What it does
This is a collection of hundreds of "skills", instruction files that teach an AI agent how to do specific tasks, all about cybersecurity. Topics include investigating break-ins, analysing malware, cloud security, threat hunting and fraud detection.
Each skill is linked to well-known security frameworks such as MITRE ATT&CK and NIST, and works with many AI coding tools, including Claude Code, GitHub Copilot, Codex and Cursor.
It is a community project and says it is not affiliated with Anthropic. Its makers say some techniques are for authorised testing only, on systems you own or have written permission to test.
Who it's for
Security professionals, students and teams using AI agents for defence and investigation.
Can I use it without coding?
Developers only. You download the files and point an AI coding tool at them. New to this? Start here.
Can I run it?
- Cost
- Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
- API key
- Not needed
Try it
- Have an AI coding agent such as Claude Code, Cursor or Gemini CLI installed.
- Add the skills library to your agent with the skills installer, or download the repository.
- Only use the attack techniques on systems you own or have written permission to test.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe