AB product-4a-architecture
基于产品需求，先生成一张完整的 4A 分层主图，再采用苏格拉底追问法逐步澄清业务架构、应用架构、数据架构与技术架构，最终输出 1 张 4A 总览分层主图、4 张分层架构图以及相关文档，并结合外部权威资料校验增强质量。所有架构图默认输出为可导入 draw.io 的 XML 代码块。Use when the user asks to 梳理产品架构、业务架构、应用架构、数据架构、技术架构，或希望按“埃森哲 4A / 四横五纵”思路，从 0 到 1 访谈式产出结构化架构蓝图，并希望以 draw.io XML 形式沉淀完整的分层架构图和配套文档。
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, consistency, 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: 8. 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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (product-4a-architecture) differs from the folder (4architecher)
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 117 steps
- 100Execution cost. Instruction body is 1162 tokens
- 100Running it twice. No mutating operations
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 271: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 117 items
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.