# Agent skills on appsgit > Agent skills are folders with a SKILL.md file that teach AI coding agents such as Claude Code, Codex and Cursor how to do one task well. appsgit lists a curated, growing collection of 1,000 developer-focused open-source skills from skills.sh and GitHub, each with install commands, trigger phrases and live GitHub stats. Skills come from skills.sh, the GitHub topics claude-skills, agent-skills, claude-code-skills and skills, and the major awesome lists. A skill is listed only if its SKILL.md has a valid name and a description of 80+ characters, it has a license (the repository's or its own), the repository has a commit in the last six months, and the repository has 100+ stars or the skill is listed on skills.sh. This first batch is curated for developers (coding, testing, DevOps, data, security, frontend and technical docs) and capped at about 1,000 skills, at most 25 per repository; more categories are coming. ## Lists - [Trending agent skills](https://appsgit.com/skills/trending) - [Official agent skills](https://appsgit.com/skills/official) - [Coding](https://appsgit.com/skills/category/coding) (127): Agent skills for writing, reviewing, refactoring and architecting code across languages and frameworks. - [Testing & QA](https://appsgit.com/skills/category/testing-qa) (162): Agent skills for test-driven development, debugging, end-to-end testing and quality checks. - [Docs & writing](https://appsgit.com/skills/category/docs-writing) (127): Agent skills for documentation, technical writing, copy editing and document formats such as PDF, DOCX and slides. - [Data & analysis](https://appsgit.com/skills/category/data-analysis) (127): Agent skills for data analysis, spreadsheets, SQL, notebooks and visualisation. - [DevOps & cloud](https://appsgit.com/skills/category/devops-cloud) (80): Agent skills for deployment, CI/CD, containers, cloud platforms and infrastructure. - [Design & frontend](https://appsgit.com/skills/category/design-frontend) (234): Agent skills for UI design, frontend frameworks, CSS, accessibility and design systems. - [Security](https://appsgit.com/skills/category/security) (143): Agent skills for security review, threat modelling, vulnerability scanning and secure coding. ## Top 100 agent skills by GitHub stars - [Brainstorming](https://appsgit.com/skills/obra-brainstorming): You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. (296,071 stars, MIT) - [Systematic Debugging](https://appsgit.com/skills/obra-systematic-debugging): Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. (296,071 stars, MIT) - [Writing Plans](https://appsgit.com/skills/obra-writing-plans): Use when you have a spec or requirements for a multi-step task, before touching code. (296,071 stars, MIT) - [Requesting Code Review](https://appsgit.com/skills/obra-requesting-code-review): Use when completing tasks, implementing major features, or before merging to verify work meets requirements. (296,071 stars, MIT) - [Test Driven Development](https://appsgit.com/skills/obra-test-driven-development): Use when implementing any feature or bugfix, before writing implementation code. (296,071 stars, MIT) - [Verification Before Completion](https://appsgit.com/skills/obra-verification-before-completion): Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims… (296,071 stars, MIT) - [Receiving Code Review](https://appsgit.com/skills/obra-receiving-code-review): Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not… (296,071 stars, MIT) - [Writing Skills](https://appsgit.com/skills/obra-writing-skills): Use when creating new skills, editing existing skills, or verifying skills work before deployment. (296,071 stars, MIT) - [Finishing A Development Branch](https://appsgit.com/skills/obra-finishing-a-development-branch): Use when implementation is complete, all tests pass, and you need to decide how to integrate the work. (296,071 stars, MIT) - [Diagnosing Superpowers](https://appsgit.com/skills/obra-diagnosing-superpowers): Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so… (296,071 stars, MIT) - [Improve Codebase Architecture](https://appsgit.com/skills/mattpocock-improve-codebase-architecture): Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick. (278,361 stars, MIT) - [TDD](https://appsgit.com/skills/mattpocock-tdd): Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests. (278,361 stars, MIT) - [Setup Matt Pocock Skills](https://appsgit.com/skills/mattpocock-setup-matt-pocock-skills): Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. (278,361 