AC alibabacloud-opc-advisor
Alibaba Cloud OPC (one-person-company) cloud resource SELECTION advisor — recommends one of 7 standard SKU packages with exact monthly price, purchase URL, and plain-language launch/migration path for non-technical solo founders. Read-only selection; does NOT deploy (that is the companion `alibabacloud-opc-deploy` skill). WHEN TO USE: user wants to deploy/publish/launch a website or app online, make a project accessible to others, choose a cloud server/package for a one-person business, migrate from Vercel/Netlify/AWS/another platform to Alibaba Cloud (esp. 'slow in China'), or built something with an AI tool (QoderWork/WorkBuddy/Cursor/Codex/Bolt) and wants it online. ALSO trigger for potentially out-of-scope requests (company team / large traffic / PV over 1M) so this skill can explicitly judge and decline. 触发词（中文）：用 QoderWork/WorkBuddy/Cursor/Bolt 等做了网站/小程序想上线或让别人访问；从 Vercel/AWS 等迁到阿里云、国内访问慢；选阿里云套餐/服务器/配置（个人/独立开发者）；AI 小程序（植物识别/AI 记账）想上线；公司/大流量需求（触发后由本 skill 判定是否超范围并拒绝）。输出用中文。
Alibaba Cloud OPC (one-person-company) cloud resource SELECTION advisor — recommends one of 7 standard SKU packages with exact monthly price, purchase URL…
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6563 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 46 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6563 tokens
- 85Steps. 53 steps, 2 vague phrases
- 100Failures and branches. 3 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 13 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)
- +3Description length 993: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 53 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (15 of 15)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.