AC skill-eval
Skill evaluation framework. Use when: testing trigger rate, quality compare (with/without skill), or model comparison. Runs via sessions_spawn + sessions_history. Trigger words: evaluate skill, benchmark, trigger rate, A/B compare. NOT for: debugging conversations, general testing unrelated to skill evaluation.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 32. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (skill-eval) differs from the folder (openclaw-skill-eval)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 22 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 2197 tokens
- low 14 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -37 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 312: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.