メニュー
Quality verification framework — dimensions, severity levels, grading criteria
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/JSai23/claude-tooling --skill verify-quality-aコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SOC 職業分類に基づく
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
SKILL.md を表示中
| name | verify-quality-a |
| type | action |
| description | Quality verification framework — dimensions, severity levels, grading criteria |
| user-invocable | false |
Action skill — Quality verification procedures: dimensions, severity grading, production readiness checks.
Design quality — Are abstractions earning their complexity? Dependencies pointing right? Module boundaries in the right places? Hidden coupling?
Code integrity — Is the code genuine or performative? Do tests verify real behavior? Does error handling actually handle errors?
Code cleanliness — Unnecessary defensive code? Over-engineered abstractions? Clear naming? Dead code?
Production readiness — Tests pass? No hardcoded secrets? Errors handled? Dependencies pinned?
Critical (must fix) — Crashes, data loss, security vulnerabilities. Fake code that will fail in production. Missing error handling for common failure modes.
Warning (should fix) — Design issues that will cause problems at scale. Inconsistencies that will confuse future sessions. Tests that don't verify real behavior.
Suggestion (consider) — Readability improvements. Minor naming inconsistencies. Simplification opportunities.
Finding no issues is valid. Don't invent problems. Be specific — every finding needs path, line, description.
Every check follows: state what you're checking, run the actual command, show the output, render verdict with evidence.
### [PASS|FAIL] {Check name}
COMMAND: what you ran
OUTPUT: what you saw
VERDICT: Pass/Fail — brief reason
Overall verdict: READY or NOT READY. Don't pass checks you didn't actually run.