skills/src/completion-audit/SKILL.md
Audits product completion after task-level PASS artifacts exist. Use when the plan or Ralph story metadata marks a completion gate for a public CLI/API/runtime/release claim; otherwise it is optional.
npx skillsauth add shuymn/dotfiles completion-auditInstall 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.
<skill-root> means the directory containing this SKILL.md.<skill-root> as appropriate.Run a final product-level audit after task implementation, dod-recheck, and adversarial verification have finished.
setup-ralph propagated completion_gate: true for the plan or target storyplan.mdplan.review.mdplan.md and confirm whether a completion audit is required by plan scope or propagated story metadata.plan.review.md is PASS.completion.audit.md.# <Topic> Completion Audit
## Audit Metadata
- **Source Artifact**: [plan path]
- **Reviewed At**: [timestamp]
- **Overall Verdict**: PASS | FAIL
## Product-Path Smoke
| # | Surface | Command | Exit Code | Verdict | Evidence |
|---|---------|---------|-----------|---------|----------|
| 1 | [cli/api/runtime] | [command] | [code] | PASS/FAIL | [evidence] |
## Open Completion Gaps
| # | Area | Gap | Required Re-run |
|---|------|-----|-----------------|
| 1 | [boundary/artifact/ac-owner] | [description] | [dod-recheck/adversarial/completion-audit] |
## Decision
- Completion claim: confirmed/revoked
- Reason: [rationale]
Stop and report failure when:
Task completion and product completion are different gates. completion-audit exists to verify the latter.
development
Simplifies recently changed code by running three parallel reviews (reuse, quality, efficiency) and applying only behavior-preserving fixes. Use when the user asks to simplify, clean up, reduce duplication, improve code reuse, or optimize recently changed code, a staged diff, a branch diff, or explicitly listed files. Also use when the user says things like 'simplify this', 'まとめて整理して', 'コードをスリムにして', or invokes `/simplify`.
tools
Use when the user invokes /workflow. Injects project workflow methodology as context. Accepts argument: plan, exec, review (default: all).
development
Processes AI reviewer feedback and applies only verified fixes. Works in two modes: (1) fetches comments from a PR URL or current branch, (2) processes feedback pasted directly into the conversation. Trigger when the user wants to bulk-process or apply AI review suggestions — from a GitHub PR or pasted text. Do NOT trigger for single questions about what a bot said, or general code review discussion.
testing
Prepares .ralph/ runtime state from an approved and reviewed plan bundle. Syncs plan tasks into prd.json and updates prompt.run.md with project-specific context and quality gates. Use after plan approval, decompose-plan review PASS, and ralph init.