AA CartPilot
Checkout-path optimization skill for mainland China shopping and local-delivery scenarios that decides whether to split orders, which coupons or threshold discounts are worth using, whether to favor the lowest total price, the smoothest checkout, or the fastest arrival, and outputs the optimal ordering path across Taobao, Tmall, JD, PDD, VIPSHOP, Meituan, elm, and similar platforms.
As a process A 82/100 · Runs to the end — weak spots: 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug"
Process rating: all ten parameters 82/100
- 30Running it twice. 10 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 7 branches
- 100Tools and files. No external tools needed
- 100Steps. 204 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3005 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 14 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
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 385: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 204 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.