Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
hitchhikers-guide
majiayu000/claude-skill-registry 163
-
synthetic-monitoring
Implement synthetic monitoring and automated testing to simulate user behavior and detect issues before users. Use when creating end-to-end test scenarios, monitoring API flows, or validating user workflows.
majiayu000/claude-skill-registry 163
-
uloop-focus-window-hatayama-uloopmcp
majiayu000/claude-skill-registry 163
-
thinking-framework
Use this when complex problem-solving, root cause analysis, strategic decision-making, or systematic thinking is needed. Applies Divide & Conquer with 15 thinking methods (5 Why, SWOT, First Principles, etc.) with optional Sequential MCP integration.
majiayu000/claude-skill-registry 163
-
plan-validate-execute-template-djankies-claude-configs-08eb35e4
majiayu000/claude-skill-registry 163
-
web-testing-automation
Comprehensive web application testing automation using Playwright, including MCP integration, browser automation, E2E testing, visual regression testing, API testing, and CI/CD integration. Use when creating automated tests, setting up test frameworks, debugging test failures, implementing Page Object Model, or integrating testing into deployment pipelines.
majiayu000/claude-skill-registry 163
-
parallel-orchestration
This skill should be used when the user asks to "run multiple agents", "parallel review", "comprehensive analysis", "full review", "multi-agent workflow", or needs to coordinate multiple specialized agents working simultaneously. Provides patterns for launching agents in parallel and synthesizing results.
majiayu000/claude-skill-registry 163
-
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
majiayu000/claude-skill-registry 163
-
unit-tests
Write pytest tests using Test-Driven Development (TDD). Use when implementing features, fixing bugs, or when the user mentions testing, TDD, or pytest. Tests should be written BEFORE implementation code.
majiayu000/claude-skill-registry 163
-
sf-ai-agentforce-testing
Comprehensive Agentforce testing skill with test execution, coverage analysis, and agentic fix loops. Run agent tests via sf CLI, analyze topic/action coverage, generate test specs, and automatically fix failing agents with 100-point scoring.
majiayu000/claude-skill-registry 163
-
new-api-route
Create new ORPC API routes with contracts, routers, and client integration.
创建新的 ORPC API 路由，包含合约、路由器和客户端集成。
Use when:
- Adding new API endpoints
- Creating CRUD operations for a new entity
- User mentions "new API", "add endpoint", "create route", "新增接口", "添加 API"
majiayu000/claude-skill-registry 163
-
prepare-changelog
Guidelines for preparing changelog entries for nextest releases following Keep a Changelog format
majiayu000/claude-skill-registry 163
-
Network 101
This skill should be used when the user asks to "set up a web server", "configure HTTP or HTTPS", "perform SNMP enumeration", "configure SMB shares", "test network services", or needs guidance on configuring and testing network services for penetration testing labs.
majiayu000/claude-skill-registry 163
-
cross-model-handoff-testing
Test cross-model context handoff integrity.
majiayu000/claude-skill-registry 163
-
java-testing-advanced
Advanced testing - Testcontainers, contract testing, mutation testing, property-based
majiayu000/claude-skill-registry 163
-
openapi-toolkit-anthropic-dart
majiayu000/claude-skill-registry 163
-
api-integration-architect
Expert in API integration with React Query, SWR, RTK Query, REST/GraphQL clients, WebSocket real-time, optimistic updates, caching strategies, and error handling
majiayu000/claude-skill-registry 163
-
parallel-orchestration
This skill should be used when the user asks to "run multiple agents", "parallel review", "comprehensive analysis", "full review", "multi-agent workflow", or needs to coordinate multiple specialized agents working simultaneously. Provides patterns for launching agents in parallel and synthesizing results.
majiayu000/claude-skill-registry 163
-
monitoring-expert-jeffallan-claude-skills
majiayu000/claude-skill-registry 163
-
bugs-fundamentals
Foundational knowledge for writing BUGS/JAGS models including precision parameterization, declarative syntax, distributions, and R integration. Use when creating or reviewing BUGS/JAGS models.
majiayu000/claude-skill-registry 163
-
ai-agent-skills-raia-ai-raia-v2-docs-raia-ai-raia-v2-docs
majiayu000/claude-skill-registry 163
-
harness-runner
Run WaveCap-SDR test harness with automated parameter sweeps and validation. Use when regression testing, validating audio quality across configurations, testing SDR hardware, or benchmarking demodulation performance.
majiayu000/claude-skill-registry 163
-
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
majiayu000/claude-skill-registry 163
-
project-architecture-patterns
Architecture patterns for rRNA-Phylo project including FastAPI backend design, service organization, async task processing with Celery, Pydantic schemas, testing with pytest, Biopython integration, and API design conventions. Covers project structure, dependency injection, error handling, and configuration management.
majiayu000/claude-skill-registry 163