AC Fact Check
This skill should be used when the user asks to "fact check", "verify this", "is this true", "check the facts", "validate claims", "are these field names correct", "is this API still current", "驗證", "是真的嗎", "確認資訊正確", or when output contains version numbers, API references, model names, dates, or technical claims that could be outdated.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 58/100
- 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
- 40Consistency. Frontmatter name (Fact Check) differs from the folder (fact-check-verify)
- 60Tools and files. Uses tools (bash, web, git, python) that frontmatter does not declare
- 70Failures and branches. 4 branches
- 100Steps. 40 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2074 tokens
- 100Running it twice. Mutating operations check current state
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 337: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.