The open registry for Claude Code
Claude Skills
Claude skills are reusable SKILL.md instructions that extend Claude Code with new capabilities. Install free Claude skills from Anthropic, Microsoft, Google, Vercel, Stripe, and the developer community, in one command, with security scanning and version control built in.
What are Claude skills?
A Claude skill is a Markdown file with frontmatter, a SKILL.md, that tells Claude Code how to do one specific job well. Code review. Test generation. Deploying to Render. Auditing for HIPAA. Generating an API spec. The format is plain text, the standard is open, and the file is portable across every AI tool that supports the Agent Skills spec.
What makes skills different from a system prompt is conditional loading. A system prompt sits in every conversation, eating context. A skill is invoked only when its triggers match the task, so you can install hundreds of Claude skills without bloating the model's context window. Claude reads the skill, follows its instructions, and unloads it when the task is done.
What makes Claude skills different from Cursor rules, Copilot instructions, or any other tool-specific format is portability. The same SKILL.md works in Claude Code, Cursor, Codex CLI, Windsurf, Copilot, Gemini CLI, and any MCP-compatible client. Write once, run in every tool.
Best Claude skills
See all →The most-installed Claude skills on skills-hub.ai right now. Every skill is versioned, security-scanned, and linked to its upstream GitHub repository.
01code-review
375 installsThorough code review — checks correctness, security, performance, readability, and test coverage. Gives actionable feedback ranked by severity.
Review02ui-design-system
218 installsUI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use when creating design systems, generating design tokens, maintaining visual consistency, or facilitating design-dev collaboration and developer handoff.
Buildfrom Multi-Domain Skills03senior-frontend
154 installsFrontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.
Buildfrom Multi-Domain Skills04frontend-design
112 installsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
Buildfrom Anthropic05markitdown
108 installsConvert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
Researchfrom Scientific Skills06web-research-agent
102 installsA comprehensive autonomous web research agent that performs targeted searches, fetches and parses web content, summarizes findings, and generates structured reports, adhering to industry best practices for accuracy, security, and robustness.
Analysis07self-improving-agent
85 installsCurate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.
Buildfrom Multi-Domain Skills08Skill Finder
81 installsWorkflow orchestrator. Decomposes a task into ordered steps, finds or installs the right skill for each step, runs the chain, and offers to save it as a reusable skill.
Combo09senior-backend
72 installsDesigns and implements backend systems including REST APIs, microservices, database architectures, authentication flows, and security hardening. Use when the user asks to "design REST APIs", "optimize database queries", "implement authentication", "build microservices", "review backend code", "set up GraphQL", "handle database migrations", or "load test APIs". Covers Node.js/Express/Fastify development, PostgreSQL optimization, API security, and backend architecture patterns.
Buildfrom Multi-Domain Skills10security-review
66 installsSecurity audit and vulnerability assessment for any codebase. Scans for authentication bypasses, missing auth middleware, broken JWT validation (algorithm confusion, weak secrets, missing expiry), OAuth state and PKCE flaws, IDOR and horizontal privilege escalation.
Reviewfrom Skills Hub11using-superpowers
63 installsUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Buildfrom Superpowers12quickstart
63 installsZero to power user in one invoke — detects OS, installs Homebrew/apt/Node.js/Python, sets up Claude Code, authenticates skills-hub CLI, connects MCP servers, and installs recommended skills based on your project..
Productivity13refactor
58 installsSystematic code refactoring — extract functions, reduce complexity, eliminate duplication, improve naming, and split large files. Preserves behavior with tests.
Review14unit-test
57 installsGenerate comprehensive unit tests with edge cases, error paths, and boundary values. Triggers: you need to add unit tests, increase code coverage, test edge cases, or verify error handling paths.
Testfrom Skills Hub15design-to-code
55 installsTurn a design into production-quality frontend code: extract a design system with tokens and components, make layouts responsive across breakpoints, add dark mode with WCAG-compliant theming, then run a UX audit to validate everything..
Combofrom Skills Hub16social-media-manager
54 installsWhen the user wants to develop social media strategy, plan content calendars, manage community engagement, or grow their social presence across platforms. Also use when the user mentions 'social media strategy,' 'social calendar,' 'community management,' 'social media plan,' 'grow followers,' 'engagement rate,' 'social media audit,' or 'which platforms should I use.' For writing individual social posts, see social-content. For analyzing social performance data, see social-media-analyzer.
Marketingfrom Multi-Domain Skills17pptx
51 installsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.
Creativefrom Anthropic18marketing-strategy-pmm
45 installsProduct marketing skill for positioning, GTM strategy, competitive intelligence, and product launches. Use when the user asks about product positioning, go-to-market planning, competitive analysis, target audience definition, ICP definition, market research, launch plans, or sales enablement. Covers April Dunford positioning, ICP definition, competitive battlecards, launch playbooks, and international market entry. Produces deliverables including positioning statements, battlecard documents, launch plans, and go-to-market strategies.
Marketingfrom Multi-Domain Skills19security-audit
32 installsScan a codebase for security vulnerabilities — OWASP Top 10, secrets in code, dependency CVEs, auth flaws, injection risks, and misconfigurations. Fixes what it finds.
Review20humanizer
31 installsMulti-pass editor that removes AI-writing tells from drafted content — eliminates filler phrases, balances sentence length, restores opinion and voice, and strips em-dash overuse so posts sound human and opinionated rather than ChatGPT-generic..
