Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
cloudflare-mcp-server
Use this skill when building Model Context Protocol (MCP) servers on Cloudflare Workers. This skill should be used when deploying remote MCP servers with TypeScript, implementing OAuth authentication (GitHub, Google, Azure, etc.), using Durable Objects for stateful MCP servers, implementing WebSocket hibernation for cost optimization, or configuring dual transport methods (SSE + Streamable HTTP). The skill prevents 15+ common errors including McpAgent class export issues, OAuth redirect URI mismatches, WebSocket state loss, Durable Objects binding errors, and CORS configuration mistakes. Includes production-tested templates for basic MCP servers, OAuth proxy integration, stateful servers with Durable Objects, and complete wrangler.jsonc configurations. Covers all 4 authentication patterns: token validation, remote OAuth with DCR, OAuth proxy (workers-oauth-provider), and full OAuth provider implementation. Self-contained with Worker and Durable Objects basics. Token efficiency: ~87% savings (40k → 5k tokens). Production tested on Cloudflare's official MCP servers.
Keywords: MCP server, Model Context Protocol, cloudflare mcp, mcp workers, remote mcp server, mcp typescript, @modelcontextprotocol/sdk, mcp oauth, mcp authentication, github oauth mcp, durable objects mcp, websocket hibernation, mcp sse, streamable http, McpAgent class, mcp tools, mcp resources, mcp prompts, oauth proxy, workers-oauth-provider, mcp deployment, McpAgent export error, OAuth redirect URI, WebSocket state loss, mcp cors, mcp dcr
majiayu000/claude-skill-registry 163
-
beam-master
Shared resource library for Beam AI integration skills. DO NOT load directly - provides common references (setup, API docs, error handling, authentication) and scripts used by beam-connect and individual Beam skills.
majiayu000/claude-skill-registry 163
-
Blueprint Multi-Tenancy Integration
Integrate the Blueprint multi-tenancy pattern into new features and modules. Use this skill when adding Blueprint-aware functionality, implementing BlueprintMember access control, handling Blueprint ownership (User vs Organization), enforcing resource isolation, and integrating with BlueprintEventBus. Ensures proper multi-tenant architecture where Blueprint defines permission boundaries and all resources respect Blueprint context.
majiayu000/claude-skill-registry 163
-
rspec-service-testing
Write RSpec tests for service objects testing business logic, transaction handling, and complex workflows. Use when testing service objects, form objects, or multi-step business processes following TDD.
majiayu000/claude-skill-registry 163
-
write-unit-test
Generate behavioral unit tests from functional specifications using PreDB/PostDB pattern. Use when user provides specs with Preconditions/Workflow/Postconditions structure or asks to write tests for a specification before implementation (TDD approach).
majiayu000/claude-skill-registry 163
-
industry-research
Research a market, pinpoint an underserved customer pain, and design a venture that can capture the opportunity within 12 months. Comprehensive 10-step workflow from market mapping to 90-day action plan.
majiayu000/claude-skill-registry 163
-
worldcrafter-feature-builder
Build complete features with Server Actions, forms, Zod validation, database CRUD operations, and comprehensive tests. Use when user requests "add a feature", "build a [feature]", "create [feature] with forms", or needs end-to-end implementation with validation and testing. Scaffolds pages, actions, schemas, loading/error states, and unit/integration/E2E tests. Supports multi-step wizards, image uploads, markdown editing, custom JSON attributes, and relationship management. Do NOT use for simple static pages (use worldcrafter-route-creator), database-only changes (use worldcrafter-database-setup), testing existing code (use worldcrafter-test-generator), or auth-only additions (use worldcrafter-auth-guard).
majiayu000/claude-skill-registry 163
-
ai-engineer
LLM application and RAG system specialist. Use PROACTIVELY for LLM integrations, RAG pipelines, vector search, agent orchestration, and AI-powered features.
majiayu000/claude-skill-registry 163
-
symfony:e2e-panther-playwright
Write end-to-end tests with Symfony Panther for browser automation or Playwright for complex scenarios
majiayu000/claude-skill-registry 163
-
opportunityiq-mvp-scanner
Scans client data against revenue opportunity scenarios to identify and rank the top sales opportunities. Matches clients to scenarios like FIA replacements approaching surrender, cash drag opportunities, and concentrated portfolio positions. Calculates revenue potential and generates prioritized opportunity reports for financial advisors.
