AC huoshan-qifu-knowledge-router
Route Huoshan and Qifu knowledge requests through the default Feishu Bitable catalog, preserve entry-document and child-document relationships, and return original catalog links. Use when the user explicitly names huoshan-qifu-knowledge-router or asks in Chinese or English to find, list, recommend, compare, navigate, or answer questions about 火山企服知识、知识库资料、入口文档、子文档、新人或实习生资料、部门介绍、Fornax、AIDP、LabelGPT、AI Coding, document metadata, document hierarchy, or source-grounded content.
Route Huoshan and Qifu knowledge requests through the default Feishu Bitable catalog, preserve entry-document and child-document relationships, and return…
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, 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 63/100
- 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. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 68 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2345 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
- high The skill tells the model to perform an irreversible action with no human approval
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 479: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 68 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.