Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Anthropic Cybersecurity Skills is a community-maintained collection of structured cybersecurity skills for AI agents, following the agentskills.io open standard. The README cites roughly 817–818 skills across 29–34 security domains (the counts differ between sections of the README). Examples include memory forensics, detection rules, cloud breach scoping, and privacy compliance tasks such as GDPR data-subject access requests and privacy impact assessments.
Each skill is mapped to the frameworks relevant to its subject: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, MITRE D3FEND, NIST AI RMF and the MITRE Fight Fraud Framework (F3). The README lists compatibility with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI and 20+ other platforms. Users clone the repository and point their agent at the skills directory.
The project states that it is independent and not affiliated with Anthropic PBC. It includes offensive and dual-use techniques, such as red-team C2, phishing simulation and exploitation, and is intended only for authorized penetration testing, security research, defense and education. The README also links to a Casky.ai playground with a waitlist, which is a separate service.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
A skills collection that gives coding agents cybersecurity expertise, including frameworks like MITRE ATT&CK and NIST. Works with Claude Code, Copilot, Codex CLI, Cursor and Gemini CLI.
Closest neighbours by meaning, not just by category.
Library · Anthropic
Anthropic agent skill that steers Claude toward distinctive, intentional frontend design instead of generic AI-looking UI.
Library
MIT-licensed pack of 25 engineering skills and slash commands for AI coding agents, covering spec through ship.
App · Anthropic
Anthropic's Claude assistant and agentic coding tool, with chat apps, Projects, skills, connectors and Claude Code.
Library · NVIDIA
NVIDIA's open-source security scanner for AI agent skills, checking repos, URLs, zips and files for vulnerabilities.
Model · Anthropic
Anthropic's unrestricted variant of the Fable 5.2 model, available to vetted cybersecurity and biomedical organizations.
Agent · Anthropic
Claude Code mode that fans out many parallel sub-agents for deep tasks such as full codebase reviews.
