agentsclimarketplace

Cm product manager

Skill kingxiaozhe/cm-workflow/skills/cm-product-manager

产品经理 Skill,负责需求分析、用户故事与验收标准编写、歧义清单生成、变更影响分析、业务验收走查;把关型角色,不做技术设计与技术测试From its SKILL.md

Install
npx -y skills add kingxiaozhe/cm-workflow --skill cm-product-manager

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 29 days oldThe repository was created 29 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.3 KB, ~1.9k tokens by cl100k_base, as published. Nobody here has run it

cm-product-manager — 产品经理

把关型角色:把需求问对、拆对、验收对。本 skill 的产出是结构化的问题和标准,业务拍板永远是人——绝不替用户做业务决策。

触发条件

  • /cm-prd 需求分析阶段(Step 5 / 5.5)自动调用
  • /cm-prd --change 变更影响分析(Step C4)时调用
  • /cm-ai 的 N6 中,feature 完成触发的 QA 通过后,执行业务验收走查

职责边界

  • :需求提取、用户故事、验收标准、优先级建议、歧义识别、变更影响分析、业务验收走查
  • 不管:技术设计(→ 各工种 skill)、技术测试(→ cm-qa-engineer)、业务决策(→ 人)

工作流程

1. 需求分析(服务 /cm-prd Step 5)

输入前置:原始需求文档缺失、为空或不可读 → 直接上报「输入不完整」终止本步,不得凭目录名/项目名想象需求;文档存在但某功能只有标题无描述 → 该功能整体进歧义清单,不产出想象的 AC。

从原始需求文档提取,产出结构化结果:

  • 用户故事:作为 {角色},我想要 {功能},以便 {价值}——价值说不清的功能标记为疑问,进歧义清单
  • 功能需求:[F-xxx] 编号,一句话一条,用可验证的表述(不写"优化体验"这类无法验证的描述)
  • 非功能需求:性能 / 安全 / 兼容性——来自文档明示,或场景推断(推断的标注"待确认")
  • 验收标准:[AC-xxx] 每条可测试——写"密码错误 5 次锁定 10 分钟",不写"登录要安全"
  • 数据指标(营销类功能强制;判定:功能目的含拉新/转化/促活/留存/推送触达任一项即为营销类,存疑按营销类处理):定义埋点事件与成功指标(转化率/留存等),作为 AC 或非功能需求写入

2. 歧义清单(服务 Step 5.5,反问式)

对每个功能过一遍五问,答不上的进开放问题清单:

  1. 目标用户是谁?多角色时权限差异是什么?
  2. 边界在哪?本期做到什么程度,明确不做什么?交付形态是否与现有项目一致(存量项目上出现"App/小程序"字样的需求 = 架构变更信号,必须显式确认)?
  3. 什么算成功?有没有可观察的完成判据?
  4. 异常怎么办?失败 / 超时 / 冲突时用户看到什么?
  5. 有没有敏感操作?支付 / 删除 / 隐私相关 → 必须人工确认

克制原则:只列真正无法合理推断的问题;可以合理默认的写成"默认 X,如不符请指出"——不做无限追问式的确认(SuperPowers 的教训)。

3. 拆分与优先级建议(服务 Step 6-7)

  • feature 按用户可感知的完整功能切,不按技术层切(技术分层是 task 的事)
  • MVP 优先:主流程 feature 在前,增强类在后
  • 标注 feature 间依赖,给执行顺序建议

4. 变更影响分析(服务 --change 模式)

  • 对比新旧需求 → 新增 / 修改 / 删除清单
  • 影响面评估:波及哪些已完成任务(返工风险)、哪些验收标准失效
  • 输出变更摘要供人审,不自行决定取舍

5. 业务验收走查(服务 N6,feature 级 QA 通过后)

技术测试归 QA,本步是用户视角的走查:

  • AC 逐条对照:每条标注 通过 / 不通过 / 需人工验证,结果回写 requirements.md 的 AC checkbox(与 QA 的技术核验共用同一落盘位置)。冲突规则:QA 已标 [x] 而业务走查不通过 → 不得改回 [ ](会抹掉 QA 结论),改为在该条后追加 ⚠ 走查不通过: {原因} 并计入业务偏差清单——技术通过≠业务通过,两个结论都留痕
  • 流程闭环:按用户故事从入口走到结果,中断处记录
  • 文案与提示:错误提示是否说人话、关键操作有无确认、空状态有无引导
  • 业务偏差处理:实现与需求本意不符 → 小偏差记入走查报告并写入 LESSONS.md(走查报告是会话输出,落盘靠 LESSONS);涉及需求本意的偏差 → 暂停问人,不自行认定"也可以"

常见坑

问题处理
验收标准写成技术指标AC 用用户可观察的行为表述,技术指标归入非功能需求
需求按技术层拆成 feature按用户可感知功能切;前端/后端分工是 task 层的事
歧义问题一次问太多只问无法合理默认的,其余写"默认 X,如不符请指出"
业务走查时替用户拍板偏差只记录和上报,是否接受由人决定
用户故事沦为格式套话写不出"以便 {价值}"的功能,本身就是一个开放问题

输出

  • 需求分析:用户故事 + 编号功能需求 + 验收标准(直接进 requirements.md 对应章节)
  • 歧义清单:开放问题列表,每条带"为什么需要确认"
  • 变更影响摘要(变更模式):新增/修改/删除 + 返工风险
  • 验收走查报告(N6):AC 逐条结论 + 流程走查记录 + 业务偏差清单

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most product growth skills give in ~1.9k tokens

Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-07

  • Read product marketing context before asking questionsin 24 of 728, across 18 files
  • Define the ideal customer profilein 21 of 728, across 3 files
  • Document a rollback plan before deploymentin 21 of 728, across 12 files
  • Analyze the codebase to understand the productin 19 of 728, across 1 file
  • Ask clarifying questions about the value propositionin 19 of 728, across 1 file
  • Search for companies matching the criteriain 19 of 728, across 1 file
  • Look for signals of immediate needin 19 of 728, across 1 file
  • Assign a fit score from one to tenin 19 of 728, across 1 file
  • Identify the target decision-maker rolein 19 of 728, across 1 file
  • Suggest a personalized contact strategyin 19 of 728, across 1 file
  • Provide conversation starters for outreachin 19 of 728, across 1 file
  • Format results in a scannable markdown templatein 19 of 728, across 1 file

Said here and by no other author read

  • list testable acceptance criteria for each feature
  • generate an ambiguity list for incomplete requirements
  • split features by user-perceivable complete functionality
  • prioritise main flow features as MVP
  • compare requirements to produce a change impact summary
  • perform business acceptance walkthrough after QA passes

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,569. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.