メニュー
Review an existing repository for architecture issues, runtime risks, testing gaps, and code quality regressions. Use when asked to review, audit, harden, or check whether the current implementation is stable.
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。
SOC 職業分類に基づく
Two-layer memory system — read and update long-term facts, recall past events from conversation history.
Browser automation via Playwright MCP — navigate, click, fill forms, take screenshots, scrape pages, run E2E tests. Use when the user needs web automation, testing, or scraping JavaScript-rendered sites.
Structured code review — security, correctness, performance, maintainability. Use when asked to review code, a PR, or a diff.
Analyze CSV, JSON, Excel data; generate charts and reports. Use when the user provides data files or asks for statistics, charts, or data insights.
Deploy applications to cloud platforms — Fly.io, Railway, Vercel, or via SSH. Use when the user wants to publish, deploy, or release an application.
Build, run, and manage Docker containers and images. Use when the user asks about containers, Docker builds, logs, or deployment.
| name | repo-review |
| description | Review an existing repository for architecture issues, runtime risks, testing gaps, and code quality regressions. Use when asked to review, audit, harden, or check whether the current implementation is stable. |
| metadata | {"ccbot":{"emoji":"🧪"}} |
Use this skill when the task is to review an existing codebase rather than build a new feature from scratch.
Channel -> AgentTeam -> Supervisor -> WorkerPool -> Worker.claude/settings.json alignmentAlways summarize:
Prefer:
uv run ruff check .
uv run pytest
If testing a live runtime path, start with CLI before bot channels.