stars, MIT) - [Prototype](https://appsgit.com/skills/mattpocock-prototype): Build a throwaway prototype to answer a design question. (278,361 stars, MIT) - [Codebase Design](https://appsgit.com/skills/mattpocock-codebase-design): Shared vocabulary for designing deep modules. (278,361 stars, MIT) - [Diagnosing Bugs](https://appsgit.com/skills/mattpocock-diagnosing-bugs): Diagnosis loop for hard bugs and performance regressions. (278,361 stars, MIT) - [Code Review](https://appsgit.com/skills/mattpocock-code-review): Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match… (278,361 stars, MIT) - [Wizard](https://appsgit.com/skills/mattpocock-wizard): Generate an interactive bash wizard that walks a human through steps only they can perform. (278,361 stars, MIT) - [Setup Pre Commit](https://appsgit.com/skills/mattpocock-setup-pre-commit): Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. (278,361 stars, MIT) - [Writing Beats](https://appsgit.com/skills/mattpocock-writing-beats): Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it. (278,361 stars, MIT) - [Writing Shape](https://appsgit.com/skills/mattpocock-writing-shape): Writing, exploit: shape raw material into an article, paragraph by paragraph. (278,361 stars, MIT) - [Scaffold Exercises](https://appsgit.com/skills/mattpocock-scaffold-exercises): Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. (278,361 stars, MIT) - [Migrate To Shoehorn](https://appsgit.com/skills/mattpocock-migrate-to-shoehorn): Migrate test files from as type assertions to @total-typescript/shoehorn. (278,361 stars, MIT) - [Setup Ts Deep Modules](https://appsgit.com/skills/mattpocock-setup-ts-deep-modules): Wire dependency-cruiser into a TypeScript repo so each package is a deep module, with implementation hidden in subfolders and reachable only through its entry-point files. (278,361 stars, MIT) - [Implement Spec](https://appsgit.com/skills/mattpocock-implement-spec): Implement the result of /to-spec and /to-tickets in code. (278,361 stars, MIT) - [Golang Testing](https://appsgit.com/skills/affaan-m-golang-testing): Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. (274,402 stars, MIT) - [Accessibility](https://appsgit.com/skills/affaan-m-accessibility): Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels, accessibility traits and hints, focus management, contrast, target… (274,402 stars, MIT) - [Backend Patterns](https://appsgit.com/skills/affaan-m-backend-patterns): Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. (274,402 stars, MIT, needs API key) - [Design System](https://appsgit.com/skills/affaan-m-design-system): Generate a design system from an existing codebase or audit one for visual consistency: extract tokens (colors, typography, spacing, shadows) into design-tokens.json and CSS custom properties with… (274,402 stars, MIT) - [Frontend A11y](https://appsgit.com/skills/affaan-m-frontend-a11y): Accessibility patterns for React and Next.js — semantic HTML, ARIA attributes, form labeling, keyboard navigation, focus management, and screen reader support. (274,402 stars, MIT) - [Frontend Design Direction](https://appsgit.com/skills/affaan-m-frontend-design-direction): Set an ECC-specific frontend design direction for production UI work. (274,402 stars, MIT) - [Postgres Patterns](https://appsgit.com/skills/affaan-m-postgres-patterns): PostgreSQL database patterns for query optimization, schema design, indexing, and security. (274,402 stars, MIT) - [React Patterns](https://appsgit.com/skills/affaan-m-react-patterns): React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and… (274,402 stars, MIT) - [React Performance](https://appsgit.com/skills/affaan-m-react-performance): React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). (274,402 stars, MIT) - [React Testing](https://appsgit.com/skills/affaan-m-react-testing): React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress… (274,402 stars, MIT) - [Karpathy Guidelines](https://appsgit.com/skills/multica-ai-karpathy-guidelines): Behavioral guidelines to reduce common LLM coding mistakes. (217,301 stars, MIT) - [Frontend Design](https://appsgit.com/skills/anthropics-frontend-design): Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. (179,945 stars, Apache-2.0, official) - [Skill Creator](https://appsgit.com/skills/anthropics-skill-creator): Create new skills, modify and improve existing skills, and measure skill performance. (179,945 stars, Apache-2.0, official) - [Webapp Testing](https://appsgit.com/skills/anthropics-webapp-testing): Toolkit for interacting with and testing local web