majiayu000/claude-skill-registry 163
-
skill-cli
Testing and using skill-cli for progressive disclosure across platforms (CI/CD, Cursor, Windsurf, hot-swapping)
majiayu000/claude-skill-registry 163
-
forecast-premortem
Use to stress-test predictions by assuming they failed and working backward to identify why. Invoke when confidence is high (>80% or <20%), need to identify tail risks and unknown unknowns, or want to widen overconfident intervals. Use when user mentions premortem, backcasting, what could go wrong, stress test, or black swans.
majiayu000/claude-skill-registry 163
-
claude-skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
rspec-testing
Write and update RSpec tests following BDD principles with behavior-first approach, characteristic-based context hierarchy, and happy path priority. **Activate when:** user mentions RSpec/specs/testing, works with *_spec.rb files, asks to write/add/update/fix tests, or requests test coverage. Ensures tests describe observable behavior, not implementation details.
majiayu000/claude-skill-registry 163
-
uloop-control-play-mode-hatayama-uloopmcp
majiayu000/claude-skill-registry 163
-
quality-engineering
Use when designing test strategies, implementing test automation, or optimizing performance
majiayu000/claude-skill-registry 163
-
bmad
BMad Method v6: workflow-driven agile delivery (track selection, PRD/spec, UX, architecture, epics/stories).
majiayu000/claude-skill-registry 163
-
meta-title-optimizer
Generate and optimize meta titles and descriptions for therapy pages following NextStep's formula (Service + Location | Differentiator | NextStep Therapy). Creates 5 CTR-optimized variations under 60 chars, tests against SERP simulator, scores each for click-through potential. Use when user mentions "meta title", "meta description", "optimize for CTR", "improve SERP appearance", or provides page URL for SEO optimization.
majiayu000/claude-skill-registry 163
-
resonant-probe-deployment
Deploy resonant probes to test system response patterns.
majiayu000/claude-skill-registry 163
-
interrogate-user
Interrogate the user like an intense therapy session designed to help transform a user's thought into a complete, insanely detailed specification.
majiayu000/claude-skill-registry 163
-
react-components-patterns
Comprehensive guide to React component patterns used in the Plataforma B2B de treinamento técnico corporativo educational platform. This skill covers functional components with hooks, composition patterns, state management, props flow, and error handling strategies essential for building maintainable React applications.
Learn how to create reusable, testable components following React best practices while avoiding common antipatterns like prop drilling, unnecessary class components, and improper state management. The skill emphasizes composition over inheritance, unidirectional data flow, and separation of concerns.
Real-world examples are taken directly from the project codebase, including CLearningSystem, BashLearningSystem, Breadcrumb, AreaCard, and FlashcardModal components. Each pattern is demonstrated with production code showing how architectural decisions were implemented in a 5,500+ line React application with 17 components.
Key topics include functional components (vs class components), React Hooks (useState, useEffect, custom hooks), component composition strategies, props vs Context API decision-making, controlled components for forms, error boundaries for resilience, and testing patterns with Vitest and Testing Library.
This skill is essential for understanding the system's component architecture, contributing new features, refactoring duplicated code (current 25% duplication target: <10%), and maintaining consistency across the 227-module educational platform. Includes troubleshooting guides for common React issues encountered during development.
majiayu000/claude-skill-registry 163
-
Test Quality Audit
Scan test files for anti-patterns including mesa-optimization, disabled tests, trivial assertions, and error swallowing
majiayu000/claude-skill-registry 163
-
skill-documentarian
Documentation expert for Claude Skills showcase website. Maintains skill-to-website sync, manages tag taxonomy and badges, creates blog-style artifacts, and preserves multi-skill collaborations for posterity. Activate on 'document', 'sync skills', 'create artifact', 'validate skills', 'add tags', 'tag management', 'badge', 'metadata'. NOT for code implementation (use domain skills), design creation (use web-design-expert), testing (use test-automator), or project planning (use orchestrator).
majiayu000/claude-skill-registry 163
-
yaml-master
PROACTIVE YAML INTELLIGENCE: Automatically activates when working with YAML files, configuration management,
CI/CD pipelines, Kubernetes manifests, Docker Compose, or any YAML-based workflows. Provides intelligent
validation, schema inference, linting, format conversion (JSON/TOML/XML), and structural transformations
with deep understanding of YAML specifications and common anti-patterns.
majiayu000/claude-skill-registry 163