshold"]
end
classDef completed fill:#90EE90,stroke:#228B22
classDef inProgress fill:#FFD700,stroke:#DAA520
classDef open fill:#ADD8E6,stroke:#4682B4
classDef blocked fill:#FFB6C1,stroke:#CD5C5C
class 241 completed
class 242 inProgress
```
**By Milestone:**
```
Show issues for specific sprint:
list_issues(milestone="Sprint 18")
```
### Status Colors
**By Component:**
```
Show only backend issues:
list_issues(labels=["Component/Backend"])
```
## Progress Comment Parsing
Agents post structured progress comments in this format:
```markdown
## Progress Update
**Status:** In Progress | Blocked | Failed
**Phase:** [current phase name]
**Tool Calls:** X (budget: Y)
### Completed
- [x] Step 1
### In Progress
- [ ] Current step
### Blockers
- None | [blocker description]
```
**To extract real-time progress:**
1. Fetch issue comments: `get_issue(number)` includes recent comments
2. Look for comments containing `## Progress Update`
3. Parse the **Status:** line for current state
4. Parse **Tool Calls:** for budget consumption
5. Extract blockers from `### Blockers` section
**Progress Summary Display:**
```
In Progress Issues:
#45: [Sprint 18] feat: JWT service
Status: In Progress | Phase: Testing | Tool Calls: 67/100
Completed: 4/6 steps | Current: Writing unit tests
#46: [Sprint 18] feat: Login endpoint
Status: Blocked | Phase: Implementation | Tool Calls: 23/100
Blocker: Waiting for JWT service (#45)
```
## Blocker Detection
The command identifies blocked issues by:
1. **Progress Comments** - Parse `### Blockers` section from structured comments
2. **Status Labels** - Check for `Status/Blocked` label on issue
3. **Dependency Analysis** - Uses `list_issue_dependencies` to find unmet dependencies
4. **Comment Keywords** - Checks for "blocked", "blocker", "waiting for"
5. **Stale Issues** - Issues with no recent activity (>7 days)
## When to Use
Run `/sprint-status` when you want to:
- Start your day and see what needs attention
- Prepare for standup meetings
- Check if the sprint is on track
- Identify bottlenecks or blockers
- Decide what to work on next
- See which tasks can run in parallel
## Integration with Other Commands
- Use `/sprint-start` to begin working on identified tasks
- Use `/sprint-close` when all issues are completed
- Use `/sprint-plan` to adjust scope if blocked items can't be unblocked
| Status | Color | Hex |
|--------|-------|-----|
| Completed | Green | #90EE90 |
| In Progress | Yellow | #FFD700 |
| Open | Blue | #ADD8E6 |
| Blocked | Red | #FFB6C1 |
## Visual Output
When executing this command, display the plugin header followed by a progress block:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
⚡ EXECUTION
📊 STATUS
║ [Sprint Name] ║
╚══════════════════════════════════════════════════════════════════╝
┌─ Sprint Progress ────────────────────────────────────────────────┐
│ [Sprint Name] │
│ ████████████░░░░░░░░░░░░░░░░░░ 40% complete │
│ ✅ Done: 4 ⏳ Active: 2 ⬚ Pending: 4 │
└──────────────────────────────────────────────────────────────────┘
```
Replace `[Sprint Name]` with the actual sprint/milestone name. Calculate percentage from completed vs total issues.
Then proceed with the full status report.
## Example Usage
```
User: /sprint-status
Sprint Status Report
====================
Sprint: Sprint 18 - Authentication System
Progress: 3/8 (37.5%)
Next Actions:
1. Complete #46 - it's blocking #47
2. Start #50 or #52 - both are unblocked
Would you like me to generate execution prompts for the unblocked tasks?
```

View File

@@ -4,92 +4,44 @@ description: Analyze CHANGELOG.md and suggest appropriate semantic version bump
# Suggest Version
## Purpose
Analyze CHANGELOG.md and suggest appropriate semantic version bump.
## Behavior
## Invocation
1. **Read current state**:
- Read `CHANGELOG.md` to find current version and [Unreleased] content
- Read `.claude-plugin/marketplace.json` for current marketplace version
- Check individual plugin versions in `plugins/*/. claude-plugin/plugin.json`
Run `/suggest-version` after updating CHANGELOG or before release.
