project-template/.claude/skills/plan-writer/SKILL.md
Decompose a story into ultra-granular implementation tasks (2-5 minutes each) with exact file paths, complete code, and verification commands. Use for stories estimated at more than 50 lines of code. Includes a plan-reviewer subagent for validation.
npx skillsauth add adrien-barret/claude-kit plan-writerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You produce implementation plans where each task is a single action taking 2-5 minutes. The plan must be detailed enough for "an enthusiastic junior with no taste or judgment" to execute correctly.
List ALL files that will be created, modified, or tested:
| # | File | Action | Responsibility |
|---|------|--------|----------------|
| 1 | src/services/auth.ts | Create | Authentication service |
| 2 | src/services/auth.test.ts | Create | Auth service tests |
| 3 | src/routes/login.ts | Modify | Add login endpoint |
Each task follows this template:
- [ ] **Step N: {action description}**
- **Files**: {Create|Modify|Test} `path/to/file`
- **Code**:
```{language}
{COMPLETE code — no placeholders, no "add logic here", no TODOs}
```
- **Verify**: `{exact command to run}`
- **Expected**: {what success looks like — test output, HTTP status, etc.}
npm test -- --grep "auth")For code stories, tasks MUST follow RED-GREEN-REFACTOR:
After writing the plan, dispatch a plan-reviewer subagent to validate it (see plan-reviewer-prompt.md). Maximum 3 iterations of review.
Stories estimated at 50 lines or less use the standard plan format (files + approach + criteria mapping). The lead decides the threshold.
data-ai
Data-driven backlog prioritization using WSJF, RICE, value/effort matrix, and dependency analysis.
development
Build a traceability matrix from BMAD artifacts (problem.md, backlog.md, user-journey.md). Detects orphan tasks, orphan stories, and drift between task descriptions and story intent.
development
Generate unit and integration tests for project code. Use when new code is written or test coverage needs improvement.
testing
For each modified function, find or create its test, run it, and update it only if the function contract changed intentionally. Never silently adjust tests to make failures disappear.