✨ Editor's Choice

cloud

cloud

107Kbackend-api

Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2 or v3), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP WebSocket connections, stealth browsers, residential proxies, CAPTCHA handling, webhooks, workspaces, skills marketplace, liveUrl streaming, pricing, or integration patterns (chat UI, subagent, adding browser tools to existing agents). Also trigger for questions about n8n/Make/Zapier integration, Playwright/ Puppeteer/Selenium on cloud infrastructure, or 1Password vault integration. Do NOT use this for the open-source Python library (Agent, Browser, Tools config) — use the open-source skill instead.

browser-use avatarbrowser-use
Get
apple-hig

apple-hig

84Kagent-workflows

Apple Human Interface Guidelines as 14 agent skills covering platforms, foundations, components, patterns, inputs, and technologies for iOS, macOS, visionOS, watchOS, and tvOS.

nexu-io avatarnexu-io
Get
image-generation

image-generation

78Kbackend-api

Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.

bytedance avatarbytedance
Get
vitest

vitest

108Ktesting-qa

Vitest API and config reference (Jest-compatible) — mocking with vi.*, spies, fake timers, coverage configuration, fixtures, snapshots, and test filtering. Use for Vitest API and configuration questions anywhere in the monorepo; for Studio-specific test strategy and component-test setup, start with studio-testing and studio-mock-api-tests.

supabase avatarsupabase
Get
fsharp-testing

fsharp-testing

238Ktesting-qa

F# testing patterns with xUnit, FsUnit, Unquote, FsCheck property-based testing, integration tests, and test organization best practices.

affaan-m avataraffaan-m
Get
fix

fix

247Kfrontend

Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.

facebook avatarfacebook
Get

🆕 New Arrivals

View all
salesforce-apex-quality

salesforce-apex-quality

39Kbackend-api

Apex code quality guardrails for Salesforce development. Enforces bulk-safety rules (no SOQL/DML in loops), sharing model requirements, CRUD/FLS security, SOQL injection prevention, PNB test coverage (Positive / Negative / Bulk), and modern Apex idioms. Use this skill when reviewing or generating Apex classes, trigger handlers, batch jobs, or test classes to catch governor limit risks, security gaps, and quality issues before deployment.

github avatargithub
Get
solid

solid

18Kfrontend

SolidJS renderer for json-render. Use when building @json-render/solid catalogs/registries, wiring Renderer providers, implementing bindings/actions, or troubleshooting Solid-specific reactivity patterns.

vercel-labs avatarvercel-labs
Get
xstate

xstate

18Kbackend-api

XState Store adapter for json-render's StateStore interface. Use when integrating json-render with @xstate/store for state management via @json-render/xstate.

vercel-labs avatarvercel-labs
Get
amazon-ec2-image-builder

amazon-ec2-image-builder

2.7Ksecurity

Creates and automates custom image builds with EC2 Image Builder - Linux, Windows, and macOS AMIs, and container images to ECR. Covers the build IAM role, Amazon-managed and custom components, image recipes, infrastructure and distribution configuration (launch templates, SSM parameters, other Regions), one-off builds, recurring scheduled pipelines for golden AMI automation and OS patching, custom image workflows, and diagnosing failed builds. Applies when creating, automating, or scheduling AMI or container image builds with Image Builder, or when debugging a failed build. Not for launching instances from existing AMIs, AMI lifecycle/retirement, or general EC2 fleet management.

aws avataraws
Get
tscircuit

tscircuit

24design-ui

Build, modify, and debug tscircuit (React/TypeScript) PCB designs. Use when working with tsci CLI (init/dev/search/add/import/build/export/snapshot/push), choosing footprints, placing parts, wiring nets/traces, or preparing fabrication outputs (Gerbers/BOM/PnP).

tscircuit avatartscircuit
Get
capture-screen

capture-screen

1.4Kdesign-ui

Programmatic screenshot capture on macOS. Find window IDs with Swift CGWindowListCopyWindowInfo, control application windows via AppleScript (zoom, scroll, select), and capture with screencapture. Use when automating screenshots, capturing application windows for documentation, or building multi-shot visual workflows.

