lmiranda
2d51df7a42
Phase 1b: Rename all ~94 commands across 12 plugins to /<noun> <action> sub-command pattern. Git-flow consolidated from 8→5 commands (commit variants absorbed into --push/--merge/--sync flags). Dispatch files, name: frontmatter, and cross-reference updates for all plugins. Phase 2: Design documents for 8 new plugins in docs/designs/. Phase 3: Scaffold 8 new plugins — saas-api-platform, saas-db-migrate, saas-react-platform, saas-test-pilot, data-seed, ops-release-manager, ops-deploy-pipeline, debug-mcp. Each with plugin.json, commands, agents, skills, README, and claude-md-integration. Marketplace grows from 12→20. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1.2 KiB
1.2 KiB
name
| name |
|---|
| data setup |
/data setup - Data Platform Setup Wizard
Skills to Load
- skills/setup-workflow.md
- skills/visual-header.md
Visual Output
Display header: DATA-PLATFORM - Setup Wizard
Usage
/data setup
Workflow
Execute skills/setup-workflow.md phases in order:
Phase 1: Environment Validation
- Check Python 3.10+ installed
- Stop if version too old
Phase 2: MCP Server Setup
- Locate MCP server (installed or source path)
- Check/create virtual environment
- Install dependencies if needed
Phase 3: PostgreSQL Configuration (Optional)
- Ask user if they want PostgreSQL access
- If yes: create
~/.config/claude/postgres.env - Test connection and report status
Phase 4: dbt Configuration (Optional)
- Ask user if they use dbt
- If yes: explain auto-detection via
dbt_project.yml - Check dbt CLI installation
Phase 5: Validation
- Verify MCP server can be imported
- Display summary with component status
- Inform user to restart session
Important Notes
- Uses Bash, Read, Write, AskUserQuestion tools (NOT MCP tools)
- MCP tools unavailable until session restart
- PostgreSQL and dbt are optional - pandas works without them