Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
prompt-library
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
majiayu000/claude-skill-registry 163
-
go-dev-guidelines
This skill should be used when writing, refactoring, or testing Go code. It provides idiomatic Go development patterns, TDD-based workflows, project structure conventions, and testing best practices using testify/require and mockery. Activate this skill when creating new Go features, services, packages, tests, or when setting up new Go projects.
majiayu000/claude-skill-registry 163
-
blogwatcher
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
majiayu000/claude-skill-registry 163
-
fpkit-component-builder
Build React components using @fpkit/acss library patterns. Scaffolds complete component structures (tsx, types, scss, stories, tests), validates CSS variables follow naming conventions (--component-property with rem units), enforces TypeScript patterns, accessibility standards (WCAG 2.1 AA), and Storybook documentation. Use when building new components, generating boilerplate, or refactoring to use fpkit primitives. Includes automation scripts, reference guides, and templates.
majiayu000/claude-skill-registry 163
-
refactor-form-to-builder
将传统表单页面重构为使用 FormBuilderWrapper 的声明式表单。自动检测表单字段，检查是否有对应的封装 field 组件，如果没有则先创建 field 包装器，然后将表单转换为 FormFieldConfig 列表形式，减少重复代码
majiayu000/claude-skill-registry 163
-
Setting up Next.js Project
Configure Next.js projects with ESLint, Prettier, and recommended settings. Use when initializing Next.js projects, setting up linting, or when user mentions Next.js setup/Next.jsセットアップ.
majiayu000/claude-skill-registry 163
-
typescript-strictest-standards
majiayu000/claude-skill-registry 163
-
mobile-design
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.
majiayu000/claude-skill-registry 163
-
curate-delta
Synthesize Reflector insights into structured delta proposals for playbook updates, following ACE paper's Curator architecture
majiayu000/claude-skill-registry 163
-
prediction-tracking
Track and evaluate AI predictions over time to assess accuracy. Use when reviewing past predictions to determine if they came true, failed, or remain uncertain.
majiayu000/claude-skill-registry 163
-
world-operator
Provides comprehensive context about the Codako game engine's world operator, actor/character/rule types, stage helpers, and simulation logic. Use when modifying world-operator.ts, stage-helpers.ts, types.ts, or any game simulation, rule evaluation, or world state management code.
majiayu000/claude-skill-registry 163
-
code-quality
コードレビュー、コミットメッセージ生成、リファクタリング提案、テスト作成支援。静的解析、コーディング規約チェック、セキュリティスキャン。「レビュー」「コミット」「リファクタリング」「テスト」「コード品質」に関する質問で使用。
majiayu000/claude-skill-registry 163
-
dockerignore-generator
Generate .dockerignore files to exclude unnecessary files from Docker builds. Triggers on "create dockerignore", "generate docker ignore", "dockerignore for", "docker exclude files".
majiayu000/claude-skill-registry 163
-
create-feature-pr
Create a new feature branch, implement feature work, commit with semantic-commit, and open a PR with gh using standardized templates. Use when the user asks to develop a new feature, start a feature branch, or open a feature PR; also when asked to draft a feature PR based on the latest commit message.
majiayu000/claude-skill-registry 163
-
symbolication-setup
Configure crash symbolication for readable stack traces. Use when setting up dSYMs (iOS), ProGuard/R8 mappings (Android), or source maps (React Native).
majiayu000/claude-skill-registry 163
-
eld-model-law-discovery
コードベースや要件からVocabulary（語彙）とLaw（守るべき条件）を自動発見するスキル。
名辞抽象（Term/Type）と関係抽象（Law/制約）の両方を抽出し、
/lde-term-card および /lde-law-card への入力を生成する。
使用タイミング: (1) 新規プロジェクトでVocabulary/Lawを洗い出す時、
(2) 既存コードからLaw/Termを抽出する時、(3) 「Lawを発見して」「語彙を抽出して」、
(4) LDEをレトロフィットする時、(5) Phase A-Bで初期Catalogを作る時
majiayu000/claude-skill-registry 163
-
researching-web
Web research via Perplexity AI. Use when user asks to research topics, compare technologies (X vs Y), find best practices, lookup industry standards, or get current information. Triggers on "research", "compare", "vs", "best practice", "pros and cons", "which is better".
majiayu000/claude-skill-registry 163
-
etetoolkit
Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.
majiayu000/claude-skill-registry 163
-
npm-helper
NPM and Node.js package management, project configuration, and dependency troubleshooting.
majiayu000/claude-skill-registry 163
-
mobile-testing-playwright
Mobile device testing with Playwright MCP for iOS and Android. Use when testing mobile apps, responsive layouts, touch interactions, device emulation, viewport testing, mobile browser testing, visual regression testing, or working with iPhone, iPad, Pixel, Galaxy devices. Covers test patterns, execution workflows, device configurations, and Playwright MCP tools.
majiayu000/claude-skill-registry 163
-
factory-validator
생성된 컴포넌트 검증 및 품질 보증 스킬
majiayu000/claude-skill-registry 163
-
typeorm-entity-generator
Typeorm Entity Generator - Auto-activating skill for Backend Development.
Triggers on: typeorm entity generator, typeorm entity generator
Part of the Backend Development skill category.
majiayu000/claude-skill-registry 163
-
zero-trust-architecture
Implement Zero Trust security model with identity verification, microsegmentation, least privilege access, and continuous monitoring. Use when building secure cloud-native applications.
majiayu000/claude-skill-registry 163
-
agent-evaluation
Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
majiayu000/claude-skill-registry 163