daymade avatardaymade
Get
connector-x

connector-x

0backend-api

MANDATORY recipe for every Caffeine build that posts to X (Twitter) from a canister. The supported path is the `x-client` mops package (X API v2) over outbound HTTPS, with per-user OAuth 2.0 (PKCE, no client secret). Hand-rolling `ic.http_request` calls to `api.x.com` is a FORBIDDEN anti-pattern — it bypasses bearer auth, the non-replicated-outcall safeguard, and the package's null-field JSON handling. Load this skill whenever the user, spec, or any prior task mentions posting a tweet, "tweet this", X/Twitter, sharing to X, or any equivalent phrasing — and BEFORE writing any code that touches an X endpoint.

caffeinelabs avatarcaffeinelabs
Get
radare2

radare2

37Kmcp-integrations

Use this skill whenever the user wants to analyze binaries with radare2/r2 from the command line, including reverse engineering, disassembly, function analysis, strings/import inspection, patching, binary diffing, hex inspection, or r2 scripting. Also use it when the user mentions PE/ELF/Mach-O/DEX/WASM files together with CLI analysis, `rabin2`, `rasm2`, `radiff2`, `r2pipe`, or asks for radare2 command help on Windows/Linux/macOS.

zhaoxuya520 avatarzhaoxuya520
Get
figma-design-to-code

figma-design-to-code

2Kdesign-ui

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE calling the `get_design_context` Figma MCP tool. You MUST trigger this skill whenever the user wants to implement, build, port, or code up a Figma design as code. Example prompts (not exhaustive) are 'implement this Figma design', 'build this screen from Figma', 'turn this Figma into code', 'design to code'. This skill provides critical instructions and steps to the agent on how to correctly implement Figma designs in code and must NOT be skipped.

figma avatarfigma
Get

What is an AI Agent Skill?

An AI Agent Skill (also known as Claude skills or AI skills) is a reusable capability you can add to an agent to automate tasks like writing, social posting, research, or development workflows.

Think of them as "plugins" for your AI. Browse our Claude skills marketplace to find Claude code templates and open-source GitHub repositories. Most come with a simple one-line installation command.

According to Anthropic's documentation on extending Claude with skills, skills package instructions, scripts, and resources so agents can perform specialized tasks more reliably.

Source: Anthropic — Extend Claude with skills

Skill: Research
v1.2.0 • Installed

Skills vs nearby concepts

AI Agent Skill

What it is

Reusable capability package (often a repo with SKILL.md) that teaches an agent a workflow.

When to use it

You want installable, shareable agent behaviors for Claude Code, Codex, or similar agents.

MCP server

What it is

A protocol endpoint that exposes tools/data to an agent over Model Context Protocol.

When to use it

You need live tool access (APIs, browsers, databases) rather than a static skill package.

Slash command

What it is

Built-in or local shortcut inside an agent UI/CLI.

When to use it

Quick in-product actions; less portable than a full skill.

🔥 Trending This Week

View all
skill-creator

skill-creator

386Kagent-workflows

Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources.

openclaw avataropenclaw
Get
coding-agent

coding-agent

384Kagent-workflows

Delegate coding work to Codex, Claude Code, or OpenCode as background workers; not simple edits or read-only code lookup.

steipete avatarsteipete
Get
investor-outreach

investor-outreach

239Kwriting-content

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

affaan-m avataraffaan-m
Get
ui-demo

ui-demo

232Kbrowser-web

Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.

affaan-m avataraffaan-m
Get
fastapi

fastapi

101Kbackend-api

FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.

fastapi avatarfastapi
Get
emilkowalski-motion

emilkowalski-motion

91Kdesign-ui

Motion-design follow-up skill inspired by Emil Kowalski's animation guidance. Use after an interface exists to add tasteful micro-interactions, state transitions, and page motion with product-grade restraint.

nexu-io avatarnexu-io
Get
ponytail

ponytail

79Kcode-generation

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

dietrichgebert avatardietrichgebert
Get
api-security-testing

api-security-testing

59Kbackend-api

Security-test a REST, GraphQL, or gRPC API with Strix — autonomous agents that enumerate endpoints from an OpenAPI/GraphQL schema (or by crawling), then actually exploit the API-specific vulnerability classes in the OWASP API Security Top 10 (2023) — broken object-level authorization (BOLA/IDOR), broken object property level authorization (excessive data exposure and mass assignment), broken function-level authorization, unrestricted resource consumption, SSRF, injection, and auth/token flaws. Every finding comes with a working proof-of-concept request. Use when the user asks to pentest, security-test, audit, or find vulnerabilities in an API, endpoint, or backend service.

usestrix avatarusestrix
Get
bmad-agent-ux-designer

bmad-agent-ux-designer

53Kdesign-ui

UX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer

bmad-code-org avatarbmad-code-org
Get

Browse by Category

View all
Trusted by AI enthusiasts worldwide
7.7K
Skills
987
Authors
245M
Stars
158
New / Week

Counts reflect released skills currently listed in the directory (distinct maintainers, cumulative GitHub stars on listed repos, and new releases in the last 7 days). Updated automatically. Directory snapshot refreshed hourly.

