Back to Details

product-management

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Skill: Product management AI

Skill: 产品管理AI

Purpose

用途

Assist with core product management activities including writing product requirements documents (PRDs), analyzing feature requests, synthesizing user research, planning roadmaps, and communicating product decisions to stakeholders and engineering teams.
协助完成核心产品管理工作，包括撰写产品需求文档（PRDs）、分析功能需求、整合用户研究、规划路线图，以及向利益相关者和工程团队传达产品决策。

When to use this skill

何时使用本Skill

  • You need to write or update PRDs with clear requirements, success metrics, and technical considerations.
  • You're evaluating feature requests and need structured analysis of impact, effort, and priority.
  • You need to synthesize user research findings into actionable insights.
  • You're planning roadmaps and need to organize, prioritize, and communicate plans.
  • You need to communicate product decisions clearly to engineering, design, and business stakeholders.
  • You're doing competitive analysis or market research synthesis.
  • You need to track and analyze product metrics to inform decisions.
  • 你需要撰写或更新PRD，包含清晰的需求、成功指标和技术考量。
  • 你正在评估功能需求，需要对影响、工作量和优先级进行结构化分析。
  • 你需要将用户研究结果整合为可落地的洞察。
  • 你正在规划路线图，需要对计划进行整理、优先级排序和沟通。
  • 你需要向工程、设计和业务利益相关者清晰传达产品决策。
  • 你正在进行竞品分析或市场研究整合。
  • 你需要跟踪和分析产品指标以辅助决策。

Key capabilities

核心能力

Unlike point-solution PM tools:
  • Integrated with codebase: Can reference actual code, APIs, and technical constraints.
  • Context-aware: Understands your specific product, architecture, and technical debt.
  • Flexible templates: Adapt documentation to your organization's needs.
  • Version controlled: All artifacts live in git alongside code.
  • Collaborative: Works within existing dev workflows (PRs, issues, docs).
与单点PM工具不同：
  • 与代码库集成：可参考实际代码、API和技术限制。
  • 上下文感知：了解你的特定产品、架构和技术债务。
  • 灵活模板：可根据组织需求调整文档格式。
  • 版本控制：所有产出物与代码一同存储在Git中。
  • 协作性：可在现有开发工作流（PR、Issue、文档）内协作。

Inputs

输入信息

  • Product context: Current state, key stakeholders, strategic goals.
  • Feature requests: User feedback, business needs, or strategic initiatives.
  • Technical constraints: Known limitations, dependencies, or technical debt.
  • User research: Interview notes, survey results, analytics data.
  • Business goals: Metrics, OKRs, or success criteria to optimize for.
  • 产品上下文：当前状态、关键利益相关者、战略目标。
  • 功能需求：用户反馈、业务需求或战略举措。
  • 技术限制：已知局限、依赖关系或技术债务。
  • 用户研究：访谈记录、调研结果、分析数据。
  • 业务目标：需要优化的指标、OKRs或成功标准。

Out of scope

适用范围外场景

  • Making final product decisions (this is the PM's job; the skill assists).
  • Managing stakeholder relationships and politics.
  • Detailed UI/UX design work (use design tools and collaborate with designers).
  • Project management and sprint planning (use project management tools).
  • 做出最终产品决策（这是PM的职责；本Skill仅提供协助）。
  • 管理利益相关者关系和职场政治。
  • 详细UI/UX设计工作（使用设计工具并与设计师协作）。
  • 项目管理和迭代规划（使用项目管理工具）。

Conventions and best practices

规范与最佳实践

PRD structure

PRD结构

A good PRD should include:
  1. Problem statement: What user pain point or business need are we addressing?
  2. Goals and success metrics: What does success look like quantitatively?
  3. User stories and use cases: Who will use this and how?
  4. Requirements: Functional and non-functional requirements, prioritized.
  5. Technical considerations: Architecture implications, dependencies, constraints.
  6. Design and UX notes: Key interaction patterns or design requirements.
  7. Risks and mitigations: What could go wrong and how to address it.
  8. Launch plan: Rollout strategy, feature flags, monitoring.
  9. Open questions: What still needs to be decided or researched.
优质PRD应包含：
  1. 问题陈述：我们要解决的用户痛点或业务需求是什么？
  2. 目标与成功指标：量化的成功标准是什么？
  3. 用户故事与使用场景：谁会使用该功能，如何使用？
  4. 需求：按优先级排序的功能需求与非功能需求。
  5. 技术考量：架构影响、依赖关系、限制条件。
  6. 设计与UX说明：关键交互模式或设计要求。
  7. 风险与缓解方案：可能出现的问题及应对措施。
  8. 上线计划：发布策略、功能开关、监控方案。
  9. 待解决问题：仍需决策或研究的内容。