applications using Playwright. (179,945 stars, Apache-2.0, official) - [MCP Builder](https://appsgit.com/skills/anthropics-mcp-builder): Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. (179,945 stars, Apache-2.0, official) - [Canvas Design](https://appsgit.com/skills/anthropics-canvas-design): Create beautiful visual art in .png and .pdf documents using design philosophy. (179,945 stars, Apache-2.0, official) - [Web Artifacts Builder](https://appsgit.com/skills/anthropics-web-artifacts-builder): Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). (179,945 stars, Apache-2.0, official) - [Brand Guidelines](https://appsgit.com/skills/anthropics-brand-guidelines): Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. (179,945 stars, Apache-2.0, official) - [Slack Gif Creator](https://appsgit.com/skills/anthropics-slack-gif-creator): Knowledge and utilities for creating animated GIFs optimized for Slack. (179,945 stars, Apache-2.0, official) - [Claude API](https://appsgit.com/skills/anthropics-claude-api): Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. (179,945 stars, Apache-2.0, official, needs API key) - [Ponytail](https://appsgit.com/skills/dietrichgebert-ponytail): Forces the laziest solution that actually works, simplest, shortest, most minimal. (156,966 stars, MIT) - [Ponytail Review](https://appsgit.com/skills/dietrichgebert-ponytail-review): Code review focused exclusively on over-engineering. (156,966 stars, MIT) - [Ponytail Audit](https://appsgit.com/skills/dietrichgebert-ponytail-audit): Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. (156,966 stars, MIT) - [Next Bundle Optimizer](https://appsgit.com/skills/vercel-next-bundle-optimizer): Audit and reduce Next.js browser initial-load work. (143,231 stars, MIT, official) - [Next Cache Components Adoption](https://appsgit.com/skills/vercel-next-cache-components-adoption): Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. (143,231 stars, MIT, official) - [Next Cache Components Optimizer](https://appsgit.com/skills/vercel-next-cache-components-optimizer): Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). (143,231 stars, MIT, official) - [Next Dev Loop](https://appsgit.com/skills/vercel-next-dev-loop): Verify Next.js runtime behavior after editing app code. (143,231 stars, MIT, official) - [Next Partial Prefetching Adoption](https://appsgit.com/skills/vercel-next-partial-prefetching-adoption): Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. (143,231 stars, MIT, official) - [Next Partial Prefetching Optimizer](https://appsgit.com/skills/vercel-next-partial-prefetching-optimizer): Optimize what selected Next.js client navigations include before the click under Partial Prefetching. (143,231 stars, MIT, official) - [Autoplan](https://appsgit.com/skills/garrytan-autoplan): Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (135,577 stars, MIT) - [Design Consultation](https://appsgit.com/skills/garrytan-design-consultation): Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview... (135,577 stars, MIT) - [Design HTML](https://appsgit.com/skills/garrytan-design-html): Design finalization: generates production-quality Pretext-native HTML/CSS. (135,577 stars, MIT) - [Design Review](https://appsgit.com/skills/garrytan-design-review): Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (135,577 stars, MIT) - [Document Generate](https://appsgit.com/skills/garrytan-document-generate): Generate missing documentation from scratch for a feature, module, or entire project. (135,577 stars, MIT) - [iOS Clean](https://appsgit.com/skills/garrytan-ios-clean): Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (135,577 stars, MIT) - [iOS Design Review](https://appsgit.com/skills/garrytan-ios-design-review): Visual design audit for iOS apps on real hardware. (135,577 stars, MIT) - [iOS Sync](https://appsgit.com/skills/garrytan-ios-sync): Regenerate the iOS debug bridge against the latest upstream gstack templates. (135,577 stars, MIT) - [Plan Design Review](https://appsgit.com/skills/garrytan-plan-design-review): Designer's eye plan review — interactive, like CEO and Eng review. (135,577 stars, MIT) - [Banner Design](https://appsgit.com/skills/nextlevelbuilder-banner-design): Design banners for social media, ads, website heroes, creative assets, and print. (133,647 stars, MIT) - [Brand](https://appsgit.com/skills/nextlevelbuilder-brand): Brand voice, visual identity, messaging frameworks, asset management, brand consistency. (133,647 stars, MIT) - [Design](https://appsgit.com/skills/nextlevelbuilder-design): Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML… (133,647 