Power your workflows

Discover specialized agents tailored to specific industries and tasks.

Content Creation

Generate blog posts, social media captions, and marketing copy effortlessly using specialized writing agents trained on high-converting frameworks.

Automation

Streamline repetitive tasks like file organization, data entry, and email sorting with intelligent automation scripts that run 24/7.

Data Analysis

Extract insights from large datasets, visualize trends, and generate comprehensive reports in seconds with data-centric agent skills.

Built with open-source maintainers

This directory currently lists 7,660 released skills from 987 GitHub maintainers, with 579 new releases in the last 7 days. Counts come from published listings — not paid reviews.

  • Source-linked listings

    Every skill page points back to its upstream repository so you can inspect code, licenses, and recent commits.

  • Release gating

    Skills are only marked released after automated quality checks. Stars alone are not treated as a security guarantee.

  • Independent directory

    AI Agent Skills is community-run and not affiliated with Anthropic or OpenAI.

How to install a skill

2 minutes
1

Find a skill

Browse our extensive catalog of verified skills. Filter by category, popularity, or rating to find the perfect tool for your specific needs.

2

Copy command

Every skill comes with a simple, one-line installation command. Just click the copy button on the skill's detail page to capture the unique identifier.

3

Paste & run

Open your preferred AI environment like Claude Desktop. Paste the command into the chat or terminal. The system will automatically fetch and verify the skill.
Open Source

Built by the Community

Join thousands of developers contributing to the future of AI. All skills are open-source and vetted by the community.

Frequently Asked Questions

What is the difference between Skills and MCP?

MCP (Model Context Protocol) is the underlying standard protocol. Claude skills and AI skills are the actual tools and capabilities built using this standard that you install to give your AI agent new powers.

Are these skills safe to use?

Most Claude code skills listed in our marketplace are open-source, allowing you to review the code. We verify popular skills, but we always recommend reviewing the requested permissions (like file access or internet) before installation.

How are skills added to the directory?

The directory is maintained from public skill sources and repositories, with automated quality and safety checks before skills are released.

Is this service free?

Yes, browsing and discovering skills on AI Agent Skills is completely free. Most Claude code templates and plugins listed are also open-source and free to use.

What is a Claude skills marketplace?

A Claude skills marketplace is a platform where developers share and discover AI skills, Claude code templates, and plugins. AI Agent Skills focuses on curated, released skills for Claude Code, Codex CLI, and other AI agents.

How do I find Claude code templates?

Use our search feature or browse by category to find Claude code templates. Filter by stars, recent updates, or specific categories like development, automation, or content creation to find the perfect template for your needs.

Can I use multiple skills together?

Yes, you can install and use multiple AI skills simultaneously. Claude skills are designed to work independently, so you can combine a writing skill with a research skill or use several Claude code skills in the same workflow without conflicts.

Where can I inspect a skill's source code?

Open the skill detail page and follow its repository link. Review the README, source files, permissions, and recent activity before installing it.

How do skills differ from slash commands?

Slash commands are built-in shortcuts in Claude Code (like /help or /clear). Claude skills are external capabilities you install to extend your AI agent with new powers—like web search, code review, or content generation. Skills are more powerful and customizable than basic commands.

How often are skills updated?

Skills in our Claude code skills market are updated by their maintainers. Popular AI skills typically receive updates weekly or monthly. You can sort by 'Recently Updated' to find actively maintained Claude skills, and check the GitHub repository for update frequency.

What is marketplace.json?

marketplace.json is a configuration file some skills use to define metadata for the Claude marketplace. It includes the skill name, description, version, and installation instructions. Not all skills require this file—many work directly from their GitHub repository.

Is this website affiliated with Anthropic or OpenAI?

No, AI Agent Skills is an independent Claude skills marketplace created by the community. We are not officially affiliated with Anthropic (makers of Claude) or OpenAI. We curate and list open-source AI skills and Claude code templates from developers worldwide.