# Anthropic Cybersecurity Skills

> An open-source library of 754 structured cybersecurity skills for AI agents, mapped to 5 frameworks across 26 security domains.

Anthropic Cybersecurity Skills is the largest open-source cybersecurity skills library for AI agents, containing 754 production-grade skills spanning 26 security domains. Every skill follows the agentskills.io standard with YAML frontmatter for fast discovery and structured Markdown for step-by-step execution. The library provides unified cross-framework coverage across MITRE ATT&CK v18, NIST CSF 2.0, MITRE ATLAS v5.4, MITRE D3FEND v1.3, and NIST AI RMF 1.0 — the only open-source skills library to map every skill to all five frameworks.

Key features include:

- **754 production-grade skills** across 26 security domains including Cloud Security, Threat Hunting, Malware Analysis, Incident Response, Penetration Testing, and more
- **Five-framework mapping** covering MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, and NIST AI RMF in every skill
- **Progressive disclosure architecture** where each skill costs ~30 tokens to scan (frontmatter) and 500–2,000 tokens to fully load, enabling agents to search all 754 skills without blowing context windows
- **Structured skill anatomy** with SKILL.md, references (standards + workflows), scripts, and asset templates per skill directory
- **26+ compatible AI platforms** including Claude Code, GitHub Copilot, Cursor, OpenAI Codex CLI, Gemini CLI, LangChain, CrewAI, AutoGen, and any agentskills.io-compatible agent
- **Quick start via npx** — run `npx skills add mukul975/Anthropic-Cybersecurity-Skills` or clone the repo directly to get started immediately
- **Apache 2.0 license** allowing free use, modification, and distribution in personal and commercial projects
- **Community-driven contributions** with PRs reviewed for technical accuracy and agentskills.io compliance within 48 hours

## Features
- 754 structured cybersecurity skills
- 26 security domains
- MITRE ATT&CK v18 mapping (14 tactics, 200+ techniques)
- NIST CSF 2.0 alignment (6 functions, 22 categories)
- MITRE ATLAS v5.4 mapping (AI/ML adversarial threats)
- MITRE D3FEND v1.3 mapping (267 defensive techniques)
- NIST AI RMF 1.0 mapping (4 functions, 72 subcategories)
- Progressive disclosure architecture (~30 tokens to scan frontmatter)
- agentskills.io standard compliance
- YAML frontmatter for sub-second agent discovery
- Structured Markdown workflow sections
- ATT&CK Navigator layer file included in releases
- Compatible with 26+ AI platforms and agent frameworks
- npx quick-start installation
- Community contributions with 48-hour PR review

## Integrations
Claude Code, GitHub Copilot, Cursor, OpenAI Codex CLI, Gemini CLI, Windsurf, Cline, Aider, Continue, Roo Code, Amazon Q Developer, Tabnine, Sourcegraph Cody, JetBrains AI, Devin, Replit Agent, SWE-agent, OpenHands, LangChain, CrewAI, AutoGen, Semantic Kernel, Haystack, Vercel AI SDK

## Platforms
WINDOWS, ANDROID, IOS, WEB, API, JETBRAINS_PLUGIN, DEVELOPER_SDK, CLI

## Pricing
Open Source

## Version
v1.2.0

## Links
- Website: https://mahipal.engineer/Anthropic-Cybersecurity-Skills/
- Documentation: https://github.com/mukul975/Anthropic-Cybersecurity-Skills/blob/main/CONTRIBUTING.md
- Repository: https://github.com/mukul975/Anthropic-Cybersecurity-Skills
- EveryDev.ai: https://www.everydev.ai/tools/anthropic-cybersecurity-skills