Agent skills discovery
Find trusted agent skills. Install in minutes.
One directory for every AI coding tool. Browse skills for Claude Code, Cursor, Copilot, Codex CLI, Gemini CLI, and more - review trust and risk before you install.
Why people need this now
AI agents are everywhere. Trusted skills are not.
Whether you use Claude Code, Cursor, Copilot, Codex CLI, or Gemini CLI — the question is the same: what to install first, what is actually useful, and how to avoid a random repo you do not understand.
This site is a decision layer between hype and action: less vague catalog, more guided discovery. One SKILL.md format, every tool.
What is different here
The site should optimize for install decisions, not just GitHub discovery. That means package intent, starter skill guidance, and visible risk context.
Who this is for
AI agent users across Claude Code, Cursor, Copilot, Codex CLI, Gemini CLI, and teams trying to standardize which packages are safe enough to try first.
What to do first
Start from the trusted shortlist if you want a cleaner path. Use the broader packages page when you already know the kind of workflow you need.
A better browse flow
Use the site in three steps
The goal is not to make you read every page. The goal is to move you from “agent skills look interesting” to “I know which package to try first and why”.
Install workflow
Copy the command only after you understand the package
The site should not rush people from hype to install. It should help them understand the package first, then make the install command obvious when they are ready.
Default command
One command, but not blind install
npx skills add agentworks/secure-skills
1. Shortlist a package
2. Review fit, starter skill, and risk
3. Then copy the install command
Install on your agent
DocsClaude Code skills
- Create skills directory
- Install a package (recommended)
mkdir -p ~/.claude/skills
Or install via: npx skills add owner/repo
Codex skills
- Install new skills (CLI or manual)
- Restart Codex to pick up new skills
mkdir -p ~/.codex/skills
Then restart Codex.
Use Agent Skills in VS Code
- Store skills inside your repo
- Share with your team
.github/skills/my-skill/SKILL.md
Cursor agent skills
- Add a remote rule from GitHub
- Apply skills to the project
npx skills add owner/repo
FAQ
What should I do before installing a package?
Read the package detail page first: check what the package is for, which skill to start with, and whether the risk notes match your tolerance.
Why is this site useful for the OpenClaw wave?
Because people need more than a GitHub link. They need help deciding which packages are installable, understandable, and worth trying first.
What is the default install command?
Run npx skills add owner/repo to install a package in seconds. Use the package detail page to decide whether you should run it.
Step 01
Start from trusted packages
If you are new to the ecosystem, do not start from the noisiest or newest repo. Start from the shortlist that looks installable and understandable.
Open trusted shortlistStep 02
Read the package like a product
A useful detail page should tell you what the package is for, when to skip it, which skill to read first, and how much real implementation it bundles.
Browse package detailsStep 03
Install only after you understand it
The install command should be the last step in the decision flow, not the first thing you see before you know what the package actually contains.
See install flowRecommended first click
Trusted packages to start with
Best for security-sensitive workflows
agentworks/secure-skillsCurated, low-risk skills for code review, research, and triage.
Signals
🟠 StaleStars 1,280 · 120 forks
Updated 3 months ago
Topics
code-review · security · agents
Best for MCP and agent tooling
stripe/aiOne-stop shop for building AI-powered products and businesses with Stripe.
Signals
🟢 ActiveStars 1,430 · 247 forks
Updated 14 days ago
Topics
ai · llm · llm-agents
Best for reusable agent workflows
openclaw/openclawYour own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Signals
🟢 ActiveStars 339,013 · 66,704 forks
Updated 20 days ago
Topics
ai · assistant · crustacean
Safer entry points
Low-risk packages for first-time installs
Best for security-sensitive workflows
agentworks/secure-skillsCurated, low-risk skills for code review, research, and triage.
Signals
🟠 StaleStars 1,280 · 120 forks
Updated 3 months ago
Topics
code-review · security · agents
Best for reusable agent workflows
supabase/agent-skillsAgent Skills to help developers using AI agents with Supabase
Signals
🟢 ActiveStars 1,822 · 118 forks
Updated 13 days ago
Topics
ai · ai-agents · skills
Best for reusable agent workflows
firecrawl/firecrawl🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data
Signals
🟢 ActiveStars 99,678 · 6,665 forks
Updated 20 days ago
Topics
ai · ai-agents · ai-crawler
Recently updated
Fresh packages worth evaluating
Best for operations and runbooks
wanshuiyin/Auto-claude-code-research-in-sleepARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, ...
Signals
🟢 ActiveStars 5,435 · 464 forks
Updated 13 days ago
Topics
ai-research · ai-tools · aris
Best for coding-agent workflows
garrytan/gstackUse Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Signals
🟢 ActiveStars 63,373 · 8,532 forks
Updated 13 days ago
Topics
General workflow package
Best for coding-agent workflows
anthropics/claude-agent-sdk-pythonNo description provided.
Signals
🟢 ActiveStars 6,118 · 839 forks
Updated 13 days ago
Topics
General workflow package