The open
registry for
AI Agent Skills

Discover, save, and install thousands of safety-reviewed skills for AI agents: Claude Code, Cursor, Codex, and 60+ more, all from one place.

25,790 skills 1,462 Official 60+ agents 100% free to use

Use a skill in 3 steps

1
Connect
npm i skillmds
2
Ask

“Add a Dockerfile optimizer.”

3
Build

The skill loads itself. No copy-paste.

Works with 60+ AI agents →

Official Agent Skills

anthropic
frontend-design
Guides distinctive, intentional visual design for new UI or existing interfaces, covering aesthetic direction, typography, and avoiding templated defaults.
158k · bundle
anthropic
pptx
Create, read, edit, and convert PowerPoint (.pptx) files with design guidance and visual QA workflows.
158k · bundle
anthropic
docx
Create, read, edit, and manipulate Word documents (.docx files) with formatting, tables, images, and tracked changes.
158k · bundle
anthropic
skill-creator
Create new skills, modify existing ones, and measure their performance through iterative evaluation and benchmarking.
158k · bundle
anthropic
web-artifacts-builder
Creates elaborate, multi-component HTML artifacts using React, Tailwind CSS, and shadcn/ui for complex frontend projects.
158k · bundle
anthropic
canvas-design
Creates visual art in .png and .pdf documents by first generating a design philosophy and then expressing it on a canvas.
158k · bundle
cloudflare-security-audit
security-audit
Finds exploitable vulnerabilities in codebases through a structured multi-phase audit covering recon, hunting, validation, and reporting.
· bundle
anthropic
xlsx
Create, edit, and analyze spreadsheet files (.xlsx, .xlsm, .csv, .tsv) with formulas, formatting, and financial modeling conventions.
158k · bundle
anthropic
theme-factory
Apply consistent, professional color palettes and font pairings to presentation slide decks and other artifacts using pre-set themes or custom on-the-fly generation.
158k · bundle
anthropic
algorithmic-art
Create algorithmic art by first writing a generative philosophy, then expressing it as p5.js sketches with seeded randomness and interactive parameter exploration.
158k · bundle
googlechrome
modern-web-guidance
Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: - UI/Layout: Modals, dialogs, popovers, Glassmorphism/backdrop-filters, anchor positioning, container queries, `:has()`, `:user-valid`. - Scroll/Motion: View Transitions, Scroll-driven animations, scroll parallax/reveals. - Performance: CWV (LCP, INP), content-visibility, Fetch Priority, image optimization. - System/APIs: Local filesystem access, WebUSB, WebSockets sync, WebAssembly widgets. - Frameworks: Adapting layout/styles in React, Vue, Angular. - General Frontend: Forms, autofill, advanced inputs, custom scrollbars, modern component states, etc. DO NOT trigger for: - Backend: Database SQL, ORMs, Express API routes. - Pipelines: CI/CD deployment, Docker, Actions. - Generic: Local scripts (Python/Go tools), ESLint, Git.
1.6k · bundle
anthropic
pdf
Read, extract, merge, split, rotate, watermark, encrypt, and create PDF files using Python libraries and command-line tools.
158k · bundle
obra
using-superpowers
Ensures skills are invoked before any response, including clarifying questions, and establishes how to find and use skills.
247k · bundle
microsoft
azure-ai
Integrate with Azure AI services including Search, Speech, OpenAI, and Document Intelligence for search, transcription, OCR, and text-to-speech tasks.
2.7k · bundle
View all

Top Agent Skills

anthropic
frontend-design
Guides distinctive, intentional visual design for new UI or existing interfaces, covering aesthetic direction, typography, and avoiding templated defaults.
158k · bundle
anthropic
pptx
Create, read, edit, and convert PowerPoint (.pptx) files with design guidance and visual QA workflows.
158k · bundle
anthropic
docx
Create, read, edit, and manipulate Word documents (.docx files) with formatting, tables, images, and tracked changes.
158k · bundle
anthropic
skill-creator
Create new skills, modify existing ones, and measure their performance through iterative evaluation and benchmarking.
158k · bundle
anthropic
web-artifacts-builder
Creates elaborate, multi-component HTML artifacts using React, Tailwind CSS, and shadcn/ui for complex frontend projects.
158k · bundle
anthropic
canvas-design
Creates visual art in .png and .pdf documents by first generating a design philosophy and then expressing it on a canvas.
158k · bundle
cloudflare-security-audit
security-audit
Finds exploitable vulnerabilities in codebases through a structured multi-phase audit covering recon, hunting, validation, and reporting.
· bundle
anthropic
xlsx
Create, edit, and analyze spreadsheet files (.xlsx, .xlsm, .csv, .tsv) with formulas, formatting, and financial modeling conventions.
158k · bundle
alirezarezvani
caveman
Reduces token usage by ~75% by stripping filler words, articles, and pleasantries while preserving full technical accuracy. Activates on user commands like 'caveman mode' or 'be brief'.
20.4k · bundle
anthropic
theme-factory
Apply consistent, professional color palettes and font pairings to presentation slide decks and other artifacts using pre-set themes or custom on-the-fly generation.
158k · bundle
juliusbrussee
caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into a concise format to save input tokens while preserving technical substance, code, URLs, and structure.
· bundle
alirezarezvani
code-reviewer
Automates code review for pull requests across 14+ languages, analyzing complexity, risk, code quality, and generating structured review reports.
20.4k · bundle
anthropic
algorithmic-art
Create algorithmic art by first writing a generative philosophy, then expressing it as p5.js sketches with seeded randomness and interactive parameter exploration.
158k · bundle
alirezarezvani
senior-architect
Design system architecture, evaluate microservices vs monolith, create architecture diagrams, analyze dependencies, choose databases, and make technical decisions with architecture decision records.
20.4k · bundle
View all

