Anthropic-Cybersecurity-Skills vs skills
AI security workflows compared
Anthropic-Cybersecurity-Skills and skills both provide structured workflows for AI-assisted security work. Anthropic-Cybersecurity-Skills organizes guidance across security domains and maps it to industry frameworks, while skills offers focused plugins for security analysis, testing, and development.
Anthropic-Cybersecurity-Skills: Give AI Agents Security Playbooks
A library of structured cybersecurity workflows for AI agents, covering 34 security domains and mapped to six industry frameworks. Use it to provide compatible agents with practical guidance for authorized security work.
skills: Security Workflows for Claude Code and Codex
Trail of Bits Skills is a Claude Code plugin marketplace for AI-assisted security analysis, testing, and development. Codex can load the marketplace through Claude plugin compatibility, giving teams a collection of focused audit and verification workflows.
| Anthropic-Cybersecurity-Skills | skills | |
|---|---|---|
| Language | Python | Python |
| License | Apache-2.0 | CC-BY-SA-4.0 |
| Stars | 33.7k | 7.7k |
| Forks | 4.1k | 667 |
| Last analyzed | Oct 3, 2026 | Oct 21, 2026 |
Key differences
- Anthropic-Cybersecurity-Skills covers 34 security domains, while skills focuses on workflows for specific code, platform, and development targets.
- Anthropic-Cybersecurity-Skills uses structured skill files with YAML metadata and Markdown workflows; skills is a Claude Code plugin marketplace that can also be loaded by Codex.
- Anthropic-Cybersecurity-Skills maps skills to six frameworks, including MITRE ATT&CK and NIST CSF 2.0; skills emphasizes tools and workflows such as CodeQL, Semgrep, patch validation, and testing.
- Anthropic-Cybersecurity-Skills is Apache-2.0 licensed, while skills is CC-BY-SA-4.0 licensed, which carries attribution and share-alike obligations.
- Anthropic-Cybersecurity-Skills is community-maintained and intended for compatible agents; skills is from Trail of Bits and also documents ChatGPT Workspace imports.
Choose Anthropic-Cybersecurity-Skills if you…
- need guidance spanning security domains such as incident response, cloud security, forensics, and threat hunting.
- want workflows mapped to frameworks such as MITRE ATT&CK and NIST CSF 2.0.
- prefer Apache-2.0 licensed skill files that follow the agentskills.io standard.
Choose skills if you…
- need focused code audit, vulnerability discovery, or patch verification workflows.
- work with targets such as smart contracts, C/C++, Rust, GitHub Actions, or Android Firebase configurations.
- want a Claude Code marketplace that can also be loaded through Codex compatibility.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.