Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 404 files from 1 741 authors, of which 61 763 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Add a new tool to the backend OpenAI function calling system. Use when user mentions "new tool", "add tool", "backend function", "agent capability", or wants to extend what the AI agent can do.
Add a new event type to the frontend feed system with corresponding React component. Use when user mentions "new event", "add event type", "event block", "new block type", or wants to display new agent output types.
Start the backend (FastAPI/uvicorn) and frontend (Vite) development servers. Use when user mentions "start dev", "run servers", "launch app", "start the app", or needs to run the application locally.
Run ESLint and TypeScript type checking on the frontend codebase. Use when user mentions "lint", "type check", "check code", "eslint", "tsc", or before committing changes.
Review security of command execution, tool permissions, and API key handling. Use when user mentions "security review", "audit", "check security", "vulnerabilities", or before deploying to production.
Comprehensive Bitbucket pipeline automation using direct Node.js API calls. Monitor pipeline status, analyze failures, download logs, and trigger builds. Use this skill when the user asks to check pipeline status, find failing pipelines, download logs, trigger builds, or debug pipeline failures. No MCP approval prompts required - uses Bash tool with node commands.
> Guide and run a SharePoint audit locally. Collect inputs, confirm PowerShell 7.4+ and Python 3.10+ are available, call PowerShell with certificate auth via wrapper, parse audit.json, and render Markdown/HTML. Use only local shell commands.
Four-phase debugging framework that ensures root cause identification before fixes. Use when encountering bugs, test failures, unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline ('debug this', 'fix this error', 'test is failing', 'not working').
Deep code review with web research to verify against latest ecosystem. Use when user says 'double check against latest', 'verify versions', 'check security', 'review against docs', or needs deep analysis beyond automatic quality hook.
Systematic refactoring with small-step discipline. Use when user says 'refactor', 'clean up', 'restructure', 'extract', 'rename', 'simplify', or mentions code smells. Enforces one change → test → commit cycle. For structural improvements, NOT style/formatting (use /lint). NOT for adding features or fixing bugs.
Converts static web or Next.js projects into ArcBlock blocklets using provided DID. Analyzes project structure, generates configuration files, and validates setup. Requires blocklet DID as parameter.
Creates a new release for a blocklet project by bumping version, building, and bundling. Use when asked to "create a new release", "bump and bundle", or "update blocklet version".
Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for 2025+ AI development.
Use this skill when designing REST, GraphQL, or gRPC APIs. Provides comprehensive API design patterns, versioning strategies, error handling conventions, authentication approaches, and OpenAPI/AsyncAPI templates. Ensures consistent, well-documented, and developer-friendly APIs across all backend services.
Use this skill when documenting significant architectural decisions. Provides ADR templates following the Nygard format with sections for context, decision, consequences, and alternatives. Helps teams maintain architectural memory and rationale for backend systems, API designs, database choices, and infrastructure decisions.
Understand and navigate the DevPrep AI 7-folder architecture. Use this skill when asked about code organization, where to place new features, what modules exist, or when starting development tasks that need architecture context. Auto-triggers on keywords like "where should", "add module", "architecture", "structure", "organize", "place code", "what modules".
Creates beautiful ASCII art visualizations for plans, architectures, workflows, and data. This skill should be used when explaining system architecture, creating implementation plans, showing workflows, visualizing comparisons, or documenting file structures. NOT for code syntax highlighting or markdown tables. User explicitly loves ASCII art - use liberally for visual communication.
Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation
Use this skill when conducting or improving code reviews. Provides structured review processes, conventional comments patterns, language-specific checklists, and feedback templates. Ensures consistent, constructive, and thorough code reviews across teams.
Use this skill when designing database schemas for relational (SQL) or document (NoSQL) databases. Provides normalization guidelines, indexing strategies, migration patterns, and performance optimization techniques. Ensures scalable, maintainable, and performant data models.
Guided workflow for implementing HTML design prototypes as production React components with glassmorphism styling and quality standards enforcement. Use when converting design prototypes to production code.
CI/CD pipelines, containerization, Kubernetes, and infrastructure as code patterns
Deploy to edge runtimes (Cloudflare Workers, Vercel Edge, Deno Deploy) for globally distributed, low-latency applications. Master edge middleware, streaming, and runtime constraints for 2025+ edge computing.
This skill teaches agents how to collect and verify evidence before marking tasks complete. Inspired by production-grade development practices, it ensures all claims are backed by executable proof:...
Scaffolds new feature modules in DevPrep AI following the 6-folder architecture with proper TypeScript interfaces, path aliases, and quality standards. Use when creating new domains like 'analytics', 'notifications', or any new feature module.
Structured logging, metrics, distributed tracing, and alerting strategies
Full-stack performance analysis, optimization patterns, and monitoring strategies
Convert design prototypes (HTML, CSS, Figma exports) into production-ready components. Analyzes prototype structure, extracts design tokens, identifies reusable patterns, and generates typed React components. Adapts to existing project tech stack with React + TypeScript as default.
This skill teaches agents how to assess task complexity, enforce quality gates, and prevent wasted work on incomplete or poorly-defined tasks. Inspired by production-grade development practices, qu...
Automatically reviews DevPrep AI code for quality standards including ESLint compliance, TypeScript strict mode, 180-line file limits, complexity under 15, proper naming conventions, import patterns, and architectural compliance with the 6-folder structure
Design and implement React Server Components with Next.js 15 App Router. Master server-first architecture, streaming SSR, Server Actions, and modern data fetching patterns for 2025+ frontend development.
