BC fact-check
Fast, source-backed answer to a factual question — a technology, a term/noun, a date/version/value, or a "is it true that…" claim. Triage the question simple vs complex, fan out PARALLEL web searches, early-exit the moment the answer is corroborated, and return a citation-backed bottom-line answer within a hard time budget: simple ≤2 min, complex ≤5 min. Speed/efficiency is the defining goal. Use when the user wants a quick verified answer: "fact-check this", "quickly find out / look up X", "what is <tech/term>", "is it true that Y", "$fact-check". Do NOT use for: a thorough, exhaustive, multi-source RESEARCH REPORT (that is deep-research — this skill returns a bounded BLUF answer, not a report); subjective / opinion / recommendation questions with no factual answer ("best laptop for me"); domain deep-evaluations with their own skill (album-review for 乐评, hifi-review for audio gear); questions answerable from the open repo/context with no web lookup; creative, math, or coding tasks with no external fact to verify.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Shorten the description to 1024 characters.
- 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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1030 chars, limit 1024
Process rating: all ten parameters 52/100
- 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 (fast-fact-check)
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 64Steps. 3 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1005 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
- +3Description length 1029: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 6 headings
- +3Step-by-step instructions: 3 items
- +4Reference files are cited in the instructions (5 of 5)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.