● 279 skills indexed free + every skill scanned 36 new this week

Find the skill
your agent can trust.

The only free directory where every community skill is scanned for prompt injection, credential leaks, and hidden malicious code — before you install it.

Every skill scanned · prompt injection · credential leaks · malicious code · dep CVEs Security policy →
279 skills · 28 editor-verified · 10 categories · 30+ agents · 1.4M installs

Frequently Asked Questions

What are agent skills?

+

Agent skills are reusable instruction packages that teach AI coding agents how to handle specific tasks. Each skill is a folder containing a SKILL.md file with instructions the agent follows when activated. Skills work across Claude Code, OpenAI Codex, Gemini CLI, Cursor, and 30+ other tools.

How do I install an agent skill?

+

Type the skill's slash command (e.g. /code-review) directly in your AI coding agent. Skills can also be installed by cloning the skill repository to your ~/.claude/skills/ directory.

Which AI coding agents support skills?

+

The Agent Skills format is an open standard supported by Claude Code, OpenAI Codex, Google Gemini CLI, Cursor, Windsurf, Antigravity, and 25+ other AI coding agents. Skills are portable across platforms.

How are skills security-scanned?

+

Every community-submitted skill is automatically scanned for prompt injection, credential leaks, malicious code patterns, and dependency CVEs before it appears in the directory. Skills that fail the scan are rejected and logged publicly. See the rejected skills log and security reports.

The open directory of skills for AI coding agents. Every skill scanned. Always free.

279 Skills
28 Verified
30+ Agents
1.4M Installs
Added to wishlist