Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
worktree-management
Use when managing git worktrees. Provides patterns for creation, cleanup, and branch naming.
majiayu000/claude-skill-registry 163
-
weaviate-connection
Connect to local Weaviate vector database and verify connection health
majiayu000/claude-skill-registry 163
-
install-tool
Use when a tool, CLI, or package is needed but not installed, or when the user asks to install/add a tool. Prefers mise for all installations.
majiayu000/claude-skill-registry 163
-
playwright-automation
Automate browser testing, web scraping, and user workflow testing with Playwright across multiple browsers. Use when writing end-to-end tests for web applications, automating repetitive browser tasks, scraping data from websites, testing across Chrome/Firefox/Safari, taking screenshots for visual regression testing, testing authentication flows, filling and submitting forms programmatically, testing responsive designs across viewports, or any browser automation requiring reliable, cross-browser testing capabilities.
majiayu000/claude-skill-registry 163
-
context-engineering
Context engineering and prompt patterns for AI agents
majiayu000/claude-skill-registry 163
-
novel-creator
Interactive novel creation workflow combining RPG-style storytelling with professional EPUB ebook production.
Use when users want to: (1) Create interactive stories/RPG games with branching choices, (2) Write full novels from story concepts,
(3) Generate novels with time-travel/fantasy/romance elements, (4) Convert markdown stories to EPUB ebooks,
(5) Create Chinese web novels with ancient poetry paired with modern lyrics, (6) Write light novels or serialized fiction.
Triggers: "write a novel", "create a story", "interactive fiction", "RPG story", "make an ebook", "穿越小说", "写小说", "创作故事", "制作电子书"
majiayu000/claude-skill-registry 163
-
performance-scaling
Cross-model performance optimization and scaling configurations for autonomous agents
majiayu000/claude-skill-registry 163
-
technical-review
Validate completed implementation against plan tasks and acceptance criteria. Use when: (1) Implementation is complete, (2) User wants validation before merging/shipping, (3) Quality gate check needed after implementation. Reviews ALL plan tasks for implementation correctness, test adequacy, and code quality. Produces structured feedback (approve, request changes, or comments) - does NOT fix code.
majiayu000/claude-skill-registry 163
-
component-quality-validator
Validates that generated skills, agents, and hooks are production-ready before use.
Scores components against quality criteria and grades them A-F.
Triggers: validate component, quality check, production ready, component validation,
skill quality, agent quality, hook quality, phase 6.5
majiayu000/claude-skill-registry 163
-
prd-v03-moat-definition
Assess competitor defensibility and define our own moat strategy during PRD v0.3 Commercial Model. Triggers on requests to analyze competitor moats, define our defensibility, assess switching costs, identify vulnerabilities, find wedge opportunities, or when user asks "what's our moat?", "how defensible are they?", "where can we compete?", "switching costs?", "defensibility", "who to target". Consumes Competitive Landscape (v0.2) CFD- entries. Outputs CFD- entries for competitor moats and BR- entries for targeting rules and our defensibility strategy.
majiayu000/claude-skill-registry 163
-
maestro-workflow
Maestro 기반 모바일 테스트 자동화 워크플로우를 시작합니다. planner -> grouper -> generator -> executor -> healer 순서로 Agent 기반 테스트를 자동 실행합니다. "/maestro-workflow", "마에스트로 워크플로우", "Maestro 테스트" 등의 명령으로 활성화됩니다.
majiayu000/claude-skill-registry 163
-
radix-ui
Builds accessible components with Radix UI primitives including dialogs, dropdowns, tooltips, and form controls. Use when building accessible interfaces, creating headless components, or implementing complex UI patterns.
majiayu000/claude-skill-registry 163
-
unit-test-writer
Generate comprehensive unit tests with proper structure, mocking, and coverage. Use for general unit testing guidance across languages.
majiayu000/claude-skill-registry 163
-
collaboration
Behavioral workflows and collaboration patterns for code review, agent coordination, and branch management. Use this skill when coordinating multi-agent work, managing code review processes, completing feature branches, or resolving productive disagreements between valid approaches.
majiayu000/claude-skill-registry 163
-
character-naming
Break LLM name defaults with external entropy. Use when character names cluster around statistical medians (Chen, Patel, Maya, Marcus), when cast has collision risks, or when fantasy cultures need phonologically consistent naming.
majiayu000/claude-skill-registry 163
-
model-usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
majiayu000/claude-skill-registry 163
-
chrome-devtools
Automate browsers with Puppeteer CLI scripts and persistent sessions. Use for screenshots, performance analysis, network monitoring, web scraping, form automation, JavaScript debugging.
majiayu000/claude-skill-registry 163
-
banner-creator
Create banners using AI image generation. Discuss format/style, generate variations, iterate with user feedback, crop to target ratio. Use when user wants to create a banner, header, hero image, or cover image.
majiayu000/claude-skill-registry 163
-
java-architect
Use when building enterprise Java applications with Spring Boot 3.x, microservices, or reactive programming. Invoke for WebFlux, JPA optimization, Spring Security, cloud-native patterns.
majiayu000/claude-skill-registry 163
-
generate-working-docs
開発作業ドキュメントを自動生成します。YYYYMMDD_要件名の形式でディレクトリを作成し、requirements.md、design.md、tasklist.md、testing.mdを生成します。「開発作業ドキュメント作成」「新規開発のドキュメント作って」「ドキュメント生成」などで呼び出されます。
majiayu000/claude-skill-registry 163
-
claude-code-hooks
Create event-driven hooks for Claude Code automation. Configure hook events in settings or frontmatter, parse stdin JSON inputs, return decision-control JSON, and implement secure hook scripts.
majiayu000/claude-skill-registry 163
-
jq
Command-line JSON processor. Extract, filter, transform JSON.
majiayu000/claude-skill-registry 163
-
planning-content-calendars
Creates strategic content schedules with themes, dates, and publishing cadence. Use when the user asks about content calendars, publishing schedules, content planning, editorial calendars, or content strategy timelines.
majiayu000/claude-skill-registry 163
-
voice-agents
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu
majiayu000/claude-skill-registry 163