BB blueprint
Requirements blueprint workflow for transforming vague task descriptions into high-quality, implementation-ready Spec + RFC documents. **Trigger conditions (trigger if ANY is met):** - User asks to "refine/complete/create requirements/spec/RFC" - User asks to "write/draft a specification or technical design" - User provides a task description and asks for requirement analysis or design proposal - User mentions "需求分析", "技术方案", "Spec", "RFC", "需求文档", "蓝图", "blueprint" - User says "帮我想想怎么实现", "这个需求怎么做", "帮我理一下思路", "画个蓝图" - User gives a vague task and wants to "分析一下怎么做", "帮我想想实现方案" - User mentions "功能设计", "技术评审", "方案讨论", "梳理一下", "想清楚再做" - User says "别急着写代码，先想想", "先做个设计", "写个技术方案" **Workflow:** Elicitation → Analysis → Specification → Technical Design → Validation → Implementation
As a process B 66/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7524 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 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
- 40Consistency. Frontmatter name (blueprint) differs from the folder (blueprint-spec)
- 70Execution cost. Instruction body is 7524 tokens
- 85Steps. 276 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 12 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 24 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
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +3Description length 788: enough signal without eating the budget
- +4Structure: 71 headings
- +3Step-by-step instructions: 276 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.