One email each morning — yesterday's AI, sortedGet it in your inbox

METAL LAB

mukul975/Anthropic-Cybersecurity-Skills

30,063+766 todayPython

An open-source library that gives AI agents 817 ready-made cybersecurity playbooks

This repository packages 817 structured 'skill' documents that AI coding tools and agents can reference when doing cybersecurity work. Each skill spells out when to use which tool and what steps to follow, and is mapped to six industry frameworks including MITRE ATT&CK. It plugs directly into 20+ AI platforms such as Claude Code, GitHub Copilot, and Cursor.

What it does

  1. 817 skill documents are organized across 29 security domains, covering things like memory forensics, phishing detection, and cloud breach response
  2. Each skill has a YAML summary block plus a markdown body with 'When to Use, Prerequisites, Workflow, Verification' sections, letting agents first scan lightweight summaries (~30 tokens each) and only fully load (500-2,000 tokens) the ones they need
  3. Skills are mapped to whichever of six frameworks fit them: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, NIST AI RMF, and MITRE F3 (fraud framework)
  4. Installable via npx or git clone, and works out of the box with any agentskills.io-compatible platform, including Claude Code, Copilot, Cursor, and Gemini CLI
  5. Released under Apache 2.0 as a community project; it explicitly states it is not affiliated with Anthropic

Why it matters

Amid a shortage of security professionals, this gives AI agents a practical, procedural knowledge base to follow real analyst workflows instead of guessing. The repo itself warns that it includes offensive techniques, so it must only be used with proper authorization.

Terms in this repo

  • MITRE ATT&CK · an industry-standard knowledge base cataloging real-world attacker tactics and techniques
  • NIST CSF · a U.S. NIST framework for assessing an organization's overall security posture
  • agentskills.io · an open standard defining how AI agents should read and use skill documents
  • YAML frontmatter · a metadata block at the top of a document summarizing tags and description
  • D3FEND · a MITRE knowledge base of defensive countermeasures mapped against attack techniques

Repository description (English)

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

Open on GitHub

Trending repos

All repos →

Latest from METAL LAB