AB linkfox-skill-evaluator
Evaluate whether a skill is both safe to run and effective at its job. Use when the user wants to test, benchmark, grade, critique, audit, vet, or compare versions of a skill — phrases like "这个 skill 好不好"、"evaluate this skill"、"vet this skill"、"新版本比旧版本好吗"、"帮我测测这个 skill"、"这个 skill 安全吗"、"skill 有没有效果"、"skill 质量如何". Trigger whenever a user has a skill in hand and wants an objective read — on effectiveness, on safety, or both; the evaluation always covers both dimensions regardless of which the user asks about first. Works on any skill regardless of domain (writing, code generation, data extraction, workflows, domain-specialized skills, third-party community skills).
Evaluate whether a skill is both safe to run and effective at its job.
As a process B 67/100 · Nearly there — weak spots: failures and branches, 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: 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 67/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash, web, python, node) 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
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4088 tokens
- 100Steps. 113 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 19 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
- +4Description does not say when NOT to use the skill (false activations)
- -5TODO / placeholder text left in the skill
- -252 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 670: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 113 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.