AC prd-generator
专业级产品需求文档（PRD）生成器。自动生成包含 UML 用例模型、详细用例规格说明、数据字典、交互设计、UI 规范的完整 PRD。 Use when: 用户提到写PRD、写产品需求文档、产品设计、产品规划、新功能需求分析、用例分析、用例建模时触发。 NOT for: 已有完整需求文档的润色、代码生成、技术架构设计、数据分析报告。
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
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: 5. 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 57/100
- 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
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 796 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 166: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.
External checks
ClawHub: clean
This is a document-writing helper for PRDs, with no executable code or requests for credentials, local data, network access, persistence, or privileged actions.
LLM: benign (high) · VirusTotal: · 29 May 2026