Feature prioritization

功能优先级排序

Use structured frameworks to evaluate features:
  • RICE: Reach × Impact × Confidence / Effort
  • ICE: Impact × Confidence × Ease
  • Value vs. Effort: 2×2 matrix plotting value against implementation cost
  • Kano Model: Categorize features into basic, performance, and delighters
使用结构化框架评估功能：
  • RICE：覆盖范围 × 影响 × 置信度 / 工作量
  • ICE：影响 × 置信度 × 实现难度
  • 价值vs工作量：以价值和实施成本为轴的2×2矩阵
  • Kano模型：将功能分为基础型、绩效型和兴奋型

User research synthesis

用户研究整合

When synthesizing research:
  1. Identify patterns: What themes emerge across participants?
  2. Quote verbatim: Include actual user quotes to illustrate points.
  3. Quantify when possible: "7 out of 10 participants said..."
  4. Segment findings: Different user types may have different needs.
  5. Connect to metrics: How do qualitative findings explain quantitative data?
整合研究结果时：
  1. 识别模式：参与者之间呈现出哪些共性主题？
  2. 引用原文：使用用户原话佐证观点。
  3. 尽可能量化：“10位参与者中有7位表示……”
  4. 细分结果：不同用户类型可能有不同需求。
  5. 关联指标：定性结果如何解释定量数据？

Roadmap planning

路线图规划

Effective roadmaps should:
  • Theme-based: Group work into strategic themes, not just feature lists.
  • Time-horizoned: Now / Next / Later or Quarterly structure.
  • Outcome-focused: Emphasize goals and outcomes, not just outputs.
  • Flexible: Leave room for learning and adjustment.
  • Communicated clearly: Different views for different audiences.
有效的路线图应：
  • 基于主题：将工作按战略主题分组，而非仅罗列功能。
  • 划分时间范围：采用“当前/近期/远期”或季度结构。
  • 聚焦成果：强调目标与成果，而非仅输出物。
  • 具备灵活性：预留学习和调整的空间。
  • 清晰传达：针对不同受众提供不同视图。

Required behavior

要求行为

  1. Understand context deeply: Review existing docs, code, and prior discussions before proposing changes.
  2. Ask clarifying questions: Don't assume; clarify ambiguous requirements or goals.
  3. Be specific and actionable: Avoid vague language; provide concrete, testable requirements.
  4. Consider tradeoffs: Explicitly discuss pros/cons of different approaches.
  5. Connect to strategy: Tie features and decisions back to higher-level goals.
  6. Involve stakeholders: Identify who needs to review or approve.
  7. Think through edge cases: Don't just focus on happy paths.
  8. Make it measurable: Propose concrete metrics to track success.
  1. 深度理解上下文：在提出修改建议前，先查阅现有文档、代码和过往讨论。
  2. 提出澄清问题：不做假设；对模糊的需求或目标进行澄清。
  3. 具体且可落地：避免模糊表述；提供具体、可测试的需求。
  4. 考虑权衡：明确讨论不同方案的优缺点。
  5. 关联战略：将功能和决策与更高层级的目标挂钩。
  6. 邀请利益相关者参与：确定需要审核或批准的人员。
  7. 考虑边缘情况：不要只关注常规路径。
  8. 可衡量：提出具体的成功指标跟踪方案。

Required artifacts

必备产出物

Depending on the task, generate:
  • PRD document: Comprehensive product requirements in markdown format.
  • Feature analysis: Structured evaluation of a feature request.
  • Research synthesis: Summary of user research findings with insights.
  • Roadmap document: Organized view of planned work with themes and timelines.
  • Decision document: Record of key product decisions and rationale.
  • Competitive analysis: Comparison of competitor features and approaches.
  • Metric definitions: Clear definitions of success metrics and how to measure them.
根据任务不同，生成以下产出物：
  • PRD文档：Markdown格式的全面产品需求说明。
  • 功能分析报告：对功能需求的结构化评估。
  • 研究整合报告：用户研究结果摘要及洞察。
  • 路线图文档：按主题和时间线组织的计划视图。
  • 决策文档：关键产品决策及理由记录。
  • 竞品分析报告：竞品功能和方案的对比。
  • 指标定义：成功指标的清晰定义及测量方法。