Latest Agent Skills

sickn33
blockrun
BlockRun works with Claude Code and Google Antigravity.
45.1k
sickn33
bash-pro
Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.
45.1k
sickn33
ask-matt
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
45.1k
sickn33
anywrite
Compiled CLI covering all 52 endpoints of the Anytype local API — objects, properties, tags, search, chat, files — one binary, no MCP server needed.
45.1k
sickn33
wiki-qa
Answer repository questions grounded entirely in source code evidence. Use when user asks a question about the codebase, user wants to understand a specific file, function, or component, or user asks "how does X work" or "where is Y defined".
45.1k
sickn33
videodb
Video and audio perception, indexing, and editing. Ingest files/URLs/live streams, build visual/spoken indexes, search with timestamps, edit timelines, add overlays/subtitles, generate media, and create real-time alerts.
45.1k · bundle
sickn33
varlock
Secure-by-default environment variable management for Claude Code sessions.
45.1k
sickn33
ux-flow
Design user flows and navigation structure following proven UX patterns
45.1k
sickn33
ux-copy
Generate UX microcopy (button labels, error messages, empty states, toasts) following a casual-but-polite voice and tone
45.1k
sickn33
use-dom
Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.
45.1k · bundle
sickn33
ui-page
Scaffold a new mobile page/screen using the StyleSeed layout patterns
45.1k
sickn33
ui-lint
Quick automated lint — detects common design system violations in seconds
45.1k
sickn33
ui-a11y
Audit a component or page for accessibility issues and fix them
45.1k
sickn33
sql-pro
Master modern SQL with cloud-native databases, OLTP/OLAP optimization, and advanced query techniques. Expert in performance tuning, data modeling, and hybrid analytical systems.
45.1k
View all

Frequently asked questions

What is an Agent Skill?

An Agent Skill is a reusable instruction file that teaches an AI agent to do one task well, such as reviewing code or extracting PDF tables. It ships as a SKILL.md file: YAML frontmatter plus Markdown instructions. The agent loads it automatically when a request matches, and the same file works across Claude Code, Cursor, Codex, and 60+ other agents.

What is a SKILL.md file?

It's the open format a skill ships in: a Markdown file with YAML frontmatter at the top (name, description, license) followed by the instructions in the body. The agent reads the short description to decide when the skill is relevant, then pulls in the full body only when needed (progressive disclosure).

Where can I download skills for Claude Code and other AI agents?

SkillMD (skillmd.com) is a free, open registry of thousands of AI agent skills. Search by task, category, or agent, then install with one CLI command (npx skillmds add owner/name), through the hosted MCP server, or by copying the SKILL.md file directly. Every public skill passes an automated safety review before it is listed.

When does an agent actually use a skill?

Automatically. The agent compares your request against each installed skill's description and triggers, then loads the most relevant one, so you don't have to invoke it by name. Good "use when…" descriptions are what make a skill discoverable to the model.

Skill vs. command vs. plugin: what's the difference?

A skill is knowledge or behaviour the agent applies on its own. A command is an explicit slash-action you run yourself. A plugin (what we call a Pack) bundles related skills, and sometimes commands, so you can install a whole workflow at once.

Do skills work across different agents and IDEs?

Yes. SKILL.md is an open standard, so the same skill works across Claude Code, Claude.ai, Codex, Cursor, Gemini, Antigravity and more. Each tool just reads the file from its skills directory. See skillmd.com/agents for per-agent install paths.

Are skills safe to install?

Treat them like any code you add to your workflow. Every skill on SkillMD shows capability flags (executes scripts, makes network calls, reads secrets, or docs-only), and SkillMD never runs a skill's scripts for you. Review the SKILL.md before installing, especially for unverified authors.

What does the verified ✓ badge mean?

It marks skills from official, trusted publishers like Anthropic, Google, Microsoft and Hugging Face. Anyone can publish, but the checkmark is reserved for vetted first-party sources.

Do AI agent skills cost anything?

No. SkillMD is 100% free: searching, saving, installing, and publishing skills all cost nothing, and skills remain under their authors' original licenses.

How do I install or submit a skill?

Install with the one-line MCP server (claude mcp add skillmds -- npx -y skillmds) and ask your agent by name, or download the SKILL.md directly. To contribute, use Submit a Skill: paste a SKILL.md or GitHub URL and it goes live after review.