BC reference-checker
Exhaustively verify English and Chinese manuscript references before journal submission. Use when checking whether references are real, accurate, complete, traceable, and formatted consistently. Uses DOI/PubMed/Crossref/publisher checks for English/international references, and uses Chinese-title-first CNKI/Wanfang/VIP/official-source checks for Chinese references. DOI is optional for Chinese references and must not be required unless the target citation style explicitly requires it.
As a process C 58/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5235 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 16 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 16 branches
- 70Execution cost. Instruction body is 5235 tokens
- 85Steps. 245 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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
- +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 488: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 245 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.