--- title: "code-eval vs agent-skills-eval" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/abacaj-code-eval-vs-darkrishabh-agent-skills-eval" tools: ["abacaj-code-eval", "darkrishabh-agent-skills-eval"] --- # code-eval vs agent-skills-eval *GraphCanon updated Aug 5, 2026* ## Verdict Pick code-eval if code-eval assesses large language models with the human-eval benchmark to provide insights into code generation reliability; pick agent-skills-eval if agent-skills-eval offers utilities to evaluate AI agents in line with agentskills.io framework using TypeScript. [code-eval](https://github.com/abacaj/code-eval) reports 431 GitHub stars, 37 forks, and 5 open issues, last pushed Sep 12, 2023. [agent-skills-eval](https://darkrishabh.github.io/agent-skills-eval/) has 637 stars, 36 forks, and 11 open issues, last pushed Jul 15, 2026. Figures are from public GitHub metadata via [code-eval's repository](https://github.com/abacaj/code-eval) and [agent-skills-eval's repository](https://github.com/darkrishabh/agent-skills-eval). | | [code-eval](/tools/abacaj-code-eval.md) | [agent-skills-eval](/tools/darkrishabh-agent-skills-eval.md) | | --- | --- | --- | | Tagline | Run evaluation on LLMs using human-eval benchmark. | A test runner for agentskills.io-style AI agent skills | | Stars | 431 | 637 | | Forks | 37 | 36 | | Open issues | 5 | 11 | | Language | Python | TypeScript | | Adopt for | code-eval assesses large language models with the human-eval benchmark to provide insights into code generation reliability. | agent-skills-eval offers utilities to evaluate AI agents in line with agentskills.io framework using TypeScript. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | Evaluation & Observability | AI Agents, Evaluation & Observability | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [code-eval](/tools/abacaj-code-eval.md) | [agent-skills-eval](/tools/darkrishabh-agent-skills-eval.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Active (82%) | | Days since push | 1058d | 13d | | Open issues (now) | 5 | 11 | | Full report | [trust report](/tools/abacaj-code-eval/trust.md) | [trust report](/tools/darkrishabh-agent-skills-eval/trust.md) | ## Decision facts: code-eval - **Adopt for:** code-eval assesses large language models with the human-eval benchmark to provide insights into code generation reliability. ## Decision facts: agent-skills-eval - **Adopt for:** agent-skills-eval offers utilities to evaluate AI agents in line with agentskills.io framework using TypeScript. ## Choose when ### Choose code-eval if… - code-eval is primarily Python; agent-skills-eval is TypeScript. - Tags unique to code-eval: humaneval, wizardcoder. - When you need clear comparisons of pass rates for different LLMs using standardized tests ### Choose agent-skills-eval if… - agent-skills-eval is primarily TypeScript; code-eval is Python. - Tags unique to agent-skills-eval: agent-evals, agent-skills, agentskills, ai-agents. - Also covers AI Agents. - When you use the agentskills.io framework for your project and require robust evaluation tools that can understand this specific framework's nuances. ## When NOT to use code-eval - If the tool's results do not correlate well with the official published benchmarks due to unknown prompt differences - For real-time or dynamic evaluations as this repo offers pre-computed static results only ## 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. ## Common questions ### What is the difference between code-eval and agent-skills-eval? code-eval: Run evaluation on LLMs using human-eval benchmark.. agent-skills-eval: A test runner for agentskills.io-style AI agent skills. See the comparison table for live GitHub stats and shared categories. ### When should I choose code-eval over agent-skills-eval? Choose code-eval over agent-skills-eval when code-eval is primarily Python; agent-skills-eval is TypeScript; Tags unique to code-eval: humaneval, wizardcoder; When you need clear comparisons of pass rates for different LLMs using standardized tests. ### When should I choose agent-skills-eval over code-eval? Choose agent-skills-eval over code-eval when agent-skills-eval is primarily TypeScript; code-eval is Python; Tags unique to agent-skills-eval: agent-evals, agent-skills, agentskills, ai-agents; Also covers AI Agents; 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 avoid code-eval? If the tool's results do not correlate well with the official published benchmarks due to unknown prompt differences For real-time or dynamic evaluations as this repo offers pre-computed static results only ### 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. ### Is code-eval or agent-skills-eval more popular on GitHub? agent-skills-eval has more GitHub stars (637 vs 431). Stars measure visibility, not whether either tool fits your constraints. ### Are code-eval and agent-skills-eval open source? Yes - both are open-source projects on GitHub (code-eval: MIT, agent-skills-eval: MIT). ### Where can I find alternatives to code-eval or agent-skills-eval? GraphCanon lists graph-backed alternatives at [code-eval alternatives](/tools/abacaj-code-eval/alternatives) and [agent-skills-eval alternatives](/tools/darkrishabh-agent-skills-eval/alternatives) ([code-eval markdown twin](/tools/abacaj-code-eval/alternatives.md), [agent-skills-eval markdown twin](/tools/darkrishabh-agent-skills-eval/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/abacaj-code-eval-vs-darkrishabh-agent-skills-eval.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, code-eval or agent-skills-eval? code-eval: Dormant. agent-skills-eval: 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 code-eval and agent-skills-eval? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [code-eval trust report](/tools/abacaj-code-eval/trust); [agent-skills-eval trust report](/tools/darkrishabh-agent-skills-eval/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=abacaj-code-eval`](/api/graphcanon/graph?tool=abacaj-code-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/_