Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
majiayu000/claude-skill-registry 163
-
Pixel Art Exporter
Export sprites to PNG, GIF, or spritesheet formats with JSON metadata for game engines. Use when the user wants to "export", "save", "output", "render", "generate", "create file", mentions file formats like "PNG", "GIF", "animated GIF", "spritesheet", "sprite sheet", "texture atlas", "tile sheet", or game engine integration with "Unity", "Godot", "Phaser", "Unreal", "GameMaker". Trigger on layout terms ("horizontal", "vertical", "grid", "packed", "strip"), scaling ("2x", "4x", "upscale", "pixel-perfect"), file operations ("save as", "export to", "output to"), metadata formats ("JSON", "XML", "metadata", "atlas data"), and delivery terms ("for web", "for game", "for Twitter", "for itch.io", "optimized").
majiayu000/claude-skill-registry 163
-
budget-ui-components
Componentes de UI para orçamentos seguindo o padrão de components do Easy Budget.
majiayu000/claude-skill-registry 163
-
collect-selector
Use this skill to determine the correct data-testid selector for Playwright or end-to-end tests.
majiayu000/claude-skill-registry 163
-
community-sentiment-dashboard
Reporting template for tracking sentiment, risks, and advocacy signals across social + community channels.
majiayu000/claude-skill-registry 163
-
drawdown-guardrails-pattern
Consistent drawdown control pattern for trading systems - backtests, live trading, and training
majiayu000/claude-skill-registry 163
-
starwards-monorepo
npm workspace monorepo workflow for Starwards - build order, module dependencies, watch mode, testing across modules, and avoiding common monorepo pitfalls; core builds first always
majiayu000/claude-skill-registry 163
-
test-plan-generator
Generate intelligent, non-redundant test plans based on implementation changes. This skill should be used after implementing features to create comprehensive yet efficient test plans with proper coverage across unit, integration, API, and E2E tests without duplication.
majiayu000/claude-skill-registry 163
-
test-permission
Remote App 권한 요청 UI 테스트용 스킬. Use when (1) 권한 요청 UI 테스트,
(2) Hook → Remote 연동 검증, (3) awaiting_type=permission 시뮬레이션.
majiayu000/claude-skill-registry 163
-
mcp-evaluation-skill
Comprehensive evaluation creation for MCP servers - question generation, answer verification, and XML formatting for agent usability testing
majiayu000/claude-skill-registry 163
-
dotnet-development
Comprehensive .NET development guidelines covering DDD, SOLID principles, ASP.NET Core REST APIs, and C# best practices.
Use when working with: (1) C# code files (.cs), (2) .NET project files (.csproj, .sln), (3) ASP.NET Core applications,
(4) Domain-Driven Design implementations, (5) REST API development, (6) Entity Framework Core,
(7) Unit/integration testing in .NET. Specifically triggers for: classes inheriting AggregateRoot/Entity,
services with IRepository dependencies, controllers inheriting ControllerBase, or files in Domain/Application/Infrastructure folders.
majiayu000/claude-skill-registry 163
-
ios-app-tester
Test iOS apps using AXe CLI for accessibility auditing, UI automation, and simulator control. Use when testing iOS Simulator apps, automating UI interactions, recording test videos, or auditing accessibility labels and VoiceOver support.
majiayu000/claude-skill-registry 163
-
startup-idea-validation
Systematic 9-dimension validation machine for testing ideas before building. Covers problem severity, market sizing, timing, competitive moats, unit economics, founder-market fit, technical feasibility, GTM clarity, and risk profile. Makes GO/NO-GO decisions based on evidence, not assumptions.
majiayu000/claude-skill-registry 163
-
mobile-app-testing
Comprehensive mobile app testing strategies for iOS and Android. Covers unit tests, UI tests, integration tests, performance testing, and test automation with Detox, Appium, and XCTest.
majiayu000/claude-skill-registry 163
-
svelte-components
Svelte component patterns. Use for web components, component libraries (Bits UI, Ark UI, Melt UI), form patterns, or third-party integration.
majiayu000/claude-skill-registry 163
-
browser-use
Web scraping, screenshots, form filling, file downloads/uploads, Google/DuckDuckGo image search, YouTube video downloading, and TikTok video downloading.
majiayu000/claude-skill-registry 163
-
flutter-tester
A comprehensive Flutter testing skill for creating, writing, and analyzing tests in any Flutter project. Provides guidance on test structure, mocking patterns, Riverpod testing, widget testing, and industry best practices for reliable, maintainable tests.
majiayu000/claude-skill-registry 163
-
websearch-deep
ChatGPT-style deep research strategy with problem decomposition, multi-query generation (3-5 variations per sub-question), evidence synthesis with source ranking, numbered citations, and iterative refinement. Use for complex architecture decisions, multi-domain synthesis, strategic comparisons, technology selection. Keywords: architecture, integration, best practices, strategy, recommendations, comparison.
majiayu000/claude-skill-registry 163
-
Bun Test Coverage
Use for test coverage with Bun, --coverage flag, lcov reports, thresholds, and CI integration.
majiayu000/claude-skill-registry 163
-
integration-patterns-skill
Shared patterns for Nango actions and syncs - working directory verification, inline schemas, parameter naming, type safety, and registration requirements. Private dependency skill.
majiayu000/claude-skill-registry 163
-
test-runner
Run tests with Jest, Vitest, or Playwright, fix failing tests, and generate missing test coverage. Use when user says "run tests", "test this", "fix failing tests", "write tests", or when tests need to be executed or created.
majiayu000/claude-skill-registry 163
-
orchestrate-spec
Auto-detects next pending Smart Orchestrator component, spawns 2-3 research agents, generates evidence-backed specs, validates, and offers optional implementation with automatic progress tracking.
majiayu000/claude-skill-registry 163
-
edge-cases
Analyze checkpoint tests and suggest missing edge cases. Use after writing tests or when reviewing test coverage. Invoke with /edge-cases <problem> <checkpoint>.
majiayu000/claude-skill-registry 163
-
experimental-research-metacognition
Do experiment-driven research (hypotheses → minimal repros → evidence) and continuously improve research skills + tooling. Use when behavior is uncertain, contested, or performance-sensitive.
majiayu000/claude-skill-registry 163