Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
meta-agent-skills
Proactively analyzes the codebase and generates specialized subagents and skills to standardize agentic workflows.
majiayu000/claude-skill-registry 163
-
llm-application-patterns
This skill should be used when building production LLM applications in any language. It applies when implementing predictable AI features, creating structured interfaces for LLM operations, configuring language model providers, building agent systems with tools, optimizing prompts, or testing LLM-powered functionality. Covers language-agnostic patterns for type-safe contracts, modular composition, multi-provider support, and production deployment.
majiayu000/claude-skill-registry 163
-
longitudinal-drift-detector
Detect behavioral drift and alignment degradation over time.
majiayu000/claude-skill-registry 163
-
eval-review
Review LLM-generated diff classifications for the diffview eval system. Use when the user invokes this skill or pastes yanked case data from evalreview (containing "# Diff Classification Review" header). Evaluates whether classifications accurately help code reviewers, provides pass/fail verdict with detailed critique.
majiayu000/claude-skill-registry 163
-
TDD Methodology
This skill should be used when the user asks to "write tests first", "use TDD", "test-driven development", "red green refactor", "test first", "add unit tests before code", "write regression test first", "safe refactor with tests", or when TDD mode is active and the user makes any coding request that affects behavior (features, bugs, refactors).
majiayu000/claude-skill-registry 163
-
mobile-app-developer
Expert mobile app developer specializing in native and cross-platform development for iOS and Android. Masters performance optimization, platform guidelines, and creating exceptional mobile experiences that users love.
majiayu000/claude-skill-registry 163
-
ynab
Manage YNAB budgets, accounts, categories, and transactions via CLI.
majiayu000/claude-skill-registry 163
-
analyzing-backtests
Analyzes algorithmic trading backtest results from Jupyter notebooks and generates summary reports. Use when the user wants to analyze or summarize backtest notebooks.
majiayu000/claude-skill-registry 163
-
architecture-review-and-approval
Run structured architecture reviews with stakeholders and sign-off.
majiayu000/claude-skill-registry 163
-
marp-slide-creator
Marp を使用してプレゼンテーション用スライドの Markdown ファイルを作成するスキル。ユーザーの要望に基づいて、Marp の機能（ディレクティブ、画像構文、フラグメントリスト、テーマ設定等）をフル活用した高品質なスライドを生成します。「スライドを作成して」「プレゼン資料を作って」「Marp でスライドを書いて」「発表資料を Markdown で作成して」等のリクエストで使用してください。
majiayu000/claude-skill-registry 163
-
google-ads-mcp-navigator
Streamlined guide for Google Ads API queries via MCP. Use when querying campaign performance, keyword metrics, conversion data, auction insights, or ad group analysis. Reduces context overhead by providing curated field references and common query patterns. Triggers on Google Ads, SEM performance, campaign analysis, keyword research, or auction insights requests.
majiayu000/claude-skill-registry 163
-
designing-growth-loops
Help users design and optimize growth loops. Use when someone is building viral mechanics, designing referral programs, creating product-led acquisition, or figuring out how to make their product grow itself.
majiayu000/claude-skill-registry 163
-
documenso-observability
Implement monitoring, logging, and tracing for Documenso integrations.
Use when setting up observability, implementing metrics collection,
or debugging production issues.
Trigger with phrases like "documenso monitoring", "documenso metrics",
"documenso logging", "documenso tracing", "documenso observability".
majiayu000/claude-skill-registry 163
-
choose-framework
Select the right strategic framework for your situation through exploratory dialogue. Use when user describes a problem, decision, or challenge; needs structured thinking approach; mentions "strategy", "decision", or "problem-solving"; or asks "how should I think about this?". Creates framework selection briefs in .frameworks-output/ folder.
majiayu000/claude-skill-registry 163
-
expo-expert
Comprehensive Expo expert with access to complete official documentation covering React Native development, EAS Build, EAS Submit, EAS Update, Expo Router, Expo Modules API, configuration, deployment, and all platform features. Invoke when user mentions Expo, React Native, EAS, Expo Router, mobile app development, iOS/Android development, or cross-platform development.
majiayu000/claude-skill-registry 163
-
openwebf-host-theming-sync
Sync theming between Flutter and WebF (automatic theme sync, prefers-color-scheme, dark mode patterns). Use when the user mentions theme sync, dark mode, prefers-color-scheme, CSS variables, or WebF theming from MaterialApp.
majiayu000/claude-skill-registry 163
-
testing-production
Production validation specialist ensuring applications are fully implemented and deployment-ready. Use to verify no mock/stub/fake implementations remain, validate against real databases and APIs, perform end-to-end testing with actual systems, and confirm production readiness.
majiayu000/claude-skill-registry 163
-
react-frontend-spa
ReactでSPAフロントエンドを実装・改修するためのガイド。バックエンド分離前提でNext.jsやサーバーサイド機能に依存せず、React Router中心のクライアント実装を行う時に使う。認証はAuthProviderとuseAuthカスタムフックで統一し、OpenAPIからorvalまたはopenapi-typescriptで型/クライアントを生成して利用する。ESLint+Prettier、zod、shadcn/ui、デザイントークン（CSS変数/Tailwindテーマ）を前提にする場合に適用する。ディレクトリ構成はmodules/components/hooks/providers/servicesなどの直感的な命名で複雑化に耐える構成にする。
majiayu000/claude-skill-registry 163
-
workflow-phase-convention
全ワークフローで一貫したPhase番号体系、承認ゲート規約、最大リトライ回数の標準を定義
majiayu000/claude-skill-registry 163
-
signal-intel
Use when consolidating intent, product usage, and third-party signals to prioritize ABM actions.
majiayu000/claude-skill-registry 163
-
auditing-project
Audits the project for consistency issues that may arise from manual editing. Checks package scripts, tsconfig paths, README tables, and other conventions.
majiayu000/claude-skill-registry 163
-
ln-111-root-docs-creator
Creates 4 root documentation files (CLAUDE.md, docs/README.md, documentation_standards.md, principles.md). L3 Worker invoked by ln-110-project-docs-coordinator.
majiayu000/claude-skill-registry 163
-
funsloth-local
Training manager for local GPU training - validate CUDA, manage GPU selection, monitor progress, handle checkpoints
majiayu000/claude-skill-registry 163
-
set-current-spec
This skill should be used when switching between specs, after creating a new spec with "/spec-kit:specify", when the user says "switch to spec 002" or "work on feature X", or when resuming work on a different feature. Updates progress.yml with the current working specification.
majiayu000/claude-skill-registry 163