stars, MIT, needs API key) - [Design System](https://appsgit.com/skills/nextlevelbuilder-design-system): Token architecture, component specifications, and slide generation. (133,647 stars, MIT) - [UI Styling](https://appsgit.com/skills/nextlevelbuilder-ui-styling): Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. (133,647 stars, MIT) - [Shadcn](https://appsgit.com/skills/shadcn-ui-shadcn): Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. (125,223 stars, MIT) - [Migrate Radix To Base](https://appsgit.com/skills/shadcn-ui-migrate-radix-to-base): Migrates React projects and components from Radix UI to Base UI. (125,223 stars, MIT) - [Browser Use](https://appsgit.com/skills/browser-use): Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. (117,307 stars, MIT, official, needs API key) - [Cloud](https://appsgit.com/skills/browser-use-cloud): Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. (117,307 stars, MIT, official, needs API key) - [Open Source](https://appsgit.com/skills/browser-use-open-source): Documentation reference for writing Python code using the browser-use open-source library. (117,307 stars, MIT, official, needs API key) - [QA](https://appsgit.com/skills/browser-use-qa): QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. (117,307 stars, MIT, official, needs API key) - [X402](https://appsgit.com/skills/browser-use-x402): Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. (117,307 stars, MIT, official, needs API key) - [Safe Refactor](https://appsgit.com/skills/juliusbrussee-safe-refactor): Restructure code while preserving behavior. (110,252 stars, Apache-2.0) - [Surgical Patch](https://appsgit.com/skills/juliusbrussee-surgical-patch): Fix bugs and small behavior changes at the narrowest responsible layer. (110,252 stars, Apache-2.0) - [Migration](https://appsgit.com/skills/juliusbrussee-migration): Implement reversible compatibility-safe transitions. (110,252 stars, Apache-2.0) - [Caveman Setup](https://appsgit.com/skills/juliusbrussee-caveman-setup): Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. (110,252 stars, Apache-2.0, needs API key) - [Antigravity Support](https://appsgit.com/skills/google-gemini-antigravity-support): Use when the user asks questions, seeks help, or requests instructions related to installing, setting up, or migrating to Antigravity CLI. (107,240 stars, Apache-2.0, official) - [Code Review And Quality](https://appsgit.com/skills/addyosmani-code-review-and-quality): Conducts multi-axis code review. Use before merging any change. (102,166 stars, MIT) - [Security And Hardening](https://appsgit.com/skills/addyosmani-security-and-hardening): Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a… (102,166 stars, MIT) - [API And Interface Design](https://appsgit.com/skills/addyosmani-api-and-interface-design): Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. (102,166 stars, MIT) - [Performance Optimization](https://appsgit.com/skills/addyosmani-performance-optimization): Optimizes application performance across frontend, backend, queries, and databases. (102,166 stars, MIT) - [Frontend UI Engineering](https://appsgit.com/skills/addyosmani-frontend-ui-engineering): Builds production-quality, accessible, responsive user-facing UIs. (102,166 stars, MIT) - [Documentation And Adrs](https://appsgit.com/skills/addyosmani-documentation-and-adrs): Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you… (102,166 stars, MIT) - [Code Simplification](https://appsgit.com/skills/addyosmani-code-simplification): Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. (102,166 stars, MIT) - [Observability And Instrumentation](https://appsgit.com/skills/addyosmani-observability-and-instrumentation): Instruments code so production behavior is visible and diagnosable. (102,166 stars, MIT) - [Debugging And Error Recovery](https://appsgit.com/skills/addyosmani-debugging-and-error-recovery): Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. (102,166 stars, MIT) - [Doubt Driven Development](https://appsgit.com/skills/addyosmani-doubt-driven-development): Subjects every non-trivial decision to a fresh-context adversarial review before it stands. (102,166 stars, MIT) - [Context Engineering](https://appsgit.com/skills/addyosmani-context-engineering): Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project. (102,166 stars, MIT) - [Interview Me](https://appsgit.com/skills/addyosmani-interview-me): Extracts what the user actually wants instead of what they think they should want. (102,166 