Analysisfrom Skills Hub21docx
30 installsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Creativefrom Anthropic22swot-analysis
30 installsPerform a detailed SWOT analysis — strengths, weaknesses, opportunities, and threats with actionable recommendations. Use when doing strategic assessment, competitive analysis, or evaluating a product or business position.
Productfrom Product Management Skills23research-proposal
29 installsUse when the user asks to write or draft a PhD / doctoral research proposal, research plan, 研究计划书, or 开题报告 — a forward-looking plan of background, gap, research questions, methodology, timeline, and significance, in English or Chinese. Triggers: "write a research proposal", "PhD proposal", "doctoral proposal", "研究计划书", "开题报告", "写博士研究计划". Not for backward-looking literature reviews / 综述 / surveys (use medical-imaging-review), nor grant forms bound to a funder's own template (国自然/NSF).
Researchfrom Research Skills24skill-creator
27 installsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Metafrom Skills Hub
Claude skills by category
Browse Claude skills organized by what they do. Each category covers the most common tasks in modern AI-assisted development.
- Code review Claude skillsCatch bugs and review changes
- Testing Claude skillsGenerate and run tests
- Build Claude skillsConfigure builds and bundlers
- Deploy Claude skillsShip to production
- Security Claude skillsScan for vulnerabilities
- Documentation Claude skillsWrite and update docs
- Productivity Claude skillsSpeed up daily work
- Analysis Claude skillsProfile and audit code
- Integration Claude skillsConnect external services
- Ops Claude skillsRun and observe systems
- UX Claude skillsDesign and accessibility
- Combo Claude skillsMulti-skill compositions
How to install Claude skills
1. Pick a skill from the catalog
Open /browse, filter by Claude Code, sort by installs or quality, and pick a skill that matches your task. Every skill page shows a security grade, a quality score, and a link to the upstream GitHub repository.
2. Run the install command
$ npx @skills-hub-ai/cli install code-reviewThe CLI writes the SKILL.md to the right directory (
.claude/skills/for Claude Code) and adds an entry to.skills.jsonso your team gets the same skill at the same version.3. Use the skill
Open Claude Code and describe a task that matches the skill's triggers, for example, "review this PR" or "deploy to Render." Claude loads the skill on demand, follows its instructions, and unloads it when finished. No need to manage context yourself.
4. Optional: install via MCP
If your tool supports MCP, install
@skills-hub-ai/mcpand the entire registry becomes searchable as MCP prompts, no per-skill install needed.
Publish your own Claude skill
Built a great workflow in Claude Code? Publish it as a skill, get install counts and ratings, and let other developers run your work with one command. Sign in with GitHub, upload a SKILL.md, or generate one from a natural-language description.
Publish a skill →Frequently asked questions about Claude skills
What are Claude skills?
Claude skills are reusable instruction files (SKILL.md) that extend Claude Code with specialized capabilities like code review, testing, deployment, security scanning, or documentation. Claude loads a skill on demand when its trigger conditions match the task at hand, so your context window stays focused on the work, not the boilerplate. Skills follow the open Agent Skills standard and work in Claude Code, Cursor, Codex CLI, Windsurf, Copilot, and any MCP-compatible tool.
How do I install a Claude skill?
Run `npx @skills-hub-ai/cli install <skill-slug>` in your project. The CLI writes the SKILL.md file to the right directory for Claude Code (`.claude/skills/`), Cursor, Codex CLI, or any other supported tool, and adds an entry to your `.skills.json` lockfile so your team gets the same skills at the same versions. No API key required.
Where can I find the best Claude skills?
skills-hub.ai indexes Claude skills from 198 official sources, Anthropic, Microsoft, Google, Vercel, Stripe, Cloudflare, Trail of Bits, Prisma, Supabase, OpenAI, Hugging Face, and more, plus community contributions. Every skill is versioned, security-scanned with an A, F grade, and linked to its upstream GitHub repository.
Are Claude skills free?
Yes. Every skill on skills-hub.ai is free to install and use. The open Agent Skills standard is built on plain Markdown, so skills are portable and you keep ownership of any skills you publish.
How are Claude skills different from system prompts or Cursor rules?
A system prompt is loaded into every Claude conversation by default. A Claude skill is loaded only when its trigger conditions match, so you can have hundreds of skills installed without bloating your context window. Compared to Cursor rules (Cursor-specific, .cursorrules files), skills are tool-agnostic: the same SKILL.md works in Claude Code, Cursor, Codex, Windsurf, Copilot, and MCP tools.
Can I publish my own Claude skill?
Yes. Sign in with GitHub, click Publish, and either upload your existing SKILL.md or generate one from a natural-language description. Once published your skill is searchable, installable in one command, and tracked with install counts, ratings, and a quality score.
Is SKILL.md an official Anthropic format?
Anthropic introduced the Agent Skills standard in late 2025 and publishes its own skills openly at github.com/anthropics/skills. The format has been adopted by 26+ AI tools and platforms. skills-hub.ai mirrors Anthropic's official skills daily and indexes skills from 198 other companies and community publishers, all conforming to the same standard.
How does skill composition work?
Composition lets you chain multiple Claude skills into a single workflow with dependency ordering and parallel execution, for example, lint → test → security-scan → build. Each skill declares its expected inputs and outputs as structured metadata so the chain is validated before it runs. skills-hub.ai is the only Claude-skills platform that supports composition natively.