AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Cybersecurity › Anthropic Cybersecurity Skills
✦ Free & open sourceCybersecurity

Anthropic Cybersecurity Skills

Equip AI agents with 818 structured cybersecurity skills across 6 frameworks.

Cybersecurity Skills for AI Agents

Equip your AI agent with 818 structured cybersecurity skills mapped to six major frameworks.

Free forever · open source · Apache-2.0
✓ Light setup✓ Browser-based✓ Real-time collaboration
7.2
ZEKAI
Essential agent security library
Free & open source · Cybersecurity
Ease of setup2
Usefulness9
Maintenance8.5
Community9.2
★ 35,246
GITHUB
Aug 2026
UPDATED
Apache-2.0
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

This repository provides 818 production-grade cybersecurity skills designed for AI agents following the agentskills.io standard. It suits security professionals, red teams, and developers wanting to give AI assistants expert-level investigation and analysis capabilities.

Runs on
Cross-platform
Hosting
Desktop
Languages
Python
License
Apache-2.0

What it is

It feeds structured domain knowledge into AI coding assistants and CLI platforms across 34 security domains. Each skill maps directly to relevant frameworks like MITRE ATT&CK v19.1, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF, and the MITRE Fight Fraud Framework.

Who it's for

It suits security analysts and penetration testers integrating AI tooling into operational workflows. It does not suit teams lacking an AI agent platform that supports the agentskills.io standard or those seeking a traditional graphical security information and event management tool.

Key features

818 Cybersecurity Skills

Covers 34 distinct security domains from malware analysis to cloud security.

Six Framework Mappings

Maps individual skills to MITRE ATT&CK, NIST CSF 2.0, ATLAS, D3FEND, AI RMF, and F3.

Mitre F3 Support

Includes 94 fraud-relevant skills mapped to the MITRE Fight Fraud Framework.

Broad Platform Support

Works directly with Claude Code, GitHub Copilot, Codex CLI, Cursor, and Gemini CLI.

How to start

Up and running in 3 steps

1
Install via npx using the command `npx skills add mukul975/Anthropic-Cybersecurity-Skills`
2
Alternatively, clone the repository directly using Git to inspect the skill files
3
Point your supported AI coding assistant or CLI platform at the skills directory
Real talk

Our honest verdict

What's great

  • Massive library of 818 structured, production-grade cybersecurity skills
  • Precise mapping to official framework versions like MITRE ATT&CK v19.1
  • Compatible with over 26 AI platforms via the agentskills.io standard
  • Includes specialized coverage for AI security risks and cyber-enabled financial fraud

Where it falls short

  • Requires an existing compatible AI agent platform or CLI tool to utilize effectively
  • Offensive and dual-use skills demand strict adherence to authorized authorization and legal boundaries
  • Continuous upkeep needed to align local agent skill sets with evolving threat intelligence
Cost

Pricing & license

Free under its open-source license, with no paid hosted tier offered by the project. The only cost is your own time integrating and running the skills within your AI agent workflows.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: Anthropic Cybersecurity Skills for Cybersecurity
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure Anthropic Cybersecurity Skills for you — and train your team.
Get it done for you ↗
Questions

FAQ

What AI platforms are compatible with these skills?

The repository supports Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, Hermes Agent, and any platform compliant with the agentskills.io standard.

How many security frameworks are mapped in the library?

The skills map across six industry frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, NIST AI RMF, and the MITRE Fight Fraud Framework.

Are offensive security techniques included?

Yes, the repository includes dual-use and offensive techniques intended strictly for authorized penetration testing, security research, and education.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Cybersecurity — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google