--- title: "agent-skills-eval vs Anthropic-Cybersecurity-Skills" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/darkrishabh-agent-skills-eval-vs-mukul975-anthropic-cybersecurity-skills" tools: ["darkrishabh-agent-skills-eval", "mukul975-anthropic-cybersecurity-skills"] --- # agent-skills-eval vs Anthropic-Cybersecurity-Skills *GraphCanon updated Aug 16, 2026* ## Verdict Pick agent-skills-eval if agent-skills-eval offers utilities to evaluate AI agents in line with agentskills.io framework using TypeScript; pick Anthropic-Cybersecurity-Skills if anthropic-Cybersecurity-Skills is a comprehensive repository of 817 structured cybersecurity skills mapped across six industry frameworks, making it highly versatile for various AI platforms and security needs. [agent-skills-eval](https://darkrishabh.github.io/agent-skills-eval/) reports 637 GitHub stars, 36 forks, and 11 open issues, last pushed Jul 15, 2026. [Anthropic-Cybersecurity-Skills](https://mahipal.engineer/Anthropic-Cybersecurity-Skills/) has 28k stars, 3.4k forks, and 46 open issues, last pushed Aug 8, 2026. Figures are from public GitHub metadata via [agent-skills-eval's repository](https://github.com/darkrishabh/agent-skills-eval) and [Anthropic-Cybersecurity-Skills's repository](https://github.com/mukul975/Anthropic-Cybersecurity-Skills). | | [agent-skills-eval](/tools/darkrishabh-agent-skills-eval.md) | [Anthropic-Cybersecurity-Skills](/tools/mukul975-anthropic-cybersecurity-skills.md) | | --- | --- | --- | | Tagline | A test runner for agentskills.io-style AI agent skills | 817 structured cybersecurity skills for AI agents | | Stars | 637 | 27,958 | | Forks | 36 | 3,401 | | Open issues | 11 | 46 | | Language | TypeScript | Python | | Adopt for | agent-skills-eval offers utilities to evaluate AI agents in line with agentskills.io framework using TypeScript. | Anthropic-Cybersecurity-Skills is a comprehensive repository of 817 structured cybersecurity skills mapped across six industry frameworks, making it highly versatile for various AI platforms and security needs. | | Persona | - | - | | Runtime | - | - | | License | MIT | Apache-2.0 | | Categories | AI Agents, Evaluation & Observability | AI Agents, Evaluation & Observability | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agent-skills-eval](/tools/darkrishabh-agent-skills-eval.md) | [Anthropic-Cybersecurity-Skills](/tools/mukul975-anthropic-cybersecurity-skills.md) | | --- | --- | --- | | Days since push | 13d | 8d | | Open issues (now) | 11 | 46 | | Stars delta | Unknown | +2.3k (30d) | | Open issues delta | Unknown | +6 (30d) | | Full report | [trust report](/tools/darkrishabh-agent-skills-eval/trust.md) | [trust report](/tools/mukul975-anthropic-cybersecurity-skills/trust.md) | ## Decision facts: agent-skills-eval - **Adopt for:** agent-skills-eval offers utilities to evaluate AI agents in line with agentskills.io framework using TypeScript. ## Decision facts: Anthropic-Cybersecurity-Skills - **Pricing:** freemium - Available under the Apache 2.0 license, ensuring free access and modification but without guaranteeing commercial support. - **Requirements:** Min 4 GB RAM; Supports integration with over 20 platforms including Claude Code and GitHub Copilot; Requires basic understanding of cybersecurity frameworks for optimal use - **Adopt for:** Anthropic-Cybersecurity-Skills is a comprehensive repository of 817 structured cybersecurity skills mapped across six industry frameworks, making it highly versatile for various AI platforms and security needs. ## Choose when ### Choose agent-skills-eval if… - agent-skills-eval is primarily TypeScript; Anthropic-Cybersecurity-Skills is Python. - License: agent-skills-eval is MIT, Anthropic-Cybersecurity-Skills is Apache-2.0. - Tags unique to agent-skills-eval: agent-evals, agent-skills, agentskills, cli. - When you use the agentskills.io framework for your project and require robust evaluation tools that can understand this specific framework's nuances. ### Choose Anthropic-Cybersecurity-Skills if… - Anthropic-Cybersecurity-Skills is primarily Python; agent-skills-eval is TypeScript. - License: Anthropic-Cybersecurity-Skills is Apache-2.0, agent-skills-eval is MIT. - Pricing: Available under the Apache 2.0 license, ensuring free access and modification but without guaranteeing commercial support.. - Requirements: Min 4 GB RAM; Supports integration with over 20 platforms including Claude Code and GitHub Copilot; Requires basic understanding of cybersecurity frameworks for optimal use. - Tags unique to Anthropic-Cybersecurity-Skills: cybersecurity, mitre-attack, nist-csf, security. - - Use when you require integration with multiple cybersecurity frameworks like MITRE ATT&CK, NIST CSF 2.0, and others, providing a robust foundation for skill-based operations. ## When NOT to use agent-skills-eval - This tool may not be suitable if you are using a different AI agent