What it does
The library contains 818 structured cybersecurity skills across 34 security domains, each following the agentskills.io open standard. Skills are mapped to frameworks suited to their type, including MITRE ATT&CK v19.1, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, NIST AI RMF and MITRE F3. Skill mappings are recorded in each skill's frontmatter, and ATT&CK mappings were validated against the official mitreattack-python library.
It suits security work where an agent needs domain-specific guidance, such as analysing a suspicious memory dump, identifying Kerberoasting with Sigma rules, scoping a breach across several cloud providers, or reviewing cyber-enabled financial fraud techniques under the F3 framework.
To use it, clone the repository and point an agent at the skills folder. The publisher lists compatibility with Claude Code, GitHub Copilot, OpenAI Codex CLI, Cursor, Gemini CLI and other agentskills.io-compatible platforms.
Limitations and requirements
The library includes offensive and dual-use techniques, such as red-team command-and-control, phishing simulation and exploitation. The publisher states they are intended only for authorized penetration testing, security research, defence and education, and should be used only against systems the user owns or has explicit written permission to test. The user is solely responsible for how the skills are used. The project is a community project and is not affiliated with Anthropic PBC.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
Sources
- VoltAgent awesome agent skills first seen 13 Nov 2026 · last seen 16 Nov 2026 · its page on the source
Preview card provided by GitHub