2. **Analyze [Unreleased] section**:
- Extract all entries under `### Added`, `### Changed`, `### Fixed`, `### Removed`, `### Deprecated`
## Workflow
1. **Read Current State**
- CHANGELOG.md for current version and [Unreleased] content
- marketplace.json for marketplace version
- Individual plugin versions
2. **Analyze [Unreleased] Section**
- Extract entries under Added, Changed, Fixed, Removed, Deprecated
- Categorize changes by impact
3. **Apply SemVer rules**:
3. **Apply SemVer Rules**
| Change Type | Version Bump | Indicators |
|-------------|--------------|------------|
| **MAJOR** (X.0.0) | Breaking changes | `### Removed`, `### Changed` with "BREAKING:", renamed/removed APIs |
| **MINOR** (x.Y.0) | New features, backwards compatible | `### Added` with new commands/plugins/features |
| **PATCH** (x.y.Z) | Bug fixes only | `### Fixed` only, `### Changed` for non-breaking tweaks |
| Change Type | Bump | Indicators |
|-------------|------|------------|
| MAJOR (X.0.0) | Breaking changes | Removed, "BREAKING:" in Changed |
| MINOR (x.Y.0) | New features | Added with new commands/plugins |
| PATCH (x.y.Z) | Bug fixes only | Fixed only |
4. **Output recommendation**:
```
## Version Analysis
**Current version:** X.Y.Z
**[Unreleased] summary:**
- Added: N entries (new features/plugins)
- Changed: N entries (M breaking)
- Fixed: N entries
- Removed: N entries
**Recommendation:** MINOR bump → X.(Y+1).0
**Reason:** New features added without breaking changes
**To release:** ./scripts/release.sh X.Y.Z
```
5. **Check version sync**:
- Compare marketplace version with individual plugin versions
- Warn if plugins are out of sync (e.g., marketplace 4.0.0 but projman 3.1.0)
## Examples
**Output when MINOR bump needed:**
```
## Version Analysis
**Current version:** 4.0.0
**[Unreleased] summary:**
- Added: 3 entries (new command, hook improvement, workflow example)
- Changed: 1 entry (0 breaking)
- Fixed: 2 entries
**Recommendation:** MINOR bump → 4.1.0
**Reason:** New features (Added section) without breaking changes
**To release:** ./scripts/release.sh 4.1.0
```
**Output when nothing to release:**
```
## Version Analysis
**Current version:** 4.0.0
**[Unreleased] summary:** Empty - no pending changes
**Recommendation:** No release needed
```
4. **Output Recommendation**
- Current version
- Summary of changes
- Recommended bump with reason
- Release command
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ Version Analysis ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the version analysis.
## Integration
This command helps maintain proper versioning workflow:
- Run after completing a sprint to determine version bump
- Run before `/sprint-close` to ensure version is updated
- Integrates with `./scripts/release.sh` for actual release execution

View File

@@ -1,177 +0,0 @@
---
name: test-check
description: Run tests and verify coverage before sprint close
---
# Test Check for Sprint Close
Verify test status and coverage before closing the sprint.
