AC skill-eval-preflight
Validate OpenClaw skills during authoring. Use when creating, revising, or preparing a skill for release and you need to scaffold `evals/` files, check readiness for a first eval pass, review whether the frontmatter description has clear trigger coverage, or generate static comparison artifacts before deeper runtime evaluation.
As a process C 60/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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: 8. 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 60/100
- 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
- 20When it triggers. No condition that starts the skill
- 65Failures and branches. 3 branches
- 100Tools and files. No external tools needed
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1294 tokens
- 100Running it twice. Mutating operations check current state
- low 13 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 329: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.