AC docs-first
Consult official documentation BEFORE answering any question that involves a specific third-party library, framework, package, SDK, CLI tool, API, or program. Use this whenever the user asks how to use, configure, install, or call something (e.g. "how do I do X in vLLM", "what's the flag for Y", "does library Z support W", version/compatibility questions, error messages from a tool, API signatures, config schemas). Trigger this EVEN WHEN you feel confident you know the answer — training knowledge goes stale for fast-moving software, and confidence is exactly the failure mode this skill exists to catch. Search the official site and the official repository first, then answer grounded in what you found, with links and the version you relied on. Skip only for purely conceptual questions ("what is a hash map") that name no specific tool.
Consult official documentation BEFORE answering any question that involves a specific third-party library, framework, package, SDK, CLI tool, API, or program.
As a process C 58/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice
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: 2. 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 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (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
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1259 tokens
- low The response is described with custom markup (3 tags): a typed call is more reliable
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)
- +3Description length 844: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 6 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.