BC reqplan-v3
项目全生命周期管理引擎。用于系统化、流程化地执行软件工程任务。 **When to use**: - 用户说"帮我开发..."、"实现...功能"、"新增..."、"写个..." - 用户说"帮我分析..."、"审查..."、"看看这个设计..." - 用户说"出错了"、"报错了"、"修个Bug"、"修复..." - 用户说"帮我规划..."、"怎么做..."、"有什么方案" - 用户说"完善文档..."、"补充文档..."、"写文档..." - 用户说"重构..."、"优化架构..."、"技术债务..." - 用户说"测试..."、"写测试..."、"覆盖率..." - 用户输入 "/reqplan" 命令 - 任何涉及多步骤、需要设计-实现-验证的复杂任务 **When NOT to use**: - 单次简单问答（如"Python列表怎么排序"），不涉及多步骤任务规划 - 纯聊天对话，无具体任务目标（无开发/分析/修复意图） - 纯粹的信息查询（如"React 18 新增了什么"），不需要代码产出 - 用户仅要求查看/浏览代码，无需分析、修改或设计 - 需求极度模糊且用户拒绝澄清，无法确定具体任务边界 - 任务目标/范围已明确固定、只需单次代码修改、不涉及多阶段协作 **How it works**: 0. 确定项目路径（元任务走兜底规则，不以路径模糊为由跳过） 1. 读取接力棒（.agent/harness/_baton.md）获取当前状态 2. 按状态机自动执行：START→ANALYZE→CONFIRM→DESIGN→IMPLEMENT→VERIFY→JUDGE（无需用户逐一下令） 3. 每个阶段必须验证产物才能进入下一阶段 4. 所有产物通过文件传递，禁止口头传递 5. 用户必须在 CONFIRM 阶段确认后才能继续 6. 每步回复第一行必须输出"当前状态：[状态名]，下一步：[操作]" 7. 每步结束执行验证链检查（计数验证/列表验证/文件验证），防止虚假完成 **What it produces**: - 需求分析报告（_analysis.md） - 技术设计文档（_design.md） - 实现摘要（_implementation.md） - 验证报告（_verification.md） - 接力棒状态（_baton.md） - **质量审核报告（_quality_audit_analysis.md / _quality_audit_design.md / _quality_audit_implement.md / _quality_audit_verify.md / _quality_audit_judge.md）**
项目全生命周期管理引擎。用于系统化、流程化地执行软件工程任务。 When to use: - 用户说"帮我开发..."、"实现...功能"、"新增..."、"写个..." - 用户说"帮我分析..."、"审查..."、"看看这个设计..." - 用户说"出错了"、"报错了"、"修个Bug"、"修复..." -…
As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- 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: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1145 chars, limit 1024
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
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 4007 tokens
- 100Tools and files. No external tools needed
- 100Steps. 89 steps
- 100Consistency. Name and required fields are in place
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1144: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -239 emoji in the instructions: noise for the model
- +2Single-language instructions
- +5Description quotes 17 example trigger phrases
- +4Structure: 44 headings
- +3Step-by-step instructions: 89 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.