Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
testing-procedures
Testing procedures for Kalahari project. Use for running tests and analyzing results.
majiayu000/claude-skill-registry 163
-
react-project-scaffolder
Use PROACTIVELY when creating new React projects requiring modern tooling and best practices. Provides three modes - sandbox (Vite + React for quick experiments), enterprise (Next.js with testing and CI/CD), and mobile (Expo + React Native). Enforces TypeScript strict mode, Testing Trophy approach, and 80% coverage. Not for non-React projects or modifying existing applications.
majiayu000/claude-skill-registry 163
-
moai-docs-unified
Enhanced docs unified with AI-powered features. Enhanced with Context7 MCP for up-to-date documentation.
majiayu000/claude-skill-registry 163
-
sp-test-skill
Test skills with subagents before deployment to resist rationalization
majiayu000/claude-skill-registry 163
-
cookie-scanner
Analyze website cookie consent compliance by testing consent banner behavior.
Use when asked to audit cookies, check GDPR/CCPA compliance, analyze tracking,
or assess consent mechanisms on websites.
majiayu000/claude-skill-registry 163
-
library-detection
Detect project stack from package manifests (package.json, pyproject.toml, go.mod, Cargo.toml, pubspec.yaml, CMakeLists.txt). Auto-identify frameworks, test tools, and build systems for onboarding.
majiayu000/claude-skill-registry 163
-
react-native-navigation
Master React Navigation - stacks, tabs, drawers, deep linking, and TypeScript integration
majiayu000/claude-skill-registry 163
-
qa-test-management
Automatic QA test lifecycle management, naming conventions, and directory structure. Use when creating, organizing, or tracking QA tests to ensure proper naming, directory structure, and status transitions.
majiayu000/claude-skill-registry 163
-
testing-quality
Coordinate research-focused testing and quality validation with clear constraints, gates, and confidence ceilings.
majiayu000/claude-skill-registry 163
-
issue-resolution
Systematically diagnose and fix bugs through triage, reproduction, root cause analysis, and verified fixes. Use when resolving bugs, errors, failing tests, or investigating unexpected behavior.
majiayu000/claude-skill-registry 163
-
search-provider-selection
Expert knowledge on choosing the right search provider (Serper vs Apify vs ScapeCreators) for Instagram/TikTok/YouTube, cost-benefit analysis, quality vs speed tradeoffs, rate limits, and provider testing scripts. Use this skill when user asks about "which provider", "search provider", "compare providers", "cost optimization", "serper vs apify", or "provider selection".
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
-
test-skill
answers with the secret
majiayu000/claude-skill-registry 163
-
plugin-testing
Validates audio plugins through automated tests, pluginval, or manual DAW testing. Use for MANUAL testing via /test command. Note - Automatic validation now built into workflow (validation-agent runs after each stage). This skill is for manual testing only, after bug fixes, or when user mentions test, validate, validation, pluginval, stability, automated tests, run tests, check plugin, or quality assurance.
majiayu000/claude-skill-registry 163
-
config-tuning
Use when you notice a pattern that should be in the config. Analyzes current setup, researches best practices, and proposes specific config changes. Also use when asked to improve agent behavior or workflows.
majiayu000/claude-skill-registry 163
-
go-testing-helpers
Test helper patterns with t.Helper()
majiayu000/claude-skill-registry 163
-
ai-phill
Strategic advisor for founders. Facilitates deep thinking through Socratic dialogue, identifies blind spots, assesses risks and opportunities, and provides guidance on strategic decisions using Extended Thinking for complex analysis.
majiayu000/claude-skill-registry 163
-
add-backend-testing
Add backend integration testing with Vitest to an existing app. Sets up isolated test database schema and writes tests for tRPC routers.
majiayu000/claude-skill-registry 163
-
mxql
Complete MXQL (Metrics Query Language) toolkit for generating, analyzing, validating, and testing queries. Supports conversational query generation, automated validation, comprehensive analysis with optimization suggestions, and test query generation with sample data. Use this for all MXQL-related tasks including creating queries, debugging, optimization, and testing.
majiayu000/claude-skill-registry 163
-
supabase-migration-deep-dive
Execute Supabase major re-architecture and migration strategies with strangler fig pattern.
Use when migrating to or from Supabase, performing major version upgrades,
or re-platforming existing integrations to Supabase.
Trigger with phrases like "migrate supabase", "supabase migration",
"switch to supabase", "supabase replatform", "supabase upgrade major".
majiayu000/claude-skill-registry 163
-
playwright-best-practices
Provides Playwright test patterns for resilient locators, Page Object Models, fixtures, web-first assertions, and network mocking. Must use when writing or modifying Playwright tests (.spec.ts, .test.ts files with @playwright/test imports).
majiayu000/claude-skill-registry 163
-
cui-java-unit-testing
CUI Java unit testing standards and patterns with JUnit 5, generators, and value object testing
majiayu000/claude-skill-registry 163
-
skill-integration
Standardized patterns for how agents discover, reference, and compose skills using progressive disclosure architecture
majiayu000/claude-skill-registry 163
-
artificial-analysis-compare
Compare LLM models using the Artificial Analysis API. This skill should be used when the user asks to compare AI models, benchmark LLMs, evaluate model performance, compare pricing between models, or find the best model for a specific use case (coding, math, speed, cost). Triggers on requests like "compare GPT-5 and Claude", "which model is fastest", "cheapest model for coding", "benchmark comparison", "model performance analysis", or "artificial analysis". (user)
majiayu000/claude-skill-registry 163