| name | skill-eval |
| version | 2.5.0 |
| description | Use when you want to test, measure, or compare skill effectiveness. Supports eval, compare, metrics, baseline capture, and regression detection. |
| trigger | manual |
| depends-on | [] |
| references | [] |
| user-invocable | true |
| allowed-tools | Read, Glob, Grep, Bash, Edit, Write |
| argument-hint | <mode> [skill-name] [--scenario <desc>] |
skill-eval
Evaluating skill: $ARGUMENTS
Modes
Parse the first argument to determine mode:
| Mode | Syntax | Purpose |
|---|
| eval | /skill-eval eval <skill-name> --scenario "<prompt>" | Test a skill against a known scenario |
| compare | /skill-eval compare <skill-name> --old <path> --new <path> --scenario "<prompt>" | A/B test two versions of a skill |
| metrics | /skill-eval metrics <skill-name> | Analyze a skill's evaluation criteria and pressure scenarios |
| baseline | /skill-eval baseline <skill-name> --scenario "<prompt>" | Capture baseline output for regression detection |
| regression | /skill-eval regression <skill-name> | Compare current skill against saved baseline |
Mode: eval
Test a skill against a scenario and grade the output against expectations.
Process
- Load the skill — Read
.claude/skills/<skill-name>/SKILL.md
- Load evaluation criteria — Read the skill's
## Evaluation Criteria section (if present in SKILL.md or SKILL_TEMPLATE.md)
- Define the scenario — Use the provided
--scenario or prompt the user for one
- Execute mentally — Walk through what Claude would do with this skill loaded, given the scenario prompt. Trace the expected decision points, tool calls, and outputs.
- Grade against criteria — For each evaluation criterion, determine PASS/FAIL with evidence
Output
## Skill Evaluation: <skill-name>
### Scenario
> <the test scenario>
| # | Criterion | Status | Evidence |
|---|-----------|--------|----------|
| 1 | [criterion text] | PASS/FAIL | [why] |
[ ] All hard gates would be respected
[ ] Red flags table would prevent shortcuts (if applicable)
Estimated SKILL.md tokens: X
References loaded: [list]
Total estimated tokens: X
[Summary of findings]