Use this skill when implementing security measures or conducting security audits. Provides OWASP Top 10 mitigations, authentication patterns, input validation strategies, and compliance guidelines. Ensures applications are secure against common vulnerabilities.
Implement real-time data streaming with Server-Sent Events (SSE), WebSockets, and ReadableStream APIs. Master backpressure handling, reconnection strategies, and LLM streaming for 2025+ real-time applications.
Use this skill when creating comprehensive testing strategies for applications. Provides test planning templates, coverage targets, test case structures, and guidance for unit, integration, E2E, and performance testing. Ensures robust quality assurance across the development lifecycle.
Scaffolds tRPC routers, procedures, and Zod schemas with full type safety following DevPrep AI patterns
Achieve end-to-end type safety with Zod runtime validation, tRPC type-safe APIs, Prisma ORM, and TypeScript 5.7+ features. Build fully type-safe applications from database to UI for 2025+ development.
生成面向敏捷开发团队的精炼设计文档。MVP导向，避免过度设计。使用场景：(1) 需要为新功能或系统模块生成设计文档 (2) 需要明确功能边界和交互流程 (3) 需要提供实现思路和关键方法 (4) 需要阐述技术难点和解决方案。该skill会先分析项目技术栈和现有组件，然后生成精炼、重点突出的设计文档。
Process and transform arrays of data with common operations like filtering, mapping, and aggregation
Query Obsidian Bases via the Bases Query plugin (RPC). Use when you need to read structured data from Obsidian bases.
Manage tasks in Obsidian via TaskNotes plugin API. Use when user wants to create tasks, list tasks, query by status or project, update task status, delete tasks, or check what they need to do.
Add new core business logic functions to Catalyst-Relay. Use when creating pure functions, ADT operations, or library-consumable code.
Add new HTTP endpoints to Catalyst-Relay server. Use when creating routes, API endpoints, or HTTP handlers.
Run unit and integration tests for Catalyst-Relay. Use when asked to test, run tests, verify changes, or check if code works.
| Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction. NOT when only fetching static content (use curl/wget instead).
| Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.
| Build interactive AI chat widgets with buttons, forms, and bidirectional actions. Use when creating agentic UIs with clickable widgets, entity tagging (@mentions), composer tools, or server-handled widget actions. Covers full widget lifecycle. NOT when building simple text-only chat without interactive elements.
| Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).
| Guides creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). Covers tool design, authentication, Docker deployment, and evaluation creation. NOT when consuming existing MCP servers (use the server directly).
| Build Next.js 16 applications with correct patterns and distinctive design. Use when creating pages, layouts, dynamic routes, upgrading from Next.js 15, or implementing proxy.ts. Covers breaking changes (async params/searchParams, Turbopack, cacheComponents) and frontend aesthetics. NOT when building non-React or backend-only applications.
| Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document ingestion pipelines, vector search with Qdrant, or context-aware retrieval. Covers chunking strategies, change detection, payload indexing, and context expansion. NOT when doing simple similarity search without production requirements.
| Implement OAuth 2.1 / OIDC authentication using Better Auth with MCP assistance. Use when setting up a centralized auth server (SSO provider), implementing SSO clients in Next.js apps, configuring PKCE flows, or managing tokens with JWKS verification. Uses Better Auth MCP for guided setup. NOT when using simple session-only auth without OAuth/OIDC requirements.
| Configures Dapr pub/sub components for event-driven microservices with Kafka or Redis. Use when wiring agent-to-agent communication, setting up event subscriptions, or integrating Dapr sidecars. Covers component configuration, subscription patterns, publishing events, and Kubernetes deployment. NOT when using direct Kafka clients or non-Dapr messaging patterns.
| Containerizes applications with Docker, docker-compose, and Helm charts. Use when creating Dockerfiles, docker-compose configurations, or Helm charts for Kubernetes. Includes Docker Hardened Images (95% fewer CVEs), multi-stage builds, and 15+ battle-tested gotchas.
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
Understand the components, mechanics, and constraints of context in agent systems. Use when designing agent architectures, debugging context-related failures, or optimizing context usage.
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
| Guides creation of effective Agent Skills with proper structure and validation. Use when users want to create a new skill, update an existing skill, or need guidance on skill design patterns, SKILL.md format, or verify.py implementation. NOT when just using existing skills (use those skills directly).
| Deploys applications to cloud Kubernetes (AKS/GKE/DOKS) with CI/CD pipelines. Use when deploying to production, setting up GitHub Actions, troubleshooting deployments. Covers build-time vs runtime vars, architecture matching, and battle-tested debugging.
| Deploys Apache Kafka on Kubernetes using the Strimzi operator with KRaft mode. Use when setting up Kafka for event-driven microservices, message queuing, or pub/sub patterns. Covers operator installation, cluster creation, topic management, and producer/consumer testing. NOT when using managed Kafka (Confluent Cloud, MSK) or local development without K8s.
| Deploys PostgreSQL on Kubernetes using the CloudNativePG operator with automated failover. Use when setting up PostgreSQL for production workloads, high availability, or local K8s development. Covers operator installation, cluster creation, connection secrets, and backup configuration. NOT when using managed Postgres (Neon, RDS, Cloud SQL) or simple Docker containers.
Claude Skills — questions
Answers built from the skills we actually parsed.