Claude Skills

Intelligent skill recommendation and activation system. Use when: (1) user asks what skills are available, (2) user needs help choosing the right skill for a task, (3) user wants to find and install new skills, (4) analyzing ANY prompt to determine which skills would help, (5) user says "подбери скилл", "какой скилл использовать", "recommend skills". This skill should activate automatically at session start to analyze user intent and suggest relevant skills.

Rewrite branch into clean, narrative-quality commits. Creates backup, reimplements on fresh branch, verifies byte-identical, then replaces original branch history.

Create a BRAND_GUIDELINES.md that defines how to communicate with your customer. Requires CUSTOMER.md to exist first. Covers voice, tone, language rules, messaging framework, and copy patterns.

Update main/master from origin, rebase current branch on it, resolve conflicts, and push.

Captures writing style/voice into AUTHOR_VOICE.md so AI can write like the user. Use when asked to match tone, write like me, replicate voice, or capture writing style for content generation.

Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.

Iteratively auto-optimize a prompt until no issues remain. Uses prompt-reviewer in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill. Runs until converged.

Audit UI/UX changes in a focus area against design guidelines for accessibility, consistency, and usability issues.

The main entry point. Understands your codebase and routes to the right workflow. Use when starting a session, saying "let's work on something", or unsure which Arc command to use. Gathers context and asks what you want to do.

GitHub PRから未対応のコメントを取得します。GraphQL APIで (1) コード特定行への未解決Review threads（Resolve可能）と (2) コードブロックを含むIssue comments（会話タブ、Resolve不可）の両方を取得し、JSON形式で出力します。PR情報（番号・タイトル・URL・状態・作成者・レビュアー）も含まれます。

View and manage the progress journal for knowledge persistence across sessions. Use when asked to "show progress", "what have we done", "add a note", or when you need context from previous sessions.

git worktree を利用した分離作業環境を自動構築します。デフォルトブランチから最新コードを取得し、.git-worktrees/ ディレクトリに新規worktreeを作成、.env・npm依存関係を自動セットアップします。ブランチ名の '/' は自動的に '-' に変換されます。既存worktreeは再利用されます。

GitHub PRの未解決Review threadsを一括Resolveします。GraphQL APIで未解決のReview threads（コード特定行へのコメント）を取得し、resolveReviewThread mutationで全て自動的にResolveします。Issue comments（会話タブ）は元々Resolve機能がないため対象外です。各スレッドのResolve結果を表示します。

Professional skill creation with research-driven workflow and automated validation. USE WHEN: Creating new skills, validating existing skills, deciding between Skills vs Subagents, migrating documents to skills, or running individual validation tools. PRIMARY TRIGGERS: "create skill" = Full creation (12 steps with research + execution planning) "validate skill" = Validation workflow (steps 3-8) "Skills vs Subagents" = Decision workflow (step 0) "convert doc to skill" = Migration workflow "estimate tokens" = Token optimization "security scan" = Security audit WORKFLOW COMPLIANCE: Structured workflows with validation checkpoints. Research phase (Step 1c-1d) ensures skills based on proven approaches. DIFFERENTIATOR: Research-driven creation. Web search (3-5 queries) before building. Multi-proposal generation. 9 automation scripts. Quality 9.0+/10. REUSED: Anthropic's init_skill.py and package_skill.py (production-tested).

Create, update, validate, and canonicalize Claude Code skills. USE WHEN user wants to create a new skill OR modify an existing skill OR validate skill structure OR fix skill format OR migrate legacy skills.

ライブラリの情報を確認するためのスキル。Next.js、shadcn、その他のライブラリについて、適切なMCPサーバーを使用して最新のドキュメントと使用方法を取得します。

git worktree を利用した分離作業環境を自動構築します。デフォルトブランチから最新コードを取得し、.git-worktrees/ ディレクトリに新規worktreeを作成、.env・npm依存関係を自動セットアップします。ブランチ名の '/' は自動的に '-' に変換されます。既存worktreeは再利用されます。

GitHub Issueの内容を取得します。ghコマンドを使用してIssueのタイトル、本文、コメント、ラベル、アサイン情報などを取得します。