Implementation checklist

实施检查清单

Writing a PRD

撰写PRD

  • Understand the problem space and strategic context
  • Review related code, APIs, and technical constraints
  • Interview key stakeholders (engineering, design, business)
  • Research user needs and competitive landscape
  • Draft problem statement and goals
  • Define user stories and use cases
  • Specify functional and non-functional requirements
  • Document technical considerations and dependencies
  • Define success metrics and measurement approach
  • Identify risks and mitigation strategies
  • Plan rollout and launch approach
  • Review with stakeholders and iterate
  • 理解问题领域和战略上下文
  • 查阅相关代码、API和技术限制
  • 访谈关键利益相关者（工程、设计、业务）
  • 研究用户需求和竞品格局
  • 草拟问题陈述和目标
  • 定义用户故事和使用场景
  • 明确功能需求与非功能需求
  • 记录技术考量和依赖关系
  • 定义成功指标和测量方法
  • 识别风险和缓解策略
  • 规划发布和上线方案
  • 与利益相关者评审并迭代

Analyzing a feature request

分析功能需求

  • Clarify the user problem or business need
  • Identify target users and use cases
  • Estimate impact (users affected, business value)
  • Assess implementation effort and complexity
  • Identify dependencies and risks
  • Check alignment with product strategy
  • Compare against alternatives
  • Calculate prioritization score (RICE, ICE, etc.)
  • Make recommendation with clear reasoning
  • 明确用户问题或业务需求
  • 确定目标用户和使用场景
  • 估算影响（受影响用户、业务价值）
  • 评估实施工作量和复杂度
  • 识别依赖关系和风险
  • 检查与产品战略的对齐性
  • 对比替代方案
  • 计算优先级得分（RICE、ICE等）
  • 提供带有明确理由的建议

Synthesizing user research

整合用户研究

  • Review all research materials (transcripts, notes, data)
  • Identify key themes and patterns
  • Extract representative quotes
  • Segment findings by user type if relevant
  • Connect qualitative findings to quantitative data
  • Formulate insights and implications
  • Generate actionable recommendations
  • Prioritize recommendations by impact
  • 查阅所有研究材料（转录稿、笔记、数据）
  • 识别关键主题和模式
  • 提取代表性引用
  • 若相关，按用户类型细分结果
  • 将定性结果与定量数据关联
  • 形成洞察和影响分析
  • 生成可落地的建议
  • 按影响优先级排序建议

Planning a roadmap

规划路线图

  • Review strategic goals and OKRs
  • Collect input from stakeholders
  • Assess current state and technical debt
  • Group potential work into strategic themes
  • Prioritize themes and initiatives
  • Estimate sizing and dependencies
  • Organize into time horizons (Now/Next/Later)
  • Define success criteria for each initiative
  • Create views for different audiences
  • Review and socialize with stakeholders
  • 回顾战略目标和OKRs
  • 收集利益相关者的输入
  • 评估当前状态和技术债务
  • 将潜在工作按战略主题分组
  • 对主题和举措进行优先级排序
  • 估算规模和依赖关系
  • 按时间范围（当前/近期/远期）组织
  • 为每个举措定义成功标准
  • 为不同受众创建视图
  • 与利益相关者评审并沟通

Example workflows

示例工作流

Example 1: Writing a PRD for a new feature

示例1：为新功能撰写PRD

markdown
undefined
markdown
undefined

PRD: Advanced Search Functionality

PRD: Advanced Search Functionality

Problem Statement

Problem Statement

Users frequently report difficulty finding specific items in our catalog when they have multiple criteria (price range, location, category, features). Our current search only supports simple text queries, leading to:
  • High bounce rates on search results pages (65% bounce rate vs 32% site average)
  • Increased support tickets asking for search help (150/month)
  • Lost conversion opportunities (estimated $500K annual revenue impact)
Users frequently report difficulty finding specific items in our catalog when they have multiple criteria (price range, location, category, features). Our current search only supports simple text queries, leading to:
  • High bounce rates on search results pages (65% bounce rate vs 32% site average)
  • Increased support tickets asking for search help (150/month)
  • Lost conversion opportunities (estimated $500K annual revenue impact)

Goals and Success Metrics

Goals and Success Metrics

Primary Goal: Enable users to find relevant items quickly using multiple filters.
Success Metrics:
  • Reduce search result page bounce rate from 65% to <40%
  • Increase search-to-purchase conversion rate by 25%
  • Reduce search-related support tickets by 50%
  • 70% of users engage with at least one filter within 30 days
Primary Goal: Enable users to find relevant items quickly using multiple filters.
Success Metrics:
  • Reduce search result page bounce rate from 65% to <40%
  • Increase search-to-purchase conversion rate by 25%
  • Reduce search-related support tickets by 50%
  • 70% of users engage with at least one filter within 30 days

