Scope and prioritize technical spikes that de-risk architecture or implementation questions.
Use when working in Python with scikit-hep vector and Awkward Array to build vector records, register behaviors, compute deltaR or invariant masses, combine or boost vectors, or access vector properties from ak.zip records of type (Momentum3D/Momentum4D/Vector4D). Vector is only useful if you are also using Awkward.
APM skill resolution. Defines how @skill references resolve to installed SKILL.md files.
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
UI/UX guidelines for app development in this Turborepo (apps/web and future apps). Use when designing or implementing app pages, layouts, navigation, or interactions with Tailwind and @repo/ui components.
[40] PLAN. Create clear action plans with steps, success criteria, and risk awareness. Use before implementing features, making changes, starting projects, or anytime you need a roadmap to success. Triggers on "plan this", "how should we approach", "what's the strategy", "steps to complete", or when facing complex multi-step work.
name: updatekfg
Base UI (@base-ui/react) の公式ドキュメント参照とAPI確認を行うためのスキル。Base UIのコンポーネント/ハンドブック/概要に関する質問が来たら使う。
Comprehensive framework for effective gptme agent onboarding that builds user trust, communicates capabilities clearly, and establishes productive working relationships from the first interaction.
Git domain expert. Knows about: - Status, Switch, Create Branch, Commit, Pull, Push, Log Use when: - User asks about git operations - Context needed before starting work - Reviewing git status - Managing git workflow
Python virtual environment management using uv for fast and reliable environment setup. Create, maintain, and manage Python virtual environments with dependency management. Use uv for environment creation, package installation, dependency resolution, and project configuration. Use when setting up new Python projects, managing dependencies, troubleshooting environment issues, or ensuring reproducible development environments.
This skill enables Claude to provide comprehensive, prioritized performance optimization recommendations for software projects. It is triggered when the user requests performance improvements, optimization suggestions, or asks for a performance review. The skill analyzes frontend, backend, and infrastructure aspects of the project to identify bottlenecks and anti-patterns. It then provides actionable advice, estimates potential performance gains, and suggests a phased implementation roadmap. Use this skill when the user mentions "optimize performance", "performance recommendations", "performance review", "improve speed", or asks about "bottlenecks".
This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured prompts and need assistance transforming them into clear, effective, and well-structured instructions that AI models can better understand and execute. This skill applies comprehensive prompt engineering best practices to enhance prompt quality, clarity, and effectiveness.
エラーや不具合の調査と日本語レポート作成（軽いヒアリング付き・ファイル自動生成）
Plan a new feature before writing code. Explores the codebase, creates a structured plan with verification criteria, and only implements after approval.
Discover and install useful Claude Code plugins for your project. Recommends based on your tech stack.
Audit and improve CLAUDE.md files. Use when rules aren't working, context is bloated, or after learning a lesson that should become a rule.
Mobile-first design thinking and decision-making for iOS and Android apps. Touch interaction, performance patterns, platform conventions. Teaches principles, not fixed values. Use when building React Native, Flutter, or native mobile apps.
DDDアーキテクチャでHonoのバックエンドを新規実装または既存コードベースをリファクタリングする際のガイド。レイヤー構成（domain/application/infrastructure/controller）、依存方向、責務境界、Hono公式ミドルウェア/プラグインの活用、Hono OpenAPIプラグイン（hono-openapi）とzod-openapiの必須採用、Drizzle ORMの利用、トランザクション境界、エラーハンドリング、テスト指針、ESLint/Prettierの必須導入を含む。
Initialize a fork of GoodDocs with fork-specific defaults and a customized doc type.