メニュー
Antigravity adapter for the readme-pm-review skill. Read the canonical skill in ai/skills before acting.
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。
Use when working on Python code changes that should follow this repo's shared review and QA loop. Read the shared workflow docs, make the smallest viable patch, run relevant tests, capture results, and route DB, credentials, secrets, or Garmin password related changes through the shared security guidance.
Use when creating or naming branches, pull requests, or commits in this repository. Follow the repo's required type prefixes for branch and PR titles, and write detailed commit messages.
Antigravity adapter for the git-change-conventions skill. Read the canonical skill in ai/skills before acting.
Antigravity adapter for the python-review-qa-loop skill. Read the canonical skill in ai/skills before acting.
Default concise communication overlay for this repository. Read the canonical skill before acting, keep it active by default, and switch to normal wording when safety, irreversible actions, or clarity need more explicit phrasing.
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", "token decrease", or invokes /caveman. Also auto-triggers when token efficiency is requested.
SOC 職業分類に基づく
| name | readme-pm-review |
| description | Antigravity adapter for the readme-pm-review skill. Read the canonical skill in ai/skills before acting. |
Canonical skill source:
ai/skills/readme-pm-review/SKILL.mdThis .agents file is only a thin adapter for Antigravity repo-local skill discovery.
ai/skills/... before acting.ai/skills/... version as the source of truth.