Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →athola/skills-eval
Evaluate Claude skill quality through auditing.
Passed 20 of 21 test cases with the skill, and 3 of 21 without it.
and 25 more in the full report
19 fixed3 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.
What requirement must composite scores across all five dimensions meet according to the evaluation exit criteria?
| Checked | Without skill | With skill |
|---|---|---|
| Requires dimension scores to sum to 100 for each audited skill. | Missed | Passed |
The instructions your model reads when the skill loads.
abstract:skill-authoring)abstract:hooks-eval)abstract:rules-eval)This framework audits Claude skills against quality standards to improve performance and reduce token consumption. Automated tools analyze skill structure, measure context usage, and identify specific technical improvements. Run verification commands after each audit to confirm fixes work correctly.
The skills-auditor provides structural analysis, while the improvement-suggester ranks fixes by impact. Compliance is verified through the compliance-checker. Runtime efficiency is monitored by tool-performance-analyzer and token-usage-tracker.
Run a full audit of all skills or target a specific file to identify structural issues.
# Audit all skills
make audit-all
# Audit specific skill
make audit-skill TARGET=path/to/skill/SKILL.md
Use skill_analyzer.py for complexity checks and token_estimator.py to verify the context budget.
make analyze-skill TARGET=path/to/skill/SKILL.md
make estimate-tokens TARGET=path/to/skill/SKILL.md
Generate a prioritized plan and verify standards compliance using improvement_suggester.py and compliance_checker.py.
make improve-skill TARGET=path/to/skill/SKILL.md
make check-compliance TARGET=path/to/skill/SKILL.md
test cases passed, vs 3 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.