AB ecommerce-aftersales-reply
Generate reusable, policy-aligned customer service replies for e-commerce aftersales scenarios. Use when support staff need fast, compliant Chinese responses for (1) return/exchange requests, (2) logistics exception inquiries such as delayed delivery, no tracking updates, lost parcels, wrong routing, or failed delivery, and (3) aftersales compensation negotiation. Reuse this skill across repeated customer conversations to keep tone, structure, empathy, and brand-service standards consistent while adapting to the specific case details.
As a process B 74/100 · Nearly there — weak spots: when it triggers, 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: 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 74/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 12 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 74 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 7 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1641 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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 540: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 74 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.