User Stories

User Stories

Must Have

Must Have

  1. As a buyer, I want to filter by price range so I can find items within my budget
  2. As a buyer, I want to filter by location so I can find items near me
  3. As a buyer, I want to filter by category so I can narrow down item types
  4. As a buyer, I want to combine multiple filters so I can find exactly what I need
  5. As a buyer, I want to see filter counts so I know how many items match before applying
  1. As a buyer, I want to filter by price range so I can find items within my budget
  2. As a buyer, I want to filter by location so I can find items near me
  3. As a buyer, I want to filter by category so I can narrow down item types
  4. As a buyer, I want to combine multiple filters so I can find exactly what I need
  5. As a buyer, I want to see filter counts so I know how many items match before applying

Should Have

Should Have

  1. As a buyer, I want to save my filter preferences so I don't have to reapply them
  2. As a buyer, I want to see suggested filters based on my search query
  3. As a buyer, I want to sort filtered results by relevance, price, or date
  1. As a buyer, I want to save my filter preferences so I don't have to reapply them
  2. As a buyer, I want to see suggested filters based on my search query
  3. As a buyer, I want to sort filtered results by relevance, price, or date

Nice to Have

Nice to Have

  1. As a buyer, I want to create saved searches that notify me of new matches
  2. As a buyer, I want to share a filtered search URL with others
undefined
  1. As a buyer, I want to create saved searches that notify me of new matches
  2. As a buyer, I want to share a filtered search URL with others
undefined

Example 2: Feature request analysis

示例2：功能需求分析

markdown
undefined
markdown
undefined

Feature Analysis: Dark Mode Support

Feature Analysis: Dark Mode Support

Request Summary

Request Summary

Source: User feedback (150+ requests in past 6 months), competitive pressure Description: Add dark mode theme option to web and mobile apps
Source: User feedback (150+ requests in past 6 months), competitive pressure Description: Add dark mode theme option to web and mobile apps

User Need

User Need

Users working in low-light environments report eye strain with current light-only theme. Power users (25% of DAU) spend 3+ hours/day in app and strongly prefer dark mode.
Users working in low-light environments report eye strain with current light-only theme. Power users (25% of DAU) spend 3+ hours/day in app and strongly prefer dark mode.

Prioritization Score

Prioritization Score

Using RICE framework:
  • Reach: 750K users = 750
  • Impact: 8/10 (high for target segment) = 0.8
  • Confidence: 85% = 0.85
  • Effort: 7 weeks = 7
RICE Score: (750 × 0.8 × 0.85) / 7 = 73.2
Using RICE framework:
  • Reach: 750K users = 750
  • Impact: 8/10 (high for target segment) = 0.8
  • Confidence: 85% = 0.85
  • Effort: 7 weeks = 7
RICE Score: (750 × 0.8 × 0.85) / 7 = 73.2

Recommendation

Recommendation

Proceed with Option 1 (Full Dark Mode)
Reasoning:
  • High impact for large user segment (45% of base)
  • Strong user demand and competitive pressure
  • Effort is reasonable relative to value
  • RICE score above our threshold (>50)
  • Aligns with product, technical, and business strategy
undefined
Proceed with Option 1 (Full Dark Mode)
Reasoning:
  • High impact for large user segment (45% of base)
  • Strong user demand and competitive pressure
  • Effort is reasonable relative to value
  • RICE score above our threshold (>50)
  • Aligns with product, technical, and business strategy
undefined

Common PM artifacts

常见PM产出物

PRD (Product Requirements Document)

PRD（产品需求文档）

Comprehensive specification of what to build and why. Include problem statement, goals, user stories, requirements, technical considerations, risks, and launch plan.
关于要构建什么及构建原因的全面说明。包含问题陈述、目标、用户故事、需求、技术考量、风险和上线计划。

Feature Brief

功能简报

Lighter-weight than PRD; quick summary of a feature idea with key details. Use for early-stage exploration before committing to full PRD.
比PRD更轻量化；对功能想法的快速摘要，包含关键细节。用于在投入撰写完整PRD前的早期探索阶段。

User Research Synthesis

用户研究整合报告

Summary of user research findings (interviews, surveys, usability tests) with patterns, insights, and recommendations.
用户研究结果（访谈、调研、可用性测试）的摘要，包含模式、洞察和建议。

