AB skill-scorer
对任何 SKILL.md（或 skill 文件夹）进行质量评估和打分，基于行业最佳实践，生成 8 维度 100 分制的结构化质检报告，精准定位问题并提供可执行的优化建议。当用户要求评审、审计、评分、检测、质检任何 skill 时使用——哪怕只是说「这个 skill 写得怎么样？」也会触发。也支持：skill质检、skill评分、检测skill。 | Evaluate and score any SKILL.md (or skill folder) against industry best practices. Generates a structured quality report with a 100-point score across 8 dimensions, pinpoints issues, and provides actionable optimization suggestions. Use this skill whenever the user asks to review, audit, evaluate, grade, score, lint, or quality-check a skill — even if they just say 'is this skill any good?' or 'help me improve this skill'. Also triggers on: 'skill review', 'rate my skill'.
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, 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 · 1
✓ No critical or high findings
Medium and low: 1
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (web, python) 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
- 100Steps. 22 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1528 tokens
- 100Running it twice. No mutating operations
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 653: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.