staruhub/ClaudeSkills / skills/Geek-skills-product-manager
product-manager
Verified资深产品经理助手,提供 PRD/MRD/BRD 创作与评审、产品策略、留存增长、竞品分析、功能优先级,以及 grill-me-to-doc 逐轮访谈。用户要求“逐个问我”“先把需求问清楚”“grill me”“把想法变成产品文档”时进入 grill-me-to-doc:先读仓库证据,每轮只问一个决策,给推荐答案与理由,记录决策和未决项,支持 resume,产出结构化 PRODUCT-DOC;文档完成且用户批准前硬停止,任何时候都不写实现代码。即使未提“产品”,讨论 App 功能、增长或商业模式也应触发。不用于:单纯代码实现、系统架构深设(用 solution-architect)、需多源引用的市场调研(用 deep-research)、纯营销文案。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.4 KB |
| evals/routing-evals.json | config | 2.1 KB |
| references/GRILL-ME-TO-DOC.md | markdown | 6.0 KB |
| references/PM-BEST-PRACTICES.md | markdown | 16.7 KB |
| references/PRD-TEMPLATE.md | markdown | 11.6 KB |
| references/PRD-WRITING-GUIDE.md | markdown | 13.0 KB |
| references/PRODUCT-DOC-TEMPLATE.md | markdown | 1.6 KB |
| references/REVIEW-CHECKLIST.md | markdown | 12.8 KB |
| schemas/grill-state.schema.json | config | 5.0 KB |
| scripts/validate_grill_session.py | script | 12.3 KB |
evals/routing-evals.json
View on GitHub[
{
"id": "pm-01",
"prompt": "帮我写一份社区团购小程序的PRD,目标用户是小区宝妈。",
"should_trigger": true,
"reason": "explicit PRD creation"
},
{
"id": "pm-02",
"prompt": "我们产品次留只有20%,帮我诊断下问题出在哪。",
"should_trigger": true,
"reason": "场景触发:留存诊断,未出现 PRD/需求文档关键词"
},
{
"id": "pm-03",
"prompt": "帮我评审这份 PRD 的需求优先级排得对不对。",
"should_trigger": true,
"reason": "PRD review; 镜像 kq-05(keqian 负例的移交目标)"
},
{
"id": "pm-04",
"prompt": "带我用 AI 把这个产品从需求文档一路开发到测试全部通过。",
"should_trigger": false,
"route_to": "keqian-method",
"reason": "dev methodology execution, not product management"
},
{
"id": "pm-05",
"prompt": "帮我调研在线教育赛道的竞品格局,要有引用来源和局限性。",
"should_trigger": false,
"route_to": "deep-research",
"reason": "cited multi-source research artifact"
},
{
"id": "pm-06",
"prompt": "把这个功能的后端接口实现一下。",
"should_trigger": false,
"route_to": "none",
"reason": "code implementation, plain dev task"
},
{
"id": "pm-07",
"prompt": "设计一个推荐系统功能,顺便给下算法和技术选型建议。",
"should_trigger": true,
"boundary": true,
"reason": "两可:功能设计归本 skill,深度技术选型归 solution-architect;倾向本 skill 主导、选型部分声明移交"
},
{
"id": "pm-08",
"prompt": "别急着写代码,先读一下仓库,然后每次只问我一个问题,把这个模糊想法 grill 成产品文档。",
"should_trigger": true,
"expected_mode": "grill-me-to-doc",
"reason": "明确要求证据优先、单问题访谈和文档产出"
},
{
"id": "pm-09",
"prompt": "继续昨天没问完的产品访谈,从保存的状态接着来,不要重问。",
"should_trigger": true,
"expected_mode": "grill-me-to-doc",
"reason": "恢复 grill-me-to-doc 会话"
}
]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |