Claude Skills

Verify test coverage for code changes. Analyzes diff against main and reports coverage gaps.

Audit TypeScript code for type safety issues—any/unknown abuse, invalid states, missing narrowing.

Run all code review agents in parallel (bugs, coverage, maintainability, simplicity, type-safety if typed, CLAUDE.md adherence, docs). Respects CLAUDE.md reviewer configuration.

Internal verification runner. Executes all verification methods from definition against codebase. Called by /do, not directly by users.

Implements scroll-driven storytelling experiences with pinned sections, progressive reveals, and scroll-linked animations. Use when asked to build scrollytelling, scroll-driven animations, parallax effects, narrative scroll experiences, or story-driven landing pages.

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.

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.

Review and analyze LLM prompts using the 10-Layer Architecture. Provides detailed assessment without modifying files.

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.

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

Persistent task backlog that survives across sessions. Git-committed, always available. Use when asked to "add a task", "show my tasks", "update the backlog", "prioritize", or when managing what needs to be done across sessions.

スキルを作成・更新・プロンプト改善するためのメタスキル。 **collaborative**モードでユーザーと対話しながら共創し、 抽象的なアイデアから具体的な実装まで柔軟に対応する。 **orchestrate**モードでタスクの実行エンジン（Claude Code / Codex / 連携）を選択。 Anchors: • Continuous Delivery (Jez Humble) / 適用: 自動化パイプライン / 目的: 決定論的実行 • The Lean Startup (Eric Ries) / 適用: Build-Measure-Learn / 目的: 反復改善 • Domain-Driven Design (Eric Evans) / 適用: 戦略的設計・ユビキタス言語・Bounded Context / 目的: ドメイン構造の明確化 • Clean Architecture (Robert C. Martin) / 適用: 依存関係ルール・層分離設計 / 目的: 変更に強い高精度スキル • Design Thinking (IDEO) / 適用: ユーザー中心設計 / 目的: 共感と共創 Trigger: 新規スキルの作成、既存スキルの更新、プロンプト改善を行う場合に使用。 スキル作成, スキル更新, プロンプト改善, skill creation, skill update, improve prompt, Codexに任せて, assign codex, Codexで実行, GPTに依頼, 実行モード選択, どのAIを使う

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.

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 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。

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.

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).

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。

Generates metadata for research documents and specifications including date/time, git commit, branch, and repository info. Use when creating research documents, handoffs, or any documentation that needs timestamp and git metadata.