888 件 ・ 関連度順
概要と使いどころ
新しいフックの雛形（スクリプト + 配線）を本リポジトリの規約どおりに生成する。 イベント選定（PreToolUse / PostToolUse / Stop / SessionStart 等）とブロッキング可否を対話的に決め、 ai-agents/hooks/ か ai-agents/settings/<cli>/hooks/ への配置と、hooks.json / settings.json への配線まで行う。 新しいフックを追加したいときに `/hook-scaffold <フック名> [用途の一言]` で呼び出す。
Review a GitHub pull request from multiple perspectives in parallel, output only findings, then let the user pick which to fix in the same session. Use when the user asks to review a PR by number, mentions "PRレビュー" / "PR review" with a number, or invokes `/pr-review <number>`. Fans out subagents for absolute-rules, stop-slop, security, architecture, code-quality, testing, and ai-antipattern.
Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and poorly, draft ranked improvement hypotheses, then design and run small n=1/n=2 experiments with pre-declared success criteria, guardrails, stop conditions, and a cost/ROI kill-switch. Load when the user says how did that run go, retro this run, the agent output was bad, what should we improve, draft hypotheses, run a small experiment, or after repeated dev runs of an agentic system produce uneven quality. Priority: output quality over performance over cost, each with diminishing-returns stops. NOT a product A/B test (experimentation), NOT coding-agent harness repair (harness-evolution), NOT production-scale learning (runtime-learning-loop).
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。
Create an Agent SKILL.md fallback for an existing find-XXXX finder that relies on a fragile discovery foundation — above all LLM_DECOMPILE (patterns C/D/E), which matches the decompiled shape of a predecessor function against a stored reference and breaks when a symbol is inlined or de-inlined in a way the reference does not cover. The generated fallback coexists with the preprocessor and runs only when it returns failure, recovering every target robustly by decompiling the predecessor and following the inline/de-inline boundary with semantic anchors. Use when a finder broke on a game update, or you want to durably backstop one before it does. The recipe generalizes to any finder foundation. Triggers: create agent skill fallback, add SKILL.md fallback, robust fallback for finder, backstop LLM_DECOMPILE finder, final guarantee skill
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。
Gives coding agents temporal awareness by reading the session transcript the host already writes, so the agent stops guessing about time and stops repeating commands that just failed. Activates whenever an agent reasons about recency, elapsed time, retry windows, deploy cooldowns, memory or file staleness, idle detection, or any "when / how long ago / how long did that take" question. Required for autonomous, parallel, or long-running agents.
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。
Analyze context and decide on continuation via Stop hook. Use when determining if work should continue, analyzing completion status, making continuation decisions, or implementing the Two-Claude pattern.
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。
Manage DAG execution lifecycles including start, stop, pause, resume, and cleanup. Activate on 'execution lifecycle', 'stop execution', 'abort DAG', 'graceful shutdown', 'kill process'. NOT for cost estimation, DAG building, or skill selection.
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。
Monitors a specified object against explicit stopping criteria and distinguishes replica convergence, iterative progress, and workflow terminal state. NOT for execution or setting goals.
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。
Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use jury_rig-architect), specific tool implementation.
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。
Crabboxの一時環境でネイティブアプリやWebアプリを起動し、チャットのサイドパネルに表示します。動作確認や画面操作、終了時の環境整理も扱います。
直前の説明が分かりにくかったときに、背景を補って説明し直します。簡略化された技術英語の規格とプロジェクトの用語集に沿い、話の流れを伝え直すスキルです。
Laravelの環境設定からコード検査、テスト、依存関係の脆弱性、データベース変更、キューまで順に確認し、マージやデプロイ前の問題を調べるスキル。
コマンド実行やファイル編集、入力・終了時のイベントを条件で検知し、危険な操作や機密ファイルの変更に警告・ブロックを設定するルールを作るスキル。
Claude Codeの利用ログからトークン使用量と推定費用を集計し、モデル・セッション・日付別に確認します。予算との比較やCSV出力にも使えます。
AIエージェントが使うツールの種類や入出力、エラーからの復帰手順を設計・見直します。文脈の情報量も整理し、作業完了率や再試行回数で改善を評価します。
AIエージェントの成果物を、正確さ・網羅性・明瞭さ・実行しやすさ・簡潔さの5軸で自己評価し、根拠付きの点数と優先順位を付けた改善案をまとめます。
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
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。
Beta readers for any draft, run by simulating how a real reader experiences it, moment by moment. A skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author. Use when the user asks for a beta read, beta readers, test readers, human review, reader review, to read something like a human, to be a first reader, whether a piece holds attention or will actually get read, for a quick read of whether a busy skimmer would even open a post, what readers will remember or take away tomorrow, where readers stop reading or bounce, or why a draft still feels off or hollow after anti-slop or humanizer edits. Final gate before publishing; reports where the reading broke; never rewrites.
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。
Preregister a paid eval (bars, arms, decoys, stop rules), dry-run it at zero cost, then run a three-item priced pilot whose spend table gates approval. (gstack)
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。
Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.
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。
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".
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。
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
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。
Caveman at maximum compression: fragments, one word when one word is enough, each fact once. Invoke only with /ultracave or /caveman ultra. Stays on until "stop caveman" or "normal mode".
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。
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
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。