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.
TanStack Query v5 patterns and common pitfalls. Use when implementing data fetching, cache invalidation, or debugging stale data issues. Triggers on: useQuery, useMutation, queryKey, invalidate, TanStack, React Query.
WebSocket server and client patterns with heartbeat and reconnection. Use when implementing real-time features, debugging connection issues, or reviewing WebSocket code. Triggers on: WebSocket, wss, heartbeat, reconnect, real-time.
Audits and validates skill definitions for quality, completeness, and best practices. Use when reviewing existing skills for proper formatting, evaluating if skills should be split into sub-skills, or ensuring skills follow established conventions.
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.
Validates system integration before deployment. Use when checking ports, database connections, frontend-backend APIs, or debugging blocked/stuck workflows. Detects dead ends, bottlenecks, circular dependencies.
Organizational coding standards and architectural patterns. References comprehensive skills for detailed patterns. Use when making architecture decisions or implementing features.
Save current progress to memory-keeper to prevent work loss.
Code review framework and criteria. References security-sentinel for security checks. Use when performing code reviews or defining review standards.
This skill provides comprehensive Drizzle ORM patterns for PostgreSQL with Vercel Edge Runtime support. Drizzle is Quetrex's chosen ORM because it's edge-first, type-safe, and supports all deployme...
Drizzle ORM patterns for PostgreSQL.
Use when creating UI designs to avoid generic "AI slop" aesthetics. Enforces distinctive typography, cohesive color systems, purposeful motion, and atmospheric backgrounds. Critical for landing pages, dashboards, and branded interfaces.
Git workflow with worktrees and conventional commits.
Next.js 15 App Router patterns and best practices.
Use when working with Next.js 15 features, App Router, Server Components, Server Actions, or data fetching patterns. Ensures correct usage of Server vs Client Components and modern Next.js patterns.
Checkpoint framework and validation rules for all agents. Ensures quality gates are passed at every stage of development.
Use when implementing new features in Quetrex. Ensures TDD, TypeScript strict mode, Next.js App Router patterns, ShadCN UI components, and security best practices are followed. Updated for November 2025 standards.
Each project card should show the current month's API costs with a small trend indicator (up/down arrow).
Comprehensive React 19 patterns including all hooks, Server/Client Components, Suspense, streaming, and transitions. Ensures correct React 19 usage with TypeScript.
Recover session state from memory-keeper after context loss.
Upstash Redis patterns for caching and rate limiting.
Use when working with authentication, API routes, user input, or sensitive data. Audits code for security vulnerabilities based on OWASP Top 10. Critical for payment processing, auth systems, and data handling.
Use when you need to find code by concept (not just text). Uses Serena MCP for semantic code search across the codebase with minimal token usage. Ideal for understanding architecture, finding authentication flows, or multi-file refactoring.
ShadCN UI + Framer Motion patterns.
Use when building UI components. Enforces ShadCN UI patterns, accessibility standards (Radix UI), and TailwindCSS best practices for November 2025.
TanStack Query + Zustand patterns.
Use when implementing new features. Enforces TDD workflow - write tests FIRST, then implementation. Ensures AAA pattern, proper coverage, and quality test design.
> Use when writing or reviewing TypeScript code. Enforces strict mode standards, explicit typing, and best practices. Prevents 'any' types, @ts-ignore comments, and non-null assertions. This is a COMPREHENSIVE skill - consult the detailed guides before writing any TypeScript code.
Strict TypeScript rules. Use when writing ANY TypeScript.
Use when working with Quetrex's voice interface, OpenAI Realtime API, WebRTC, or echo cancellation. Knows Quetrex's specific voice architecture decisions and patterns. CRITICAL - prevents breaking working voice system.
This skill provides comprehensive patterns for using Zod validation library in TypeScript applications. It ensures input validation is done correctly, securely, and consistently across the codebase.
Creates bauplan data pipeline projects with SQL and Python models. Use when starting a new pipeline, defining DAG transformations, writing models, or setting up bauplan project structure from scratch.
Ingest data from S3 into bauplan using the Write-Audit-Publish pattern for safe data loading. Use when loading new data from S3, performing safe data ingestion, or when the user mentions WAP, data ingestion, importing parquet/csv/jsonl files, or needs to safely load data with quality checks.
