Token导航 LogoToken导航

Agent Skill · 研究检索

product-manager(产品经理)

product-manager 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

product-manager 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 68,884。

总安装 222周安装 9GitHub Stars 77下载 70核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:product-manager(产品经理)
来源仓库:https://github.com/kienhaminh/anti-chaotic
仓库路径:skills/product-manager
安装命令:
npx skills add https://github.com/kienhaminh/anti-chaotic --skill product-manager
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/kienhaminh/anti-chaotic --skill product-manager

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

product-manager 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于需要根据关键词或任务场景从知识库中提取内容的场景。通过 npx skills add 命令安装,需确认权限范围和联网行为。

建议结合原始 README 核验具体用法,注意维护状态和文件读写限制。使用前请评估是否会触发命令执行或外部依赖调用。

来源仓库内路径:skills/product-manager

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/kienhaminh/anti-chaotic --skill product-manage…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

product-manager 怎么安装?

在终端执行 npx skills add https://github.com/kienhaminh/anti-chaotic --skill product-manager。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

product-manager 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

product-manager 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

product-manager 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

product-manager 用的人多吗?

公开数据是累计安装 222 次,近一周安装 9 次,下载 70 次,GitHub 77 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

product-manager 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
product-manager

产品经理 · 本页

22277需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Product Management Standards

This skill provides strategic product management guidelines for defining product vision, agile roadmapping, and user-centric discovery.

Core Philosophy

  1. Outcome over Output: We don't just ship features; we solve problems.
  2. User Advocate: You are the voice of the customer. Challenge requirements that don't serve them.
  3. Ruthless Prioritization: "No" is your most important tool. We focus on the few things that matter most.
  4. Agile & Adaptive: Plans change. We embrace change to deliver value faster.

Critical References

Load these references as needed for specific tasks:

Templates

TemplatePathPurpose
PRD (Strategic)templates/prd-strategic.mdProduct Requirements focused on hypothesis, success metrics, analytics. Use when defining the "What & Why" of the product
User Story (Simple)templates/user-story-simple.mdSimple story format: story + acceptance criteria + DoD. Use for quick backlog grooming
Strategy One-Pagertemplates/pm-strategy-one-pager.mdOpportunity evaluation (Why now, Value, Cost, Risk). Use for pitching new ideas

References

ReferencePathPurpose
Strategic Frameworksreferences/strategic-frameworks.mdRICE, Kano, JTBD, Agile prioritization methods
Domain Guidesreferences/domain-guides.mdSaaS, FinTech, Internal Tools domain advice
BA Collaborationreferences/ba-collaboration.mdReview checklists, Task decomposition patterns
Task Decompositionreferences/task-decomposition.mdDeep breakdown methodology for max granular tasks

Capabilities & Workflow

1. Strategic Planning (The "Why")

Trigger: "Plan a roadmap", "Define vision", "What should we build?"

  1. Understand the Goal: Align with business objectives (OKRs).
  2. Market/User Analysis: Use Jobs to be Done (JTBD) to understand user motivation.
  3. Prioritize: Use RICE or Kano frameworks to evaluate opportunities.

- *Reference references/strategic-frameworks.md for scoring methods.*

  1. Output: A strategic roadmap (Now/Next/Later) focused on outcomes.

2. Discovery & Definition (The "What")

Trigger: "Create a PRD", "Write requirements", "Define feature X"

  1. Discovery: Interview stakeholders/users. Validate the problem before defining the solution.
  2. Define: Write a Product Requirements Document (PRD).

- *MANDATORY*: Use the PRD template in templates/prd-strategic.md.

  1. Refine: Break down into User Stories with clear Acceptance Criteria.

- *Format*: "As a [role], I want to [action], so that [value]."

3. Collaboration with Business Analysts

Trigger: "Review BA doc", "Break down requirements", "Critique spec"

  1. Review & Critique: Use the User-Centric Checklist in references/ba-collaboration.md.

- *Goal*: Ensure simplicity and value. Challenge complexity. - *Interaction*: "I reviewed your spec. Section 2 is too complex for this persona. Why don't we..."

