AC yuque
语雀 (Yuque) 知识库管理。搜索、阅读、创建、编辑语雀文档，管理知识库和目录。 Use when: user mentions 语雀/Yuque, or wants to search/read/create/edit documents, manage knowledge bases, organize notes on Yuque, upload articles to Yuque.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
GeneratorInfrastructureWriting and documentstype and topics are labelled automatically from the skill text
How to improve
For the model run — optional
- 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: 17. 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 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
- 30Running it twice. 24 mutating operations with no state check
- 40Consistency. Frontmatter name (yuque) differs from the folder (yuque-knowledge-base)
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 26 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 1524 tokens
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)
- +3Output format is not stated: the model decides each time
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -31 of 13 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 198: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.
External checks
ClawHub: suspicious
This Yuque skill fits its stated purpose, but it stores an API token locally and can delete remote documents without clear safeguards.
LLM: suspicious (high) · VirusTotal: · 29 May 2026