Skill evaluation & testing

The top-rated launch-quality Skill evaluation & testing skill for AI agents is skill-scorer (grade A), followed by nat-evaluation and skillopt-sleep. Skillspace rates 510 Skill evaluation & testing skills; 111 are launch-quality.

Evals, test harnesses and quality checks for skills and prompts.

Launch-quality skills first, then by grade, then by our Skill Score, which adds judge reviews, test results, GitHub stars and adoption.

  1. skill-scorer A
  2. nat-evaluation B
  3. skillopt-sleep B
  4. octocode-skills B
  5. skill-lint B
  6. skill-governance-loop B
  7. skill-maintenance B
  8. reply-live-test B
  9. skill-verifier-candidates-v1 B
  10. skill-opt-v1 B
  11. skill-eval B
  12. scoring B
  13. finance-scenario-advisor B
  14. skillcheck B
  15. prompt-eval-builder B
  16. solo-skill-audit B
  17. demo-skill B
  18. agent-introspect B
  19. skill-reviewer C
  20. agent-qa-authoring C
  21. agent-qa-debug-fix C
  22. validate-skill C
  23. agent-qa-result-triage C
  24. Optimize C
  25. testing-skills-with-subagents C

Frequently asked questions

What is the best Skill evaluation & testing skill for AI agents?

The top-rated launch-quality Skill evaluation & testing skill for AI agents is skill-scorer (grade A), followed by nat-evaluation and skillopt-sleep. Skillspace rates 510 Skill evaluation & testing skills; 111 are launch-quality.

How does Skillspace rate Skill evaluation & testing skills?

Skillspace grades every Skill evaluation & testing skill from A to F with a published scoring engine that reads the skill's SKILL.md: architecture and maturity make the score, and a security scan can cap it. In crowded categories, a judge model also compares the strongest contenders side by side, and some skills are tested head-to-head on real tasks against other skills in the same category (including a deliberately weak one) and a no-skill baseline. Launch-quality skills are graded A to C with a clean safety verdict, and not excluded by a quality filter: the filters catch skills our model's safety screen flags for prompt injection, guardrail bypass, harmful content or credential exposure; test fixtures and attack benchmarks; skills written only for the repository they live in; templates and stubs; and near-duplicate variants and copies of other skills. Ratings were last updated on 24 September 2026; the full method is on the methodology page.

Are Skill evaluation & testing skills safe to install?

Of the 510 Skill evaluation & testing skills Skillspace rates, 443 passed its safety scan with no flag from its model, and 67 are flagged: 1 for review, 46 as risky, 14 as unsafe and 6 as test fixtures. Each skill's page shows its safety verdict. A pass is not a guarantee: the scan reads only the skill's SKILL.md, not the scripts or other files it ships, and looks for patterns such as piping a remote script into a shell, reading credentials or hiding actions from the user. Skills are third-party code that Skillspace indexes but does not host or endorse, so read a skill's source on GitHub before you install it.

Skillspace indexes and rates skills; it does not host or endorse them. Run third-party skills at your own risk.