## Framework Detection
Detect the test framework by checking for:
| Indicator | Framework | Command |
|-----------|-----------|---------|
| `pytest.ini`, `pyproject.toml` with pytest, `tests/` with `test_*.py` | pytest | `pytest` |
| `package.json` with jest | Jest | `npm test` or `npx jest` |
| `package.json` with mocha | Mocha | `npm test` or `npx mocha` |
| `package.json` with vitest | Vitest | `npm test` or `npx vitest` |
| `go.mod` with `*_test.go` files | Go test | `go test ./...` |
| `Cargo.toml` with `tests/` or `#[test]` | Cargo test | `cargo test` |
| `Makefile` with test target | Make | `make test` |
| `tox.ini` | tox | `tox` |
| `setup.py` with test command | setuptools | `python setup.py test` |
## Execution Steps
### 1. Detect Framework
1. Check for framework indicators in project root
2. If multiple found, list them and ask which to run
3. If none found, report "No test framework detected"
### 2. Run Tests
1. Execute the appropriate test command
2. Capture stdout/stderr
3. Parse results for pass/fail counts
4. Note: Some frameworks may require dependencies to be installed first
### 3. Coverage Check (if available)
Coverage tools by framework:
- **Python**: `pytest --cov` or `coverage run`
- **JavaScript**: Jest has built-in coverage (`--coverage`)
- **Go**: `go test -cover`
- **Rust**: `cargo tarpaulin` or `cargo llvm-cov`
If coverage is configured:
- Report overall coverage percentage
- List files with 0% coverage that were changed in sprint
### 4. Sprint File Analysis
If sprint context is available:
- Identify which sprint files have tests
- Flag sprint files with no corresponding test coverage
## Output Format
```
## Test Check Summary
### Test Results
- Framework: {detected framework}
- Status: {PASS/FAIL}
- Passed: {n} | Failed: {n} | Skipped: {n}
- Duration: {time}
### Failed Tests
- test_name: error message (file:line)
### Coverage (if available)
- Overall: {n}%
- Sprint files coverage:
- file.py: {n}%
- file.py: NO TESTS
### Recommendation
{READY FOR CLOSE / TESTS MUST PASS / COVERAGE GAPS TO ADDRESS}
```
## Behavior Flags
The command accepts optional flags via natural language:
| Request | Behavior |
|---------|----------|
| "run tests with coverage" | Include coverage report |
| "run tests verbose" | Show full output |
| "just check, don't run" | Report framework detection only |
| "run specific tests for X" | Run tests matching pattern |
## Framework-Specific Notes
### Python (pytest)
```bash
# Basic run
pytest
# With coverage
pytest --cov=src --cov-report=term-missing
# Verbose
pytest -v
# Specific tests
pytest tests/test_specific.py -k "test_function_name"
```
### JavaScript (Jest/Vitest)
```bash
# Basic run
npm test
# With coverage
npm test -- --coverage
# Specific tests
npm test -- --testPathPattern="specific"
```
### Go
```bash
# Basic run
go test ./...
# With coverage
go test -cover ./...
# Verbose
go test -v ./...
```
### Rust
```bash
# Basic run
cargo test
# Verbose
cargo test -- --nocapture
```
## Do NOT
- Modify test files
- Skip failing tests to make the run pass
- Run tests in production environments (check for .env indicators)
- Install dependencies without asking first
- Run tests that require external services without confirmation
## Error Handling
If tests fail:
1. Report the failure clearly
2. List failed test names and error summaries
3. Recommend: "TESTS MUST PASS before sprint close"
4. Offer to help debug specific failures
If framework not detected:
1. List what was checked
2. Ask user to specify the test command
3. Offer common suggestions based on file types found
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ 🏁 CLOSING ║
║ Test Verification ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the test check workflow.

View File

@@ -1,131 +0,0 @@
---
description: Generate tests for specified code - creates unit, integration, or e2e tests
---
# Test Generation
Generate comprehensive tests for specified code.
## Usage
```
/test-gen <target> [--type=<type>] [--framework=<framework>]
```
**Target:** File path, function name, class name, or module
**Type:** unit (default), integration, e2e, snapshot
**Framework:** Auto-detected or specify (pytest, jest, vitest, go test, etc.)
## Process
1. **Analyze Target Code**
- Parse function/class signatures
- Identify dependencies and side effects
- Map input types and return types
- Find edge cases from logic branches
2. **Determine Test Strategy**
| Code Pattern | Test Approach |
|--------------|---------------|
| Pure function | Unit tests with varied inputs |
| Class with state | Setup/teardown, state transitions |
| External calls | Mocks/stubs for dependencies |
| Database ops | Integration tests with fixtures |
| API endpoints | Request/response tests |
| UI components | Snapshot + interaction tests |
3. **Generate Tests**
For each target function/method:
- Happy path test (expected inputs → expected output)
- Edge cases (empty, null, boundary values)
- Error cases (invalid inputs → expected errors)
- Type variations (if dynamic typing)
4. **Test Structure**
```python
# Example output for Python/pytest
import pytest
from module import target_function
class TestTargetFunction:
"""Tests for target_function."""
