Migrate existing ADRs to YAML frontmatter format. Scans docs/decisions/ for ADRs without frontmatter, infers status from body text, shows dry-run for approval. Trigger: /adr-migrate
The English summary is being prepared. Showing the original description.
Start or resume an ADR session. Without number: show status overview and recommend next actionable ADR. With number: provide phase-specific guidance. Trigger: /adr-session, /adr-session NNN, /adr-session new
The English summary is being prepared. Showing the original description.
Analyze a project's harness maturity and guide staged adoption of Harness Engineering best practices (quality loops, safety gates, linters, CLAUDE.md optimization).
The English summary is being prepared. Showing the original description.
Standardized bug fix workflow using TDD (Red-Green-Refactor). Use when fixing bugs, resolving issues, or when the user invokes /bugfix. Ensures root cause analysis, failing test first, then minimal fix.
The English summary is being prepared. Showing the original description.
Create detailed specifications by iteratively clarifying unclear points for Plan mode. Use when: After completing a plan when detailed requirements need clarification before implementation.
The English summary is being prepared. Showing the original description.
Execute a pre-existing plan file by implementing tasks sequentially with test verification after each step. Use when plan/tasks are already decomposed and ready for implementation.
The English summary is being prepared. Showing the original description.
Distill ★ Insight blocks from session logs on demand (force), read the resulting digest, and decide which entries to promote into skills, ~/.claude/rules/, or CLAUDE.md. Also supports acknowledgement (ack). Use when you want to review accumulated insights now, or when a SessionStart notice points to a new digest.
The English summary is being prepared. Showing the original description.
Re-evaluate auto-review findings against the original order's intent. Filters out findings that bend the intent to reduce scope. Use after Document Workflow auto-review completes (step 5→6), or when review feedback feels like it's distorting the original goal.
The English summary is being prepared. Showing the original description.
日本語の文章を直す、書き起こすときに、文書の構成を動かすか保つかと、複数の入口を重ねて使うときの順と検査の持ち方を決める共通の判断。koncise、tanteki、yomiyasu、japanese-tech-writing から参照される役割スキルで、単独では使わない。入口のスキルが読むか、利用者がこの名前で頼んだときだけ読む。
The English summary is being prepared. Showing the original description.
日本語の技術文書・書籍原稿の文章規範。整形（一文一行、引用ブロック、脚注、コラム記法）、段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。
The English summary is being prepared. Showing the original description.
日本語の文章を、ADHD の読み手が読んですぐ動ける形に直す規範。冒頭に次の行動を置き、手順に番号を振り、脇道を後ろへ移し、前置きと締めを消す。事実・数値・条件は変えず、足りない見積もりや行動は足さずに確認点として返す。rewrite（書き直す）と check（問題点だけ挙げる）がある。`/koncise`、または「koncise で直して」のようにスキル名として頼まれたときだけ使う。英単語の concise（「もっと concise に」など）が使われただけの依頼、名前を出さない執筆や推敲の依頼、コード、英語の文章には使わない。
The English summary is being prepared. Showing the original description.
作業中に得た「次のセッションでも役立つ事実」を repo ごとの学びとして記録・参照・削除する。失敗から修正に至った手順、利用者の訂正、エラーになったコマンドと通ったコマンド、利用者が明言した方針を得たとき、または過去の学びを確認・削除したいときに使う。
The English summary is being prepared. Showing the original description.
Validate logical consistency of decisions and claims through context forking. Use proactively when judgment validity is unclear, but prefer direct tools (Read, Bash) for simple verifications like file contents or test results.
The English summary is being prepared. Showing the original description.
Analyze and refine existing Claude Code Skills for conciseness and effectiveness. Use when asked to "review", "refine", "improve", "optimize" Skills, or when user mentions "skill quality", "skill refinement", "too verbose", "skill doesn't trigger", "description quality", or wants to make a Skill more concise. Do NOT use for creating new skills from scratch (use skill-creator instead).
The English summary is being prepared. Showing the original description.
Save current session's problem context as a memo file for cross-session reference. Uses sub-agent to minimize context consumption. Supports two modes - summarize current session or read a past session by ID.
The English summary is being prepared. Showing the original description.
Setup Claude Code skills from berlysia/dotfiles for web version in other projects. Creates .claude/settings.json with auto-update hook. Use when setting up skills for web version or when user asks to configure, install, or setup external Claude Code skills for web.
The English summary is being prepared. Showing the original description.
Verify and enrich task descriptions to ensure each is independently executable with sufficient context. Use when "enriching tasks", "preparing handoff", "verifying task quality", or before running /task-handoff.
The English summary is being prepared. Showing the original description.
Design test viewpoints and test cases from code changes using ISO 25010. Use when writing test plans for plan.md, reviewing PR test coverage, or when asked to 'テスト設計', 'テスト観点洗い出し', 'design test cases'. Do NOT use for writing test code or TDD workflows (use /bugfix).
The English summary is being prepared. Showing the original description.
Explain a topic, piece of code, concept, or error for one fixed reader: a visually-oriented high school student who reasons logically and is curious. Leads with a figure chosen to fit the idea (a table, a Mermaid diagram, an ASCII sketch, or a local HTML page with SVG, Canvas, or 3D when the idea is spatial or moves), walks the cause-and-effect chain without skipping steps, names the real terms, and marks every simplification. Use when the user says 'ELI5', 'explain like I'm', 'dumb it down', 'break this down', 'simplify this', 'かみくだいて', '噛み砕いて', '図解して', '図で説明して', '高校生でも分かるように', or invokes /visual-eli. Do NOT use when the user names a different audience (a manager, a child, a specific person) or wants a document, a crash course, or a tutorial as the deliverable — use explainer for those.
The English summary is being prepared. Showing the original description.
Policy-enforcing installer that deploys hardened Claude Code Action workflows (`@claude` manual mention + dependency-bot auto-fix) into a personal GitHub repository the user administers. Use when asked to introduce Claude Code Action, apply `@claude` mention support, or set up automated CI auto-fix for dependency bot PRs, using the security-hardened templates shipped with this skill.
The English summary is being prepared. Showing the original description.
説明的な文章に緩急を設計するための規範。緩急を装飾ではなく認知モードの切替（観察→逡巡→断定→再観察）と未回収の緊張の管理として扱い、文の拍、段落の密度波形、節の入り方、緩みと駄文の判別、執筆後の機械的な点検手順を定める。読み物として読ませたい章・記事・解説文を生成するとき、または「密度はあるが平坦でおもしろくない」文章を診断・修正するときに使用する。
The English summary is being prepared. Showing the original description.
Evaluate plan.md design decisions for dominant-axis misalignment using the Decision Quality framework. Detects when a plan optimizes for the wrong evaluation axis given the nature of the change. Use during plan review alongside logic-validator and scope-justification-reviewer.
The English summary is being prepared. Showing the original description.
Decompose complex tasks into detailed, actionable todos. Each todo has a rich description that is executable from the description alone.
The English summary is being prepared. Showing the original description.
Comprehensive documentation audit and refresh. Checks code-documentation drift, generates prioritized report, then updates with approval. Use for: 'ドキュメント監査', 'docs audit', 'ドキュメント棚卸し', 'README全体見直し', 'documentation health check'.
The English summary is being prepared. Showing the original description.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)