Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never invoke it on your own.
日本語の概要は準備中です。原文の説明を表示しています。
dzhng/skills1,2902026年10月12日 更新
無料GitHub で公開
review
Closeout pass on a finished substantive change — sequence refactor-clean (shape), code-review (diff), and write-docs (docs) so all three run, in the order where each feeds the next. Use after implementing a slice or feature and before calling it done or committing; when the user asks for a final review, a cleanup-and-document pass, or to "review everything." For a diff-only audit, reach code-review directly.
含まれるファイル（1）
- SKILL.md1.8 KB
SKILL.md（原文）
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Review
A finished change earns "done" only after three lenses pass: its shape, its diff, and its docs. Each has a specialist skill. This skill owns only what they can't — the order they run in, the loop between them, and one verdict.
Workflow
- Scope. Fix the diff under review and confirm it's substantive; skip the whole pass for trivial edits.
- Shape — refactor-clean. Run it first, while restructuring is cheap and before you audit a diff that's about to move.
- Diff — code-review. Audit the settled shape. A finding that forces a structural change sends you back to step 2, not onward.
- Docs — write-docs. Update the docs this change touched. Then trace the link chain from the root README down to each one: every link on the path still resolves, and the hub-to-leaf flow still reads in order.
- Report. One verdict across all three passes — what each found, what you changed, what you left and why. Done only when every pass is clean or resolved.
Rules
- When you enter a pass, read its skill — the rules live there, not here.
- Order governs presentation, not disclosure: surface a finding the moment you hit it, even when a later pass owns it.
- Loop, don't cascade: a later fix that reopens an earlier pass returns there. Stop when a full pass adds nothing.
レビュー
まだレビューはありません。使ってみた感想をお寄せください。
同じリポジトリのスキル
概要と使いどころ
Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it. Use when the user wants to review the decisions the AI made on their behalf, before merging or committing AI-implemented work, when integrating a delegated subagent's pass, or when a fix "works" but might be a point fix.
日本語の概要は準備中です。原文の説明を表示しています。
dzhng/skills1,2902026年10月12日 更新
Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling for no-progress loops, rank a performance backlog, or implement the next simple performance fixes.
日本語の概要は準備中です。原文の説明を表示しています。
dzhng/skills1,2902026年10月12日 更新
Audit whether tests earn their maintenance cost and which suite owns each contract. Use when pruning redundant tests, investigating implementation coupling or test-only production hooks, reviewing the value of proposed coverage, or auditing an entire subsystem. Use write-tests to implement the resulting test changes.
日本語の概要は準備中です。原文の説明を表示しています。
dzhng/skills1,2902026年10月12日 更新
Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts, configurations, or other artifacts against a goal or benchmark, or when a long research run needs a planned hypothesis queue, focused trials, and durable findings.
日本語の概要は準備中です。原文の説明を表示しています。
dzhng/skills1,2902026年10月12日 更新
claude
無料Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude. Supports selecting `--model` and thinking/effort level with defaults of `opus` and `high`.
日本語の概要は準備中です。原文の説明を表示しています。
dzhng/skills1,2902026年10月12日 更新