AB alibabacloud-qianwenai-support
Create, track, and manage QianWen support tickets from the conversation: submit a new ticket, check ticket status and engineer replies, follow up, close, and rate — so platform issues get resolved without leaving the chat. Triggers: "submit ticket", "create ticket", "list tickets", "view ticket", "reply ticket", "close ticket", "rate ticket", "transfer to human", "work order", "customer service", "human support", "open ticket", "check ticket", "cancel ticket", "evaluate ticket", "ticket list", "support request", "escalate to agent". Do NOT use for general model usage questions, API Key management, or billing inquiries — only when the user explicitly needs ticket operations.
Create, track, and manage QianWen support tickets from the conversation: submit a new ticket, check ticket status and engineer replies, follow up, close, and…
As a process B 75/100 · Nearly there — weak spots: running it twice, progress reporting
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: 11. 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 75/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 21 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4709 tokens
- 85Steps. 51 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 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 15 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
- +1No license
- +2Single-language instructions
- +5Description quotes 18 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 682: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 51 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 100.