--- title: "agent-skills-eval vs qiushi-skill" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/darkrishabh-agent-skills-eval-vs-hughyau-qiushi-skill" tools: ["darkrishabh-agent-skills-eval", "hughyau-qiushi-skill"] --- # agent-skills-eval vs qiushi-skill *GraphCanon updated Sep 20, 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 qiushi-skill if qiushi-Skill methodologically equips AI agents with rigorous analytical tools derived from materialist dialectics and practical philosophy, enabling more thorough problem-solving processes. [agent-skills-eval](https://darkrishabh.github.io/agent-skills-eval/) reports 790 GitHub stars, 42 forks, and 15 open issues, last pushed Aug 5, 2026. [qiushi-skill](http://hughyau.com/qiushi-skill/) has 3.8k stars, 285 forks, and 19 open issues, last pushed Sep 6, 2026. Figures are from public GitHub metadata via [agent-skills-eval's repository](https://github.com/darkrishabh/agent-skills-eval) and [qiushi-skill's repository](https://github.com/HughYau/qiushi-skill). | | [agent-skills-eval](/tools/darkrishabh-agent-skills-eval.md) | [qiushi-skill](/tools/hughyau-qiushi-skill.md) | | --- | --- | --- | | Tagline | A test runner for agentskills.io-style AI agent skills | Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. | | Stars | 790 | 3,781 | | Forks | 42 | 285 | | Open issues | 15 | 19 | | Language | TypeScript | JavaScript | | Adopt for | agent-skills-eval offers utilities to evaluate AI agents in line with agentskills.io framework using TypeScript. | Qiushi-Skill methodologically equips AI agents with rigorous analytical tools derived from materialist dialectics and practical philosophy, enabling more thorough problem-solving processes. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | AI Agents, Evaluation & Observability | AI Agents | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [agent-skills-eval](/tools/darkrishabh-agent-skills-eval.md) | [qiushi-skill](/tools/hughyau-qiushi-skill.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Active (82%) | | Days since push | 45d | 9d | | Open issues (now) | 15 | 19 | | Stars delta | +153 (30d) | +90 (30d) | | Open issues delta | +4 (30d) | -1 (30d) | | Full report | [trust report](/tools/darkrishabh-agent-skills-eval/trust.md) | [trust report](/tools/hughyau-qiushi-skill/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: qiushi-skill - **Adopt for:** Qiushi-Skill methodologically equips AI agents with rigorous analytical tools derived from materialist dialectics and practical philosophy, enabling more thorough problem-solving processes. ## Choose when ### Choose agent-skills-eval if… - agent-skills-eval is primarily TypeScript; qiushi-skill is JavaScript. - Tags unique to agent-skills-eval: agent-evals, agent-skills, agentskills, cli. - Also covers Evaluation & Observability. - When you use the agentskills.io framework for your project and require robust evaluation tools that can understand this specific framework's nuances. ### Choose qiushi-skill if… - qiushi-skill is primarily JavaScript; agent-skills-eval is TypeScript. - Tags unique to qiushi-skill: methodology, skills, workflow. - When you need AI agents to deeply analyze problems rather than just provide surface-level answers ## 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 qiushi-skill - Avoid if quick, heuristic-based decisions are preferred over thorough analysis - Not suitable when AI personality simulation is a primary requirement - If using non-political or non-propaganda related methodological tools might be misconstrued in your context ## Common questions ### What is the difference between agent-skills-eval and qiushi-skill? agent-skills-eval: A test runner for agentskills.io-style AI agent skills. qiushi-skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done.. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-skills-eval over qiushi-skill? Choose agent-skills-eval over qiushi-skill when agent-skills-eval is primarily TypeScript; qiushi-skill is JavaScript; Tags unique to agent-skills-eval: agent-evals, agent-skills, agentskills, cli; Also covers Evaluation & Observability; 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 qiushi-skill over agent-skills-eval? Choose qiushi-skill over agent-skills-eval when qiushi-skill is primarily JavaScript; agent-skills-eval is TypeScript; Tags unique to qiushi-skill: methodology, skills, workflow; When you need AI agents to deeply analyze problems rather than just provide surface-level answers. ### 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 qiushi-skill? Avoid if quick, heuristic-based decisions are preferred over thorough analysis Not suitable when AI personality simulation is a primary requirement If using non-political or non-propaganda related methodological tools might be misconstrued in your context ### Is agent-skills-eval or qiushi-skill more popular on GitHub? qiushi-skill has more GitHub stars (3,781 vs 790). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-skills-eval and qiushi-skill open source? Yes - both are open-source projects on GitHub (agent-skills-eval: MIT, qiushi-skill: MIT). ### Where can I find alternatives to agent-skills-eval or qiushi-skill? GraphCanon lists graph-backed alternatives at [agent-skills-eval alternatives](/tools/darkrishabh-agent-skills-eval/alternatives) and [qiushi-skill alternatives](/tools/hughyau-qiushi-skill/alternatives) ([agent-skills-eval markdown twin](/tools/darkrishabh-agent-skills-eval/alternatives.md), [qiushi-skill markdown twin](/tools/hughyau-qiushi-skill/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-hughyau-qiushi-skill.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 qiushi-skill? agent-skills-eval: Steady. qiushi-skill: 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 qiushi-skill? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-skills-eval trust report](/tools/darkrishabh-agent-skills-eval/trust); [qiushi-skill trust report](/tools/hughyau-qiushi-skill/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/_