Executive coaching skill that helps you plan your 2026 using research-backed process goals. Guides you through discovery questions, creates outcome goals, converts them to daily behaviors, and sets up accountability systems. Use when you want to plan your year, set goals, or need a coach to help you stay focused.
| (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 "ChatGPT integration", "MCP server for ChatGPT", "submit to ChatGPT"
Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something for future sessions.
Audit UX waiting states for web applications with long-running operations (30+ seconds). Use when asked to evaluate, audit, or analyze a product's loading states, wait times, progress indicators, or user experience during slow operations. Requires browser automation (Chrome MCP tools). Generates comprehensive reports with screenshots, checklist evaluation, and prioritized recommendations.
Use when the user needs to choose, prioritize, or make a go/no-go decision among options.
Use when the user asks to describe, summarize, analyze, compare, explain, or report on something (text, data, events, systems) without asking for recommendations or next steps.
Use when the user asks why something happened, what’s wrong, root cause analysis, debugging, or incident explanation.
Market analysis and competitive intelligence for startups. Use when analyzing market opportunities, sizing TAM, profiling segments, or mapping competition.
Problem validation and solution design. Use when discovering customer problems, generating solution hypotheses, or defining MVP scope.
Transform objectives into structured goals with plans. Use when user declares intent ("I want to...", "Goal is to...", "Achieve X by Y"). Decomposes into subgoals, milestones, success criteria.
Track goal progress, derive state from execution, identify gaps, trigger actions. Use for goal status checks, progress reviews, and operational goal management.
Use when the user asks for a roadmap, timeline, phased plan, or execution sequence.
Use when the user asks for recommendations, next steps, best approaches, or “what should I do” guidance to achieve a goal or fix a problem.
Generate and evaluate explanatory hypotheses from incomplete observations. Use when diagnosing anomalies, explaining unexpected outcomes, or inferring causes from effects. Produces ranked hypotheses with evidence and confidence scores.
Transfer knowledge from source domains to novel target situations through structural mapping. Use when facing new markets, products, or situations where past experience provides relevant patterns. Produces adapted solutions with explicit mappings and context adjustments.
Execute evidence-based decision-making through 6-stage causal flow. Use for known processes, operational execution, and decisions with clear cause-effect chains.
Evaluate alternative scenarios by simulating interventions on past decisions or hypothetical futures. Use when assessing decisions in hindsight, planning scenarios, or comparing paths not taken. Produces comparative analysis with probability-weighted outcomes.
Synthesize competing positions through structured thesis-antithesis-synthesis process. Use when stakeholders disagree, trade-offs exist, or multiple valid perspectives need integration. Produces integrated positions with acknowledged trade-offs.
Extract patterns and generalizations from multiple observations. Use when detecting recurring themes, building predictive rules, or identifying systemic behaviors from accumulated data. Produces validated patterns with confidence bounds and exception handling.
太初有道，道生代码。从零搭建 React19+TailwindV4+Vite 前端、FastAPI Python 后端、Go Gin 后端、Taro 4.x 小程序。用户说"新建项目"、"初始化"、"从零开始"、"搭建项目"、"创建项目"、"生成落地页"、"生成官网"、"生成 Landing Page"、"动画提升"、"动效升级"、"新建小程序"、"创建小程序"、"Taro 项目"时触发。
Diagnose and fix FastAPI hangs caused by blocking ThreadPoolExecutor shutdown in the news stream route; includes py-spy capture and non-blocking executor pattern.
Plan lifecycle management for Codex plans stored in $CODEX_HOME/plans (default ~/.codex/plans). Use when a user asks to create, find, read, update, delete, or manage plan documents for implementation work or overview/reference documentation.
Optimize the research agent for rate limit handling, API call efficiency, web search integration fixes, and improved streaming UX with granular progress updates and source attribution.
Project-specific UI refactor workflow for the Scoop news platform in /home/bender/classwork/Thesis. Use when updating Scoop frontend layouts, globe UX, research workspace, and brand docs while preserving all features and enforcing a no-emoji policy across UI, logs, and docs.
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 Codex's capabilities with specialized knowledge, workflows, or tool integrations.
Add comprehensive debugging and observability tooling for backend storage layers (PostgreSQL, ChromaDB) and startup metrics. Includes storage drift detection, raw data inspection endpoints, and a Next.js admin dashboard.
Add Agentation visual feedback toolbar to a Next.js project
REST API design best practices for consistent, intuitive APIs
Claude Skills — questions
Answers built from the skills we actually parsed.