def test_happy_path(self):
"""Standard input produces expected output."""
result = target_function(valid_input)
assert result == expected_output
def test_empty_input(self):
"""Empty input handled gracefully."""
result = target_function("")
assert result == default_value
def test_invalid_input_raises(self):
"""Invalid input raises ValueError."""
with pytest.raises(ValueError):
target_function(invalid_input)
@pytest.mark.parametrize("input,expected", [
(case1_in, case1_out),
(case2_in, case2_out),
])
def test_variations(self, input, expected):
"""Multiple input variations."""
assert target_function(input) == expected
```
5. **Output**
```
## Tests Generated
### Target: src/orders.py:calculate_total
### File Created: tests/test_orders.py
### Tests (6 total)
- test_calculate_total_happy_path
- test_calculate_total_empty_items
- test_calculate_total_negative_price_raises
- test_calculate_total_with_discount
- test_calculate_total_with_tax
- test_calculate_total_parametrized_cases
### Coverage Estimate
- Line coverage: ~85%
- Branch coverage: ~70%
### Run Tests
pytest tests/test_orders.py -v
```
## Framework Detection
| Files Present | Framework Used |
|---------------|----------------|
| pytest.ini, conftest.py | pytest |
| jest.config.* | jest |
| vitest.config.* | vitest |
| *_test.go | go test |
| Cargo.toml | cargo test |
| mix.exs | ExUnit |
## Visual Output
When executing this command, display the plugin header:
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ Test Generation ║
╚══════════════════════════════════════════════════════════════════╝
```
Then proceed with the test generation workflow.
## Integration with /test-check
- `/test-gen` creates new tests
- `/test-check` verifies tests pass
- Typical flow: `/test-gen src/new_module.py` → `/test-check`

View File

@@ -0,0 +1,106 @@
---
description: Run tests with coverage or generate tests for specified code
---
# Test
## Skills Required
- skills/test-standards.md
## Purpose
Unified testing command for running tests and generating new tests.
## Invocation
```
/test # Default: run tests
/test run # Run tests, check coverage
/test run --coverage # Run with coverage report
/test run --verbose # Verbose output
/test gen <target> # Generate tests for target
/test gen <target> --type=unit # Specific test type
/test gen <target> --framework=jest # Specific framework
```
## Mode Selection
- No args or `run`**Run Mode**
- `gen <target>`**Generate Mode**
---
## Mode: Run
Run tests and verify coverage before sprint close.
### Workflow
1. **Detect Framework**
Check for: pytest.ini, package.json, go.mod, Cargo.toml, etc.
2. **Run Tests**
Execute appropriate test command for detected framework.
3. **Check Coverage** (if --coverage or available)
Report coverage percentage.
4. **Sprint File Analysis**
Identify sprint files without tests.
See `skills/test-standards.md` for framework detection and commands.
### DO NOT (Run Mode)
- Modify test files
- Skip failing tests to make run pass
- Run tests in production environments
- Install dependencies without asking
---
## Mode: Generate
Generate comprehensive tests for specified code.
### Arguments
- **Target:** File path, function name, class name, or module
- **--type:** unit (default), integration, e2e, snapshot
- **--framework:** Auto-detected or specified (pytest, jest, vitest, go test)
### Workflow
1. **Analyze Target Code**
Parse signatures, identify dependencies, map types.
2. **Determine Test Strategy**
Based on code pattern:
- Pure function → unit tests with multiple inputs
- Class → instance lifecycle tests
- API endpoint → request/response tests
- Component → render and interaction tests
3. **Generate Tests**
- Happy path cases
- Edge cases (empty, null, boundary)
- Error cases (invalid input, exceptions)
- Type variations (if applicable)
4. **Output File**
Create test file with proper structure and naming.
See `skills/test-standards.md` for test patterns and structure.
---
## Visual Output
```
╔══════════════════════════════════════════════════════════════════╗
║ 📋 PROJMAN ║
║ 🧪 TEST ║
║ [Mode: Run | Generate] ║
╚══════════════════════════════════════════════════════════════════╝
```