AB ai-cs
Use when building or running a WeChat/WeCom online customer service agent for OpenClaw or Hermes that answers company product and service questions from a local llm-wiki knowledge base, politely redirects unrelated questions, and routes risky or unsupported cases to human support. 中文触发来自真实客户问题：多少钱、怎么用、能不能、支不支持、怎么安装、出错了、打不开、怎么退款、多久发货、有没有优惠、订单在哪、发票、售后、人工。
As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 355 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "title"
Process rating: all ten parameters 75/100
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 22 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 60Consistency. The Hermes dialect needs category and tags
- 100Tools and files. No external tools needed
- 100Steps. 108 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Execution cost. Instruction body is 3925 tokens
- 100Progress reporting. Reports progress
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 355: enough signal without eating the budget
- +4Structure: 26 headings
- +3Step-by-step instructions: 108 items
- +3Output format is stated explicitly
- +4Has examples (23 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.