lmiranda
7c8a20c804
Refactored commands to extract reusable skills following the Commands → Skills separation pattern. Each command is now <50 lines and references skill files for detailed knowledge. Plugins refactored: - claude-config-maintainer: 5 commands → 7 skills - code-sentinel: 3 commands → 2 skills - contract-validator: 5 commands → 6 skills - data-platform: 10 commands → 6 skills - doc-guardian: 5 commands → 6 skills (replaced nested dir) - git-flow: 8 commands → 7 skills Skills contain: workflows, validation rules, conventions, reference data, tool documentation Commands now contain: YAML frontmatter, agent assignment, skills list, brief workflow steps, parameters Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
45 lines
980 B
Markdown
45 lines
980 B
Markdown
# /run - Execute dbt Models
|
|
|
|
## Skills to Load
|
|
- skills/dbt-workflow.md
|
|
- skills/mcp-tools-reference.md
|
|
- skills/visual-header.md
|
|
|
|
## Visual Output
|
|
|
|
Display header: `DATA-PLATFORM - dbt Run`
|
|
|
|
## Usage
|
|
|
|
```
|
|
/run [model_selection] [--full-refresh]
|
|
```
|
|
|
|
## Workflow
|
|
|
|
Execute `skills/dbt-workflow.md` run workflow:
|
|
|
|
1. **Pre-validation** (MANDATORY): Run `dbt_parse` first
|
|
2. **Execute models**: Use `dbt_run` with selection
|
|
3. **Report results**: Status, execution time, row counts
|
|
|
|
## Selection Syntax
|
|
|
|
See `skills/dbt-workflow.md` for full selection patterns.
|
|
|
|
## Examples
|
|
|
|
```
|
|
/run # Run all models
|
|
/run dim_customers # Run specific model
|
|
/run +fct_orders # Run model and upstream
|
|
/run tag:daily # Run models with tag
|
|
/run --full-refresh # Rebuild incremental models
|
|
```
|
|
|
|
## Required MCP Tools
|
|
|
|
- `dbt_parse` - Pre-validation (ALWAYS RUN FIRST)
|
|
- `dbt_run` - Execute models
|
|
- `dbt_build` - Run + test
|