菜单
Create a new Claude Code skill with best practices. Use when user wants to create a skill, add a SKILL.md, or extend Claude's capabilities.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Generic thinking protocol for deriving optimal solutions through iterative self-checking. Invoke BEFORE searching within the given problem space whenever the user asks for advice, judgment, evaluation, or choice. Reframes the problem, generates options, evaluates trade-offs, runs a self-answer check (does this answer the user's actual question at the right granularity, reach upstream, match expectations, offer non-obvious value?), and loops back to upstream tracing or same-level reframing if the check fails — until convergence. Applies across any domain — technical, process, organizational, decision-making, career. Triggers when the user uses evaluation or reconsideration language ("which is best", "root cause", "is this really needed", "sustainable long-term", "ほんとうに", "そもそも", "最善は", "根本は", "筋が良い"), when validating the soundness of someone's proposal from multiple perspectives, when the problem spans multiple layers (tech / process / org / regulation / UX / cost), or when clear trade-offs exist.
Review the local diff with flat-perspective sub-agents, fix findings in a loop, then create a PR via the create-pr skill once the review is clean
計画や設計について、ユーザーを徹底的に問い詰めて一緒に詰める。実装・着手の前に計画をストレステストしたいとき、または「詰めて」「グリルして」「問い詰めて」「ツッコんで」「設計レビューして」「ほんとうにこれでいい?」などのトリガー表現が出たときに必ず使う。
.claude/rules/ 配下のルールファイル (*.md) を新規作成・編集するときに、適切なメカニズム選択と paths スコープを保証する。ルールを書く前・書いた後に必ず適用する。
Orchestrate Epic issue as team leader. Delegate sub-issues to member agents in isolated worktrees. Members run in background and communicate via SendMessage.
Fetch a GitHub issue with its sub-issues, walk up to the parent Epic, list sibling issues under that Epic, fetch the body of each sibling issue, attach the implementing PR for each closed sibling with body and diff summary, gather related code, and present as a Japanese summary so the reader can grasp the whole task context including the actual contents of siblings and their PRs
| name | create-skill |
| description | Create a new Claude Code skill with best practices. Use when user wants to create a skill, add a SKILL.md, or extend Claude's capabilities. |
| disable-model-invocation | true |
| allowed-tools | Read, Write, Bash(mkdir *), WebFetch |
公式のベストプラクティスに従って、Claude Code の新しいスキルを作成する。
$ARGUMENTS
最新ドキュメントを取得する まず公式の Skills ドキュメントを読む:
WebFetch: https://code.claude.com/docs/en/skills
ユーザーの意図を把握する
スキル種別を決める
スキルディレクトリと SKILL.md を作成する
.claude/skills/<skill-name>/SKILL.md| 設定 | 効果 |
|---|---|
| (既定) | ユーザーも Claude も起動可能 |
disable-model-invocation: true | ユーザーのみ起動可能 (副作用ありの処理向け) |
user-invocable: false | Claude のみ起動可能 (背景知識向け) |
context: fork を使う場面---
name: skill-name
description: What this skill does and when to use it
# Optional fields below:
# disable-model-invocation: true # Only manual invocation
# user-invocable: false # Only Claude can invoke
# allowed-tools: Read, Grep # Restrict tool access
# context: fork # Run in subagent
# agent: Explore # Agent type for fork
---
# Skill Title
Brief description of what this skill does.
## Task
Clear, step-by-step instructions.
Use `$ARGUMENTS` for user input.
Use `$0`, `$1` for positional args.
$ARGUMENTS を使う - 動的なユーザー入力のため