This skill audits the current branch for compliance with project principles (DDD, TDD, DRY, ISSUE, PROCESS). It verifies all principles were followed before shipping. This skill should be used when the user says "audit", "check compliance", "監査", "原則チェック".
Audits git branches for compliance with project development principles and generates detailed reports.
/plugin marketplace add signalcompose/claude-tools/plugin install code@claude-toolsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
templates/audit-report.mdVerify that the current branch's work follows all project development principles.
$ARGUMENTS (optional): Branch name or phase name to audit.
If empty, audits the current branch against its base (main or parent feature branch).
| Principle | Check | Source |
|---|---|---|
| DDD | Spec document exists in docs/specs/ | CLAUDE.md |
| TDD | Test commits precede implementation commits | CLAUDE.md |
| DRY | No meaningful code duplication across modules | CLAUDE.md |
| ISSUE | GitHub Issues created before implementation | CLAUDE.md |
| PROCESS | Code review and shipping workflow followed correctly | dev-cycle |
git branch --show-current
git merge-base HEAD main
git log --oneline main..HEAD
git diff --stat $(git merge-base HEAD main)...HEAD
Identify base branch, all commits, and all new/modified source and test files.
Check: Does a spec document exist for this work?
Pass criteria:
docs/specs/phase-N-<scope>.mddocs/INDEX.md references the specFail: Missing spec, impact: HIGH
Check: Were tests written before implementation?
Analyze git log for commit patterns:
tests/ without src/ changes)Pass: Evidence of test-first commits in git history Partial pass: Tests comprehensive but written simultaneously Fail: No tests, or tests added after implementation. Impact: MEDIUM
Check: Is there meaningful code duplication across modules?
Look for: duplicated helper functions, copy-pasted logic (>5 lines), repeated constants. Structurally similar code (e.g., MCP tool registrations) is acceptable.
Fail: Significant duplication found. Impact: LOW-MEDIUM
Check: Were GitHub Issues created before implementation?
mcp__github__issue_read for each issuecreated_at vs first implementation commit timestampFail: No issues referenced, or issues created after implementation. Impact: LOW
Check: Was the formal code review and shipping workflow followed?
pr-review-toolkit:code-reviewer Agent used? (manual review NOT acceptable)code-reviewer Agent? (manual echo "$HASH" > /tmp/claude/review-approved-* is a violation)code:shipping-pr skill invoked? (ad-hoc push + PR NOT acceptable)--no-verify avoided?Fail: Any of the above violated. Impact: HIGH
Detection hints:
code:shipping-pr evidence: likely skippedecho "$HASH" > ...: manual circumventionFor the compliance report format, read ${CLAUDE_PLUGIN_ROOT}/skills/audit-compliance/templates/audit-report.md.
Report Generation Rules:
Target: 30-40% size reduction vs Phase 9 reports (feature-audit: 473行 → 280-330行目標).
IMPORTANT: Before committing audit reports, validate metrics against actual test/coverage output.
bash "${CLAUDE_PLUGIN_ROOT}/scripts/validate-audit-metrics.sh"
If validation fails:
npm test and npm run test:coverageThis step prevents metric inconsistencies like Phase 9 (348→355 test count).
code:sprint-impl — verify sprint output before shippingcode:shipping-pr — final gate before PR creationdocs/research/.gh CLI) for issue verificationActivates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.