AC skill-test-skill
Tests and scores any Agent Skill against the official anthropics/skills specification. Use this skill when you need to check if a skill repository or SKILL.md file is compliant with the Agent Skills standard, audit skill quality, get a compliance score, or receive specific improvement suggestions. Trigger when users say things like "check my skill", "test this skill", "does my skill follow the spec", "score my skill", "review my SKILL.md", "is my skill correct", "检查我的skill", "测试这个skill", "这个skill符合规范吗", "给我的skill打分", or when they provide a path to a skill directory or SKILL.md file and want it reviewed.
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
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: 6. 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 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 8 branches
- 70Execution cost. Instruction body is 4558 tokens
- 85Steps. 40 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +3Description length 610: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 40 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.