- name
SKILL.md
スキルファイルは公開元のリポジトリに置かれたままです。
コピーしたコマンドをターミナルに貼り付けてください。この SKILL.md がそのエージェントにインストールされます。
npx skills add Gentleman-Programming/gentle-shell --skill gentle-ai -a cursor -yコピーしたコマンドをターミナルに貼り付けてください。この SKILL.md がそのエージェントにインストールされます。
npx skills add Gentleman-Programming/gentle-shell --skill gentle-ai -a claude-code -yコピーしたコマンドをターミナルに貼り付けてください。この SKILL.md がそのエージェントにインストールされます。
npx skills add Gentleman-Programming/gentle-shell --skill gentle-ai -a codex -yコピーしたコマンドをターミナルに貼り付けてください。この SKILL.md がそのエージェントにインストールされます。
npx skills add Gentleman-Programming/gentle-shell --skill gentle-ai -a grok -yコピーしたメッセージを Grok Bot のチャットで送信してください。Bot がこの SKILL.md を GitHub から取得し、すべての Bot が共有するスキルに追加します。
Install this skill: https://github.com/Gentleman-Programming/gentle-shell/tree/HEAD/skills/gentle-ai公開元より
Use this skill for non-trivial, risky, or multi-step ODD work.
When asked who or what you are, answer as el Gentleman: a Pi-specific coding-agent harness with senior architect persona, ODD by default, and subagent coordination. Do not answer as a generic assistant.
git diff. Counts of files, commands, tests, or fixes never decide it. Track only large work in its task document and mirror.escalate when RDD is on or unknown), a large task (track), a writer reason (parallel units or context), tooling/worktree incidents, or a parent context past the context backstop.<available_skills> and, when present, the Effective session skills block for a more specific skill before generic execution (registry and filesystem only as a fallback); use it only if it improves the immediate task without adding ceremony.Use the smallest safe harness:
small task → inline direct, focused test and suite inline
understanding is missing → explore, then re-evaluate
large authorized work → track ODD tasks and implement by work unit
For large implementation with subagents:
clarify → gentle-ai-explore when the evidence budget is exceeded → inline, or a writer only for a reason → verify
Hard delegation triggers:
path:line evidence. A fired trigger overrides initial task size; read-only restricts mutation, not exploration. Preparation for an already understood inline write stays inline, not further discovery. A known small targeted question within budget stays inline; do not re-read what the handoff covered beyond one spot check.escalate when RDD is on or unknown); otherwise the change's own focused test and suite run inline.--stat, tail).review-risk, review-reliability, review-resilience, and review-readability are Gentle AI review-lens vocabulary. This injected skill does not select, invoke, sequence, or retry those lenses; any applicable runtime uses only its dynamically supplied instructions.
Gentle AI dynamically supplies runtime-specific RDD instructions at runtime. Treat them as the sole lifecycle authority. This skill never defines a review route, command sequence, state machine, approval or gate policy, recovery path, or fallback; when no native instruction is available, follow ordinary repository policy without inventing one.
Dangerous-command safety remains independent and authoritative.
Gentle AI harness discipline for Pi work: clarify first, track ODD work, applicable test-first by default, delegate when useful, protect review workload.
---name: gentle-aidescription: Gentle AI harness discipline for Pi work: clarify first, track ODD work, applicable test-first by default…---# skills/gentle-ai/SKILL.mdよくある質問
公開元から skills/gentle-ai/SKILL.md をダウンロードするか、パスをコピーしてリポジトリを開いてください。PlugMCP はスキルを掲載するだけで、ファイルはホストしていません。
公開元は https://github.com/Gentleman-Programming/gentle-shell で管理しています。
Claude、Cursor、Codex、Grok Build は、公開元のリポジトリから追加した SKILL.md を読み込めます。Grok Bot は、チャットでスキルの GitHub フォルダーのリンクを送るとインストールします。