Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →notque/agent-evaluation
Evaluate agents and skills for quality and standards compliance.
Passed 12 of 17 test cases with the skill, and 8 of 17 without it.
and 4 more in the full report
7 fixed9 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
An agent scored 62 out of 90 on its deterministic structural precheck script. What letter grade boundary corresponds to this percentage score?
| Checked | Without skill | With skill |
|---|---|---|
| Assigns a letter grade of C for a percentage score in the 60-74 percentage range. | Missed | Passed |
The instructions your model reads when the skill loads.
Evidence-based quality assessment for agents and skills. The deterministic scorer supplies a 90-point structural precheck; qualitative review covers usefulness and behavior without inventing extra points. Every qualitative finding must cite a file path and line number.
| Signal | Load These Files | Why |
|---|---|---|
| evaluating an entire agent/skill collection | batch-evaluation.md | Loads detailed guidance from batch-evaluation.md. |
| diagnosing recurring structural and content issues | common-issues.md | Loads detailed guidance from common-issues.md. |
| writing single-item or collection evaluation reports | report-templates.md | Loads detailed guidance from report-templates.md. |
| interpreting deterministic scores, JSON keys, or grade boundaries | scoring-rubric.md | Exact contract implemented by score-component.py |
Goal: Determine what to evaluate and confirm targets exist.
Read the repository CLAUDE.md first to understand current standards before evaluating anything. Only evaluate what was explicitly requested — do not speculatively analyze additional agents or skills.
# List all agents
ls agents/*.md | wc -l
# List all skills
ls -d skills/*/ | wc -l
# Verify specific target
ls agents/{name}.md
ls -la skills/{name}/
Gate: All targets confirmed to exist on disk. Proceed only when gate passes.
Goal: Check that required components exist and are well-formed.
Score every rubric category — never skip a category even if it "looks fine." Parse each required field explicitly rather than eyeballing YAML. Record PASS/FAIL with the line number for each check.
test cases passed, vs 8 / 17 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.