Comparison
agent-skills-eval vs qiushi-skill
Verdict
Unverified catalog guidance: agent-skills-eval: agent-skills-eval offers utilities to evaluate AI agents in line with agentskills.io framework using TypeScript. qiushi-skill: Qiushi-Skill methodologically equips AI agents with rigorous analytical tools derived from materialist dialectics and practical philosophy, enabling more thorough problem-solving processes.
Markdown twin · agent-skills-eval alternatives · qiushi-skill alternatives
GraphCanon updated Oct 25, 2026
Trust & integrity
| Signal | agent-skills-eval | qiushi-skill |
|---|---|---|
| Maintenance | Steady (45d since push) As of Sep 20, 2026 · github_public_v1 | Active (23d since push) As of Oct 25, 2026 · github_public_v1 |
| Provenance | Not a fork · Personal account As of Sep 20, 2026 · github_public_v1 | Not a fork · Personal account As of Oct 25, 2026 · github_public_v1 |
| OSV dependency advisories | No lockfile (source not queried) As of Jul 11, 2026 · osv@v1 | No lockfile (source not queried) As of Jul 15, 2026 · osv@v1 |
| deps.dev advisories | Not queried deps.dev@v1 | Not queried deps.dev@v1 |
| OpenSSF Scorecard | Not queried openssf-scorecard@v1 | Not queried openssf-scorecard@v1 |
Tagline
- 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.
Stars
- agent-skills-eval
- 790
- qiushi-skill
- 3.8k
Forks
- agent-skills-eval
- 42
- qiushi-skill
- 285
Open issues
- agent-skills-eval
- 15
- qiushi-skill
- 20
Language
- agent-skills-eval
- TypeScript
- qiushi-skill
- JavaScript
Adopt for
- agent-skills-eval
- Unverified catalog guidance: agent-skills-eval offers utilities to evaluate AI agents in line with agentskills.io framework using TypeScript.
- qiushi-skill
- Unverified catalog guidance: Qiushi-Skill methodologically equips AI agents with rigorous analytical tools derived from materialist dialectics and practical philosophy, enabling more thorough problem-solving processes.
Persona
- agent-skills-eval
- -
- qiushi-skill
- -
Runtime
- agent-skills-eval
- -
- qiushi-skill
- -
License
- agent-skills-eval
- MIT
- qiushi-skill
- MIT
Last pushed
- agent-skills-eval
- Aug 5, 2026
- qiushi-skill
- Oct 1, 2026
Categories
- agent-skills-eval
- AI Agents, Evaluation & Observability
- qiushi-skill
- AI Agents
Trust and health
Maintenance
- agent-skills-eval
- Steady (60%)
- qiushi-skill
- Active (82%)
Days since push
- agent-skills-eval
- 45d
- qiushi-skill
- 23d
Open issues (recorded)
- agent-skills-eval
- 15
- qiushi-skill
- 20
Stars delta
- agent-skills-eval
- +153 (30d)
- qiushi-skill
- +44 (30d)
Open issues delta
- agent-skills-eval
- +4 (30d)
- qiushi-skill
- +1 (30d)
Full report
- agent-skills-eval
- Trust report
- qiushi-skill
- Trust report
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.
- Unverified catalog guidance: 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 agent-skills-eval
- Unverified catalog guidance: 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.
- Unverified catalog guidance: 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.
Choose qiushi-skill if…
- qiushi-skill is primarily JavaScript; agent-skills-eval is TypeScript.
- Tags unique to qiushi-skill: methodology, skills, workflow.
- Unverified catalog guidance: When you need AI agents to deeply analyze problems rather than just provide surface-level answers
When NOT to use qiushi-skill
- Unverified catalog guidance: Avoid if quick, heuristic-based decisions are preferred over thorough analysis
- Unverified catalog guidance: Not suitable when AI personality simulation is a primary requirement
- Unverified catalog guidance: If using non-political or non-propaganda related methodological tools might be misconstrued in your context
Explore
Sources
Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.
- GitHub stars (darkrishabh/agent-skills-eval) · observed Sep 20, 2026
- GitHub forks (darkrishabh/agent-skills-eval) · observed Sep 20, 2026
- Last push (darkrishabh/agent-skills-eval) · observed Aug 5, 2026
- License file (MIT) · observed Sep 20, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 11, 2026
- GitHub stars (HughYau/qiushi-skill) · observed Oct 25, 2026
- GitHub forks (HughYau/qiushi-skill) · observed Oct 25, 2026
- Last push (HughYau/qiushi-skill) · observed Oct 1, 2026
- License file (MIT) · observed Oct 25, 2026
- Decision facts (enrichment) · observed Jul 17, 2026
- Trust scan (lockfile / OSV) · observed Jul 15, 2026
GitHub stars on cards: agent-skills-eval 790 · qiushi-skill 3.8k (synced Sep 20, 2026).
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 recorded GitHub metadata and shared categories.
- When should I choose agent-skills-eval over qiushi-skill?
- For agent-skills-eval, compare these recorded points with qiushi-skill: 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; Unverified catalog guidance: 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?
- For qiushi-skill, compare these recorded points with agent-skills-eval: qiushi-skill is primarily JavaScript; agent-skills-eval is TypeScript; Tags unique to qiushi-skill: methodology, skills, workflow; Unverified catalog guidance: When you need AI agents to deeply analyze problems rather than just provide surface-level answers.
- When should I avoid agent-skills-eval?
- Unverified catalog guidance: 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. Unverified catalog guidance: 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?
- Unverified catalog guidance: Avoid if quick, heuristic-based decisions are preferred over thorough analysis Unverified catalog guidance: Not suitable when AI personality simulation is a primary requirement Unverified catalog guidance: 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 recorded GitHub stars (3,825 vs 790). Stars measure visibility, not whether either tool fits your constraints.
- Which licenses are recorded for agent-skills-eval and qiushi-skill?
- agent-skills-eval: MIT. qiushi-skill: MIT. Check each repository's current license and terms before use. Public GitHub hosting alone does not establish open-source licensing.
- Where can I find alternatives to agent-skills-eval or qiushi-skill?
- GraphCanon lists candidates at agent-skills-eval alternatives and qiushi-skill alternatives (agent-skills-eval markdown twin, qiushi-skill markdown twin). The discovery order uses stored relationship proposals and shared categories; it is not a verified replacement ranking.
- Is there a machine-readable version of this comparison?
- Yes. The markdown twin at this comparison 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; qiushi-skill trust report.