development framework outside of agentskills.io, as it specializes in evaluating skills based on this particular framework. - If your project does not use TypeScript and avoiding transpiler overhead is a priority, then opting for another evaluation tool that supports your primary language might be more beneficial. ## When NOT to use Anthropic-Cybersecurity-Skills - - Avoid if your project specifically requires skills mapped exclusively to a single framework not among the six supported by Anthropic-Cybersecurity-Skills. - - Not suitable for projects that do not align with or benefit from the agentskills.io standard implementation, as it might limit customization options. ## Common questions ### What is the difference between agent-skills-eval and Anthropic-Cybersecurity-Skills? agent-skills-eval: A test runner for agentskills.io-style AI agent skills. Anthropic-Cybersecurity-Skills: 817 structured cybersecurity skills for AI agents. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-skills-eval over Anthropic-Cybersecurity-Skills? Choose agent-skills-eval over Anthropic-Cybersecurity-Skills when agent-skills-eval is primarily TypeScript; Anthropic-Cybersecurity-Skills is Python; License: agent-skills-eval is MIT, Anthropic-Cybersecurity-Skills is Apache-2.0; Tags unique to agent-skills-eval: agent-evals, agent-skills, agentskills, cli; When you use the agentskills.io framework for your project and require robust evaluation tools that can understand this specific framework's nuances. ### When should I choose Anthropic-Cybersecurity-Skills over agent-skills-eval? Choose Anthropic-Cybersecurity-Skills over agent-skills-eval when Anthropic-Cybersecurity-Skills is primarily Python; agent-skills-eval is TypeScript; License: Anthropic-Cybersecurity-Skills is Apache-2.0, agent-skills-eval is MIT; Pricing: Available under the Apache 2.0 license, ensuring free access and modification but without guaranteeing commercial support.; Requirements: Min 4 GB RAM; Supports integration with over 20 platforms including Claude Code and GitHub Copilot; Requires basic understanding of cybersecurity frameworks for optimal use; Tags unique to Anthropic-Cybersecurity-Skills: cybersecurity, mitre-attack, nist-csf, security; - Use when you require integration with multiple cybersecurity frameworks like MITRE ATT&CK, NIST CSF 2.0, and others, providing a robust foundation for skill-based operations. ### When should I avoid agent-skills-eval? This tool may not be suitable if you are using a different AI agent development framework outside of agentskills.io, as it specializes in evaluating skills based on this particular framework. If your project does not use TypeScript and avoiding transpiler overhead is a priority, then opting for another evaluation tool that supports your primary language might be more beneficial. ### When should I avoid Anthropic-Cybersecurity-Skills? - Avoid if your project specifically requires skills mapped exclusively to a single framework not among the six supported by Anthropic-Cybersecurity-Skills. - Not suitable for projects that do not align with or benefit from the agentskills.io standard implementation, as it might limit customization options. ### Is agent-skills-eval or Anthropic-Cybersecurity-Skills more popular on GitHub? Anthropic-Cybersecurity-Skills has more GitHub stars (27,958 vs 637). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-skills-eval and Anthropic-Cybersecurity-Skills open source? Yes - both are open-source projects on GitHub (agent-skills-eval: MIT, Anthropic-Cybersecurity-Skills: Apache-2.0). ### Where can I find alternatives to agent-skills-eval or Anthropic-Cybersecurity-Skills? GraphCanon lists graph-backed alternatives at [agent-skills-eval alternatives](/tools/darkrishabh-agent-skills-eval/alternatives) and [Anthropic-Cybersecurity-Skills alternatives](/tools/mukul975-anthropic-cybersecurity-skills/alternatives) ([agent-skills-eval markdown twin](/tools/darkrishabh-agent-skills-eval/alternatives.md), [Anthropic-Cybersecurity-Skills markdown twin](/tools/mukul975-anthropic-cybersecurity-skills/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/darkrishabh-agent-skills-eval-vs-mukul975-anthropic-cybersecurity-skills.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-skills-eval or Anthropic-Cybersecurity-Skills? agent-skills-eval: Active. Anthropic-Cybersecurity-Skills: Active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for agent-skills-eval and Anthropic-Cybersecurity-Skills? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-skills-eval trust report](/tools/darkrishabh-agent-skills-eval/trust); [Anthropic-Cybersecurity-Skills trust report](/tools/mukul975-anthropic-cybersecurity-skills/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=darkrishabh-agent-skills-eval`](/api/graphcanon/graph?tool=darkrishabh-agent-skills-eval) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_