Roadmap

路线图

Strategic plan of what to build over time. Organize by themes and time horizons; focus on outcomes not just outputs.
关于未来构建内容的战略计划。按主题和时间范围组织；聚焦成果而非仅输出物。

Decision Document

决策文档

Record of important product decisions, the options considered, the decision made, and the reasoning. Critical for institutional memory.
重要产品决策的记录，包括考虑的选项、做出的决策及理由。对机构记忆至关重要。

Launch Plan

上线计划

Detailed plan for rolling out a feature including phases, feature flags, metrics, monitoring, and rollback procedures.
功能发布的详细计划，包括阶段、功能开关、指标、监控和回滚流程。

Competitive Analysis

竞品分析

Comparison of competitors' features, approaches, and positioning. Inform product strategy and feature prioritization.
竞品功能、方案和定位的对比。为产品战略和功能优先级排序提供参考。

One-Pager

一页摘要

Executive summary of a product initiative. Use to communicate to leadership and get alignment.
产品举措的执行摘要。用于向领导层传达并达成共识。

Best practices for AI-assisted PM work

AI辅助PM工作的最佳实践

When using AI to write PRDs

使用AI撰写PRD时

  • Provide comprehensive context about the product, users, and technical constraints.
  • Review and edit generated content carefully; AI may miss nuances or make wrong assumptions.
  • Use AI for structure and first drafts; refine with human judgment and stakeholder input.
  • Validate technical details with engineering; don't assume AI knows your architecture.
  • 提供关于产品、用户和技术限制的全面上下文。
  • 仔细审核和编辑生成的内容；AI可能会忽略细节或做出错误假设。
  • 使用AI生成结构和初稿；结合人工判断和利益相关者输入进行优化。
  • 与工程团队验证技术细节；不要假设AI了解你的架构。

When using AI for feature analysis

使用AI进行功能分析时

  • Provide quantitative data when possible (usage numbers, customer feedback counts).
  • Use structured frameworks (RICE, ICE) to make analysis consistent and defensible.
  • Don't let AI make the final decision; use it to organize thinking and surface considerations.
  • Supplement AI analysis with qualitative stakeholder input and strategic context.
  • 尽可能提供定量数据（使用数据、客户反馈数量）。
  • 使用结构化框架（RICE、ICE）使分析一致且有说服力。
  • 不要让AI做出最终决策；用它来整理思路并梳理考量因素。
  • 用定性的利益相关者输入和战略上下文补充AI分析。

When using AI for research synthesis

使用AI整合用户研究时

  • Provide full transcripts or detailed notes for best results.
  • Ask AI to identify patterns but validate with your own reading of the data.
  • Use AI to extract quotes and organize themes; add your own interpretation and implications.
  • Don't let AI over-summarize; sometimes important details are in the nuances.
  • 提供完整的转录稿或详细笔记以获得最佳结果。
  • 让AI识别模式，但要通过自己阅读数据进行验证。
  • 使用AI提取引用并组织主题；添加自己的解读和影响分析。
  • 不要让AI过度总结；有时重要细节蕴含在细微之处。

Safety and escalation

安全与升级

  • Strategic decisions: AI should inform, not make, key product decisions. Involve human PMs and stakeholders.
  • User data: Don't feed PII or sensitive user data to AI without proper data handling procedures.
  • Technical feasibility: Always validate technical assumptions and effort estimates with engineering.
  • Competitive intelligence: Be cautious about including confidential competitive info in prompts.
  • Tone and voice: Review and adjust tone for your audience; AI may be too formal or informal.
  • 战略决策：AI仅提供参考，不做关键产品决策。需让人工PM和利益相关者参与。
  • 用户数据：在未遵循适当数据处理流程的情况下，不要将PII或敏感用户数据输入AI。
  • 技术可行性：始终与工程团队验证技术假设和工作量估算。
  • 竞品情报：在提示中包含机密竞品信息时需谨慎。
  • 语气和风格：根据受众审核和调整语气；AI可能过于正式或随意。

Integration with other skills

与其他Skill的集成

This skill can be combined with:
  • Data querying: To analyze product metrics and user behavior data.
  • AI data analyst: To perform deeper quantitative analysis for feature decisions.
  • Frontend UI integration: To implement features designed in PRDs.
  • Internal tools: To build PM tools like feature flag dashboards or metrics viewers.
本Skill可与以下Skill结合使用：
  • 数据查询：分析产品指标和用户行为数据。
  • AI数据分析师：为功能决策执行更深入的定量分析。
  • 前端UI集成：实现PRD中设计的功能。
  • 内部工具：构建PM工具，如功能开关仪表盘或指标查看器。