stars, MIT) - [Shipping And Launch](https://appsgit.com/skills/addyosmani-shipping-and-launch): Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. (102,166 stars, MIT) - [Clinical Case Report](https://appsgit.com/skills/nexu-io-clinical-case-report): Structured medical case presentation for clinical rounds, conferences, and documentation. (99,748 stars, Apache-2.0) - [Critique](https://appsgit.com/skills/nexu-io-critique): Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. (99,748 stars, Apache-2.0) - [Dating Web](https://appsgit.com/skills/nexu-io-dating-web): A consumer-feeling dating / matchmaking dashboard — left rail navigation, ticker bar of community signals, headline KPIs, a 30-day mutual-matches bar chart, and a match-rate trend block. (99,748 stars, Apache-2.0) - [Dcf Valuation](https://appsgit.com/skills/nexu-io-dcf-valuation): Discounted cash flow valuation and intrinsic value analysis for public companies. (99,748 stars, Apache-2.0) - [Digital Eguide](https://appsgit.com/skills/nexu-io-digital-eguide): A two-spread digital e-guide preview — page 1 is a cover (display title, author, "What's inside" stats, table of contents teaser); page 2 is a spread (lesson body with pull-quote and a step list). (99,748 stars, Apache-2.0) - [Flowai Live Dashboard Template](https://appsgit.com/skills/nexu-io-flowai-live-dashboard-template): Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity… (99,748 stars, Apache-2.0) - [Gamified App](https://appsgit.com/skills/nexu-io-gamified-app): A multi-frame gamified mobile-app prototype — three phone frames on a dark showcase stage. (99,748 stars, Apache-2.0) ## FAQ ### What is an agent skill? A skill is a folder containing a SKILL.md file: YAML frontmatter with a name and a description, followed by instructions, and optionally scripts or reference files. Agents load only the short description until a task matches it, then read the full instructions. The format is an open standard (agentskills.io) supported by Claude, Codex, Cursor, Gemini CLI, GitHub Copilot and others. ### How do I add a skill to Claude? In Claude Code, copy the skill folder (the one containing SKILL.md) to ~/.claude/skills// for all your projects, or to .claude/skills// inside one project. If the repository is a plugin marketplace, run /plugin marketplace add / and then /plugin install @. In the Claude apps (claude.ai and desktop), zip the skill folder and upload it under Customize > Skills > + > Upload a skill; code execution must be turned on. ### How do I add a skill to ChatGPT or Codex? Codex reads skills from .agents/skills// in your repository (and its parent folders) and from ~/.agents/skills/ (or $CODEX_HOME/skills) for every project, so copy the skill folder there. Inside Codex, the built-in $skill-installer skill can install skills from OpenAI's catalog. Standalone skills also work in the ChatGPT desktop app; skills bundled in plugins work on ChatGPT web, desktop and mobile. ### How do I add a skill to Cursor? Cursor loads agent skills from .cursor/skills/ or .agents/skills/ in a project and from ~/.cursor/skills/ or ~/.agents/skills/ for all projects. It also reads Claude's .claude/skills/ folders, so a skill installed for Claude Code is picked up by Cursor too. ### What does Official mean? Official means the skill is published by the vendor itself: Anthropic's own repositories, organizations listed as official on skills.sh, or GitHub organizations with a verified domain. 197 skills on appsgit are official. ### How are skills chosen? Skills come from skills.sh, the GitHub topics claude-skills, agent-skills, claude-code-skills and skills, and the major awesome lists. A skill is listed only if its SKILL.md has a valid name and a description of 80+ characters, it has a license (the repository's or its own), the repository has a commit in the last six months, and the repository has 100+ stars or the skill is listed on skills.sh. This first batch is curated for developers (coding, testing, DevOps, data, security, frontend and technical docs) and capped at about 1,000 skills, at most 25 per repository; more categories are coming. ### Are agent skills safe? Skills are instructions plus optional scripts that your agent may run, so only install skills from sources you trust. Read the SKILL.md and any bundled scripts first, and prefer official or widely used skills. JSON API: https://appsgit.com/api/v1/skills --- Canonical page: https://appsgit.com/skills Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed nightly. Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.