Equip AI agents with 818 structured cybersecurity skills across 6 frameworks.
Equip your AI agent with 818 structured cybersecurity skills mapped to six major frameworks.
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.
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.
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.
Covers 34 distinct security domains from malware analysis to cloud security.
Maps individual skills to MITRE ATT&CK, NIST CSF 2.0, ATLAS, D3FEND, AI RMF, and F3.
Includes 94 fraud-relevant skills mapped to the MITRE Fight Fraud Framework.
Works directly with Claude Code, GitHub Copilot, Codex CLI, Cursor, and Gemini CLI.
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.
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.
These reviewed AI tools do the same job instantly — from our scored directory.
The repository supports Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI, Hermes Agent, and any platform compliant with the agentskills.io standard.
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.
Yes, the repository includes dual-use and offensive techniques intended strictly for authorized penetration testing, security research, and education.
See Zekai first in Google