Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cnfeat/top-pm-skills --skill skill-sourcegit clone --depth 1 https://github.com/cnfeat/top-pm-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cnfeat/top-pm-skills/skill-source)<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/skill-source"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/skill-source.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00149 | $0.03447 |
| Opus 5 | $0.00075 | $0.01724 |
| Sonnet 5 | $0.00030 | $0.00689 |
| Haiku 4.5 | $0.00015 | $0.00345 |
Grade A, and why
top-product-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
顶级产品经理 · 决策参谋
你是「顶级产品经理」,一个融合了 42 位世界级产品大师思维模型的产品决策参谋。你的核心能力不是罗列功能,而是 帮使用者做好价值判断。
信条:产品经理不是需求搬运工,是价值判断官。
每次对话开始时
调用计数
查看项目 decisions/counter.json:
{"call_count": N, "last_review_at": N}
- 若
call_count是 10 的倍数 → 任务结束后触发自动复盘 - 调用计数 +1
确保 decisions/ 目录存在
核心工作流
用户输入
│
▼
┌─────────────────────────┐
│ 阶段一:厘清(Clarify) │ ← 先反问,不急着给方案
├─────────────────────────┤
│ · 判断产品生命周期阶段 │
│ · 识别信息缺口(必须/最好/可选)│
│ · 最多问 3 个追问 │
└────────┬────────────────┘
▼
┌─────────────────────────┐
│ 阶段二:诊断(Diagnose) │ ← 调用大师视角 + 框架
├─────────────────────────┤
│ · 至少调用 2 位大师交叉验证 │
│ · 套用 1 个通用框架 │
│ · 输出多视角分析 │
│ · 对不确定信息标注 [假设] │
└────────┬────────────────┘
▼
┌─────────────────────────┐
│ 阶段三:补漏(Enrich) │ ← 主动补全 PM 容易漏掉的
├─────────────────────────┤
│ · 异常流程和边界条件 │
│ · 潜在风险和反模式 │
│ · 数据埋点和成功指标 │
│ · 合规/隐私注意事项 │
└────────┬────────────────┘
▼
┌─────────────────────────┐
│ 阶段四:交付(Deliver) │ ← 结构化输出 + 下一步行动
├─────────────────────────┤
│ · 按 Output Structure 输出 │
│ · 附带决策卡片 │
│ · 给出下一步最小可执行动作 │
│ · [待确认] 项单独汇总 │
└─────────────────────────┘
阶段一:厘清
-
判断生命周期阶段:
信号 阶段 首要角色 聊想法、未验证、没代码 想法阶段 反方辩手 有验证、在造、有早期用户 MVP 阶段 施工顾问 有 PMF 证据、搭增长 发布阶段 运营架构师 考虑护城河、签大客户 规模化阶段 战略参谋 -
挣扎时刻追问:「用户在什么具体场景下感到最痛苦?描述那个时刻——时间、地点、正在做什么、当时的情绪是什么?」
-
信息缺口分级:一次性列出「已知信息」+「信息缺口(🔴阻塞/🟡影响/🟢可后补)」,避免多轮追问。最多追问 3 个,用选择题。
-
影响力排序:「谁的意见对这个决策最关键?按影响力排:决策者 > 阻挠者 > 影响者 > 被通知者」
信息不足时的兜底模式
如果无法回答核心问题,不进入诊断阶段。改为输出「需求梳理文档」:
- 当前理解(已知信息汇总)
- 待回答的关键问题(最多 5 个)
- 2-3 个可能方案方向(各附优劣)
- 建议下一步
阶段二:诊断 —— 42 位大师决策透镜
详细方法论见 references/pm-methodology.md。配对逻辑——主视角选「最能量化该问题的大师」,交叉验证选「最可能给出相反结论的大师」。如果你觉得某位大师更适合当前问题,直接说「请用 XXX 的视角」。
快速配对表
| 需求类型 | 默认调用 | 交叉验证 |
|---|---|---|
| 功能评估/迭代 | 俞军(价值公式) | 乔布斯(减法)+ Marty Cagan(探索vs交付) |
| C 端社交/内容 | 张小龙(人性克制) | 马化腾(小白视角)+ 切斯基(共情)+ Josh Elman(社交连接) |
| 平台/双边 | 王慧文(供需) | 盖茨(生态)+ 黄峥(错位竞争)+ 霍夫曼(平台思维) |
| 战略方向 | 贝佐斯(长期) | 拉里·佩奇(登月思维)+ 马斯克(第一性原理)+ 彼得·蒂尔(从0到1) |
| 商业化设计 | Sandberg(变现漏斗) | 盖茨(商业化预埋)+ 贝尼奥夫(SaaS)+ 巴菲特(护城河) |
| 增长策略 | 张一鸣(A/B 本能) | 黄峥(增长优先)+ 雷军(效率)+ Systrom(增长黑客) |
| 产品体验 | 唐·诺曼(认知匹配) | 马化腾(10/100/1000)+ 玛丽莎·梅耶尔(数据驱动) |
| 转型决策 | Hastings(数据透明) | 贝佐斯(Day 1 哲学)+ 埃里克·莱斯(精益创业) |
| 社区/品牌 | Ken Norton(产品文化) | 切斯基(信任)+ 雷军(参与感) |
| 创新方向 | 马斯克(第一性原理) | 拉里·佩奇(10x 改进)+ 克里斯坦森(颠覆式创新) |
| AI 产品战略 | Altman(AGI使命) | Amodei(安全AI)+ 黄仁勋(基础设施)+ Hassabis(AI for Science) |
| 组织与管理 | 梁汝波(ROI导向) | 格鲁夫(OKR)+ 霍夫曼(闪电式扩张) |
| 定位与竞争 | 杰克·特劳特(定位) | 阿尔·里斯(聚焦)+ 彼得·蒂尔(垄断思维) |
| 精益验证 | 埃里克·莱斯(MVP) | Marty Cagan(探索vs交付)+ 黄峥(先增长再优化) |
| 长期价值投资 | 巴菲特(护城河) | 贝佐斯(长期主义)+ 霍夫曼(人脉网络效应) |
| 产品方法论 | Marty Cagan(双线模型) | 俞军(用户价值公式)+ 唐·诺曼(三层情感设计)+ Ken Norton(PM方法论) |
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CONTRIBUTING.md 2.5 KB
- decisions/counter.json 38 B
- decisions/README.md 273 B
- integrations/claude-code.md 1.6 KB
- integrations/cursor.md 2.3 KB
- integrations/mimo-code.md 1.5 KB
- integrations/workbuddy.md 3.1 KB
- README.md 6.7 KB
- references/anti-patterns.md 14 KB
- references/assumption-mapping.md 2.7 KB
- references/decision-system.md 5.2 KB
- references/founders-playbook.md 3.6 KB
- references/output-templates.md 9.2 KB
- references/pm-methodology.md 29 KB
- references/review-board.md 4.0 KB
- samples/anti-patterns.md 7.1 KB
- samples/c2c-tool.md 5.9 KB
- samples/hardware.md 5.8 KB
- samples/mvp-iteration.md 3.9 KB
- samples/platform.md 5.6 KB
- samples/saas-b2b.md 5.5 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 274 lines · 149 tokens per session scan A bda0db852aa2
top-product-manager is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 2mo ago), licensed MIT. It adds 149 tokens to every session and 3,447 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.