AF MT-Paotui-For-Client
美团跑腿下单助手，通过直接调用地址提单等接口实现用户跑腿需求。支持场景：① 帮取送（A地取件送到B地，支持品类：餐饮、文件、生鲜、蛋糕、鲜花、数码、服饰、快递、五金、汽配等）② 帮买（代购商品）③ 帮取号（餐厅取号、医院挂号、其他取号）④ 帮搬装/帮扔杂物/其他帮忙（骑手到指定地址帮忙）。触发词：跑腿、下跑腿单、美团跑腿、同城配送、取号、挂号、排号、排队、帮搬、帮买、帮扔、帮忙、扔垃圾、寄文件、叫骑手、骑手帮忙、送东西、帮取、配送、帮送、买东西。
As a process F 33/100 · Will not run — References files that are not bundled: {授权链接}
The same skill appears in 1 more place: ClawHub
How to improve
- The text references files that are not there: add them or drop the references.
For the model run — optional
- 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: 10. 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) - warning
missing-refreference to a missing file: {授权链接}
Process rating: all ten parameters 33/100
Will not run. References files that are not bundled: {授权链接}
- 0Tools and files. 1 referenced file(s) missing: {授权链接}
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 100Steps. 39 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1238 tokens
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
- -235 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 225: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.
External checks
ClawHub: suspicious
This skill matches its Meituan errand-ordering purpose, but it runs heavily obfuscated code with an under-disclosed background updater while handling account authorization, addresses, phone data, and real orders.
LLM: suspicious (high) · VirusTotal: · 28 May 2026