Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
guided-investigation
Systematic process for investigating open-ended questions - decompose vague questions into specific sub-questions, map to data, investigate incrementally, synthesize findings
majiayu000/claude-skill-registry 163
-
fastmcp-integration
Examples and patterns for integrating FastMCP Cloud servers with Claude Agent SDK using HTTP transport
majiayu000/claude-skill-registry 163
-
chatgpt-app-builder
Build ChatGPT Apps using the Apps SDK and MCP. Use when users want to:
(1) Evaluate if their product should become a ChatGPT App
(2) Design and implement MCP servers with widgets
(3) Test apps locally and in ChatGPT
(4) Prepare for App Store submission
Triggers: "ChatGPT app", "Apps SDK", "build for ChatGPT",
"ChatGPT integration", "MCP server for ChatGPT", "submit to ChatGPT"
majiayu000/claude-skill-registry 163
-
test-pattern-analysis
Analyze existing tests to identify patterns, fixtures, and conventions before writing new tests
majiayu000/claude-skill-registry 163
-
feature-flags
Feature flag patterns for controlled rollouts, A/B testing, and kill switches. Use when implementing feature toggles, gradual rollouts, canary releases, percentage-based features, user targeting, or emergency kill switches.
majiayu000/claude-skill-registry 163
-
pytest-recording
Work with pytest-recording (VCR.py) for recording and replaying HTTP interactions in tests. Use when writing VCR tests, managing cassettes, configuring VCR options, filtering sensitive data, or debugging recorded HTTP responses.
majiayu000/claude-skill-registry 163
-
pytest
Advanced Python unit testing framework for customer support tech enablement, covering FastAPI, SQLAlchemy, PostgreSQL, async operations, mocking, fixtures, parametrization, coverage, and comprehensive testing strategies for backend support systems
majiayu000/claude-skill-registry 163
-
screenshot-eval
Evaluate browser screenshots and page state for errors. Use when verifying features work correctly, detecting error conditions, or validating UI state during browser testing.
majiayu000/claude-skill-registry 163
-
Effect Regex
Expert regex pattern generation, optimization, testing, and explanation using deterministic AST-based construction. Use when user needs to create, test, optimize, or understand regex patterns, parse CLI commands, validate inputs, or build complex text matching patterns.
majiayu000/claude-skill-registry 163
-
go-code-review
Auto-review Go code for 100+ common mistakes when analyzing .go files, discussing Go patterns, or reviewing PRs with Go code. Checks error handling, concurrency, interfaces, performance, testing, and stdlib usage.
majiayu000/claude-skill-registry 163
-
escape-room-balance-engineer
Balance escape room difficulty, timing, and hint systems to achieve 60-70% completion rate. Designs progressive difficulty curves, three-tier hint systems, stuck-point analysis, and playtest metrics. Use when balancing game difficulty, designing hint systems, analyzing playtest data, or optimizing escape room completion rates.
majiayu000/claude-skill-registry 163
-
project-testing-consiliency-treesitter-chunker-e9eee92d
majiayu000/claude-skill-registry 163
-
laravel-validation
Form request validation and comprehensive validation testing. Use when working with validation rules, form requests, validation testing, or when user mentions validation, form requests, validation rules, conditional validation, validation testing.
majiayu000/claude-skill-registry 163
-
moai-cc-claude-md
Authoring CLAUDE.md Project Instructions. Design project-specific AI guidance, document workflows, define architecture patterns. Use when creating CLAUDE.md files for projects, documenting team standards, or establishing AI collaboration guidelines.
majiayu000/claude-skill-registry 163
-
palantir-docs-local
Palantir 本地文档（en/latest）
majiayu000/claude-skill-registry 163
-
chrome-devtools-testing
Browser testing and debugging with Playwright. QA testing, screenshots, form interactions, console errors, network analysis, performance profiling. Batch scripting for multiple actions per turn.
majiayu000/claude-skill-registry 163
-
add-feature
majiayu000/claude-skill-registry 163
-
vitest-config
Vitest configuration template and validation logic for test configuration. Standards differ by package type - use package-type specific configs (react-app, react-library, node-library, node-service, contracts, database). Use factory pattern for React packages that need vite.config.ts merging.
majiayu000/claude-skill-registry 163
-
vercel-data-handling
Implement Vercel PII handling, data retention, and GDPR/CCPA compliance patterns.
Use when handling sensitive data, implementing data redaction, configuring retention policies,
or ensuring compliance with privacy regulations for Vercel integrations.
Trigger with phrases like "vercel data", "vercel PII",
"vercel GDPR", "vercel data retention", "vercel privacy", "vercel CCPA".
majiayu000/claude-skill-registry 163
-
test-e2e-account
Execute E2E tests for the account service with proper server setup, test execution, and cleanup. Use when user requests account E2E testing, test execution, or running Playwright tests for account features.
majiayu000/claude-skill-registry 163
-
puppeteer-efficient-ui-verification
Fast, repeatable UI verification using Puppeteer without paying browser startup per test. Use scenario suites + deterministic fixtures before jumping to full Jest E2E.
majiayu000/claude-skill-registry 163
-
python-testing
Generate pytest tests for Python modules with parametrization, shared fixtures in conftest.py, and minimal mocking. Use when creating unit tests, test suites, or improving test coverage. Follows 1-1 file correspondence and real object testing principles.
majiayu000/claude-skill-registry 163
-
shannon-execution-verifier
Comprehensive post-build verification of Shannon Framework's application outputs using three-layer
methodology: Flow Verification (execution trace analysis), Artifact Verification (physical output
inspection), and Functional Verification (runtime testing). Verifies Shannon built production-ready
applications across all domains (Frontend, Backend, Database, Mobile, DevOps). Ensures NO MOCKS
compliance, cross-platform functionality, and complete integration. Use after: Shannon builds any
application via /shannon:wave, need to verify build quality, production readiness assessment.
majiayu000/claude-skill-registry 163
-
pmc-ticket-init
Create ticket directories with 1-definition.md from PRD and planning docs. Use this skill to initialize new tickets with self-contained context, relationships, testing draft, and expectations.
majiayu000/claude-skill-registry 163