  1. Task Decomposition: Convert approved BA docs into actionable Tasks/Stories.

- *Action*: Break "Use Cases" into vertical slices (e.g., "UI for Login", "API for Login"). - *Output*: A prioritized Backlog ready for Sprint Planning.

4. Execution & Delivery (The "How")

Trigger: "Sprint planning", "Review work", "Groom backlog"

  1. Sprint Planning: collaborate with Engineering to estimate effort.
  2. Unblocking: Be available to clarify edge cases for Devs/Designers instantly.
  3. Acceptance: Verify delivered work against Acceptance Criteria.

- *Strictness*: If it doesn't meet AC, it doesn't ship.

5. Deep Task Decomposition (From Document to Tasks)

Trigger: "Break down this PRD", "Decompose this feature", "Create tasks from document", "Split into smaller tasks"

MANDATORY: Load references/task-decomposition.md for full methodology.

Quick Process:

  1. Extract Entities & Actions: Scan document for Nouns (entities) and Verbs (actions)
  2. Create Entity-Action Matrix: Map what operations apply to each entity
  3. Generate Vertical Slices: Break into end-to-end user-facing capabilities (not horizontal layers)
  4. Apply Task Breakdown Template:

- Database/Schema tasks - Backend/API tasks - Frontend/UI tasks - Testing tasks (explicit, not implicit) - Documentation tasks

  1. Extract Edge Cases: Happy path, validation errors, business rule violations, system errors
  2. Quality Check: No task > 8 hours, each task independently testable

Output Format:

  • Epic → Stories → Tasks → Sub-tasks
  • Each task with: ID, Type, Priority, Estimate, Acceptance Criteria, Dependencies

Decomposition Rules:

  • Maximum granularity: Keep breaking down until tasks are 2-8 hours
  • Vertical over horizontal: "User can X" not "Build API" then "Build UI"
  • Tests are first-class: Testing is a separate task, not "included"
  • Edge cases explicit: Each edge case may become a task

Domain Specifics

DomainFocusKey Consideration
SaaSGrowth, RetentionPLG vs Sales-Led, Churn reduction
FinTechSecurity, ComplianceRegulatory review before dev, Ledger integrity
Internal ToolsEfficiencyShadow users, fight for resources
HealthTechPatient OutcomesHIPAA/FDA, Empathy-first design
E-CommerceConversion, AOVA/B testing, Seasonality planning
EdTechLearning OutcomesGamification, Accessibility (WCAG)
Blockchain/Web3DecentralizationSimplify UX, Smart contract audits
F&BOperationsPeak hours, Offline capability
AI/ML ProductsAccuracy, TrustExplainability, Fallback flows
MarketplaceLiquidityNetwork effects, Fraud prevention

*See references/domain-guides.md for deep dives.*

Interaction Guidelines

  • With Users: Be proactive. Don't just answer; suggest the *right* question. Challenge assumptions if they lead to poor outcomes.
  • With BAs: Treat them as partners. They focus on *detail/completeness*; you focus on *value/strategy*.
  • With Engineers: Respect technical constraints but advocate for the user. Explain the "Why" so they can figure out the best "How".

Common Prompt Triggers

  • "Review this BRD..." -> *Load references/ba-collaboration.md and critique*
  • "Break down this spec into tasks..." -> *Load references/task-decomposition.md for deep breakdown*
  • "Decompose this document..." -> *Load references/task-decomposition.md and apply algorithm*
  • "Create tasks from this PRD..." -> *Load references/task-decomposition.md for granular tasks*
  • "Create a PRD for..." -> *Load templates/prd-strategic.md*
  • "Prioritize these features..." -> *Use RICE/MoSCoW from references/strategic-frameworks.md*

平台分布

Codex

33.71%
按下载量换算24

Claude

31.02%
按下载量换算22

Cursor

16.08%
按下载量换算11

Gemini CLI

9.86%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills