Token导航 LogoToken导航

Agent Skill · 研究检索

product-thinking(产品思维)

product-thinking 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-thinking 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,权限为只读;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 69,971。

总安装 214周安装 9GitHub Stars 公开资料未说明下载 75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-thinking(产品思维)
来源仓库:https://github.com/andybons/kit
仓库路径:skills/product-thinking
安装命令:
npx skills add https://github.com/andybons/kit --skill product-thinking
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/andybons/kit --skill product-thinking

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。

用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词、任务场景或来源线索快速定位候选结果。通过 npx skills add 命令从指定仓库安装,需结合原始 README 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-thinking 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/product-thinking

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/andybons/kit --skill product-thinking;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

product-thinking 怎么安装?

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

product-thinking 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-thinking 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

product-thinking 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-thinking 用的人多吗?

公开数据是累计安装 214 次,近一周安装 9 次,下载 75 次。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-thinking 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 只想先试试效果、不希望它改动本地文件的人。

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-thinking

产品思维 · 本页

214—只读未明确通过

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 Thinking Framework

Combines two complementary frameworks:

  • Jobs-to-be-Done (JTBD): Understand *what progress* customers seek
  • Minto Pyramid: Communicate product thinking *clearly and persuasively*

When to Use

TriggerMode
"Help me think through this product idea"Interactive Q&A
"Evaluate this feature concept"Interactive Q&A
"Write a PRD/brief/one-pager"Document Output
"Structure my product thinking"Either (ask user)
"Interview me about my product"Interactive Q&A

Core Workflow

Step 1: Establish Mode

Ask: "Would you like me to guide you through discovery questions, or produce a structured document?"

  • Interactive Q&A: Walk through JTBD discovery → synthesize → structure via Minto
  • Document Output: Gather inputs → produce pyramid-structured artifact

Step 2: JTBD Discovery

The goal is to uncover the job the customer is hiring the product to do.

The Job Statement Formula:

When [circumstance], I want to [progress/outcome], so I can [higher purpose].

Core Questions (ask 2-3 at a time, not all at once):

  1. Struggling Moment: "What's the specific moment when someone realizes they need this?"
  2. Current Workarounds: "What are people cobbling together today to make progress?"
  3. Functional Job: "What task are they literally trying to accomplish?"
  4. Emotional Job: "How do they want to feel during/after?"
  5. Social Job: "How do they want to be perceived by others?"
  6. Hiring Criteria: "What would make them 'fire' their current solution and 'hire' yours?"
  7. Anxieties: "What fears would prevent them from switching?"
  8. Circumstances: "When/where does this job arise? What's the context?"

See references/jtbd-framework.md for deeper guidance on JTBD theory.

Step 3: Synthesize the Job

After discovery, articulate:

JOB STATEMENT
━━━━━━━━━━━━━
When: [specific circumstance/trigger]
I want to: [desired progress]
So I can: [ultimate outcome/feeling]

FORCES OF PROGRESS
━━━━━━━━━━━━━━━━━━
Push (pain of current): [what's broken]
Pull (appeal of new): [what's attractive]
Anxiety (fear of new): [what holds them back]
Habit (comfort of current): [what keeps them stuck]

Step 4: Structure via Minto Pyramid

Organize all thinking top-down:

           ┌─────────────────┐
           │   ANSWER FIRST  │  ← Lead with the conclusion
           │   (So What?)    │
           └────────┬────────┘
                    │
     ┌──────────────┼──────────────┐
     │              │              │
┌────▼────┐   ┌────▼────┐   ┌────▼────┐
│ Key     │   │ Key     │   │ Key     │  ← 3-5 supporting arguments
│ Point 1 │   │ Point 2 │   │ Point 3 │
└────┬────┘   └────┬────┘   └────┬────┘
     │             │             │
  Evidence      Evidence      Evidence  ← Data, examples, research

SCQA Framework for framing the narrative:

  • Situation: Stable context everyone agrees on
  • Complication: What changed or went wrong
  • Question: The question this raises (implicit)
  • Answer: Your recommendation/insight

See references/minto-pyramid.md for communication patterns.

Document Output Templates

Product Brief (1-pager)

# [Product/Feature Name]

## Recommendation
[One sentence: what to build and why it matters]

## The Job to Be Done
When [circumstance], [user] wants to [progress], so they can [outcome].

## Why Now
- [Complication 1]: [evidence]
- [Complication 2]: [evidence]

## Solution Approach
1. [Key capability] → addresses [job dimension]
2. [Key capability] → addresses [job dimension]
3. [Key capability] → addresses [job dimension]

## Success Metrics
- [Leading indicator]: [target]
- [Lagging indicator]: [target]

## Key Risks & Mitigations
| Risk | Mitigation |
|------|------------|
| [Anxiety/obstacle] | [How addressed] |

Idea Evaluation Scorecard

# Evaluation: [Idea Name]

## JTBD Fit (1-5): __
- [ ] Clear struggling moment identified
- [ ] Job is recurring, not one-time
- [ ] Emotional/social dimensions understood
- [ ] Current alternatives are inadequate

## Market Forces (1-5): __
- [ ] Push from current pain is strong
- [ ] Pull toward solution is compelling
- [ ] Anxieties can be addressed
- [ ] Habits can be overcome

## Strategic Fit (1-5): __
- [ ] Aligns with company capabilities
- [ ] Defensible differentiation exists
- [ ] Viable business model apparent

## Verdict
[PURSUE / ITERATE / PASS]

## Reasoning (Pyramid Structure)
[Answer]: [One sentence verdict with "because..."]
- [Supporting point 1]
- [Supporting point 2]
- [Supporting point 3]

Anti-Patterns to Avoid

Anti-PatternWhy It FailsBetter Approach
Feature-first thinking"Build X" without job contextStart with struggling moment
Demographic segmentation"Millennials want..."Segment by job, not persona
Solution validation"Do you like this?""Tell me about last time you..."
Bottom-up docsBurying the leadAnswer first, then support
Correlation as causation"Users who do X also Y"Understand the *why* behind behavior

Interactive Session Flow

When in Q&A mode, follow this arc:

  1. Open: "Tell me about the problem you're trying to solve"
  2. Struggling Moment: "Walk me through a specific moment when this became painful"
  3. Current State: "What are people doing today to cope?"
  4. Dimensions: Probe functional, emotional, social jobs
  5. Forces: Map push, pull, anxiety, habit
  6. Synthesize: Reflect back the job statement for validation
  7. Structure: Organize insights into pyramid for next steps

Limit to 2-3 questions per turn. Reflect understanding before probing deeper.

References

  • references/jtbd-framework.md - Deep dive on Jobs-to-be-Done theory
  • references/minto-pyramid.md - Detailed Minto communication patterns
  • references/interview-guide.md - Full discovery interview script

平台分布

Codex

37.84%
按下载量换算28

Claude

29.29%
按下载量换算22

Cursor

20.21%
按下载量换算15

Gemini CLI

8.8%
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

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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