Token导航 LogoToken导航

Agent Skill · 开发

product-taste-intuition(产品味道直觉)

product-taste-intuition 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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-taste-intuition 是开发类 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,按安装量在开发类的 21,746 个 Skill 里排第 1,531。

总安装 27,456周安装 1,054GitHub Stars 734下载 8,888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-taste-intuition(产品味道直觉)
来源仓库:https://github.com/refoundai/lenny-skills
仓库路径:skills/product-taste-intuition
安装命令:
npx skills add https://github.com/refoundai/lenny-skills --skill product-taste-intuition
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/refoundai/lenny-skills --skill product-taste-intuition

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

使用 10 位产品领导者的框架培养产品品味和直觉。

立足于核心原则:直觉作为假设的生成,品味作为通过暴露时间建立的可学习技能,以及对自己产品反应的刻意自我观察 指导用户识别判断中的差距,建议有针对性的练习活动,并知道何时相信直觉而不是数据 包括诊断问题,以揭示用户定期分析哪些产品、他们如何注意到设计质量以及他们如何解决直觉和指标之间的冲突 标记常见错误,例如将口味视为与生俱来、有限的产品接触以及在需要判断时过度依赖数据

来源仓库内路径:skills/product-taste-intuition

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/refoundai/lenny-skills --skill product-taste-i…;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-taste-intuition 怎么安装?

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

product-taste-intuition 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-taste-intuition 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-taste-intuition 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-taste-intuition 用的人多吗?

公开数据是累计安装 27,456 次,近一周安装 1,054 次,下载 8,888 次,GitHub 734 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-taste-intuition 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。
  • 需要处理开发类任务、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。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
product-taste-intuition

产品味道直觉 · 本页

27,456734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 Taste & Intuition

Help the user develop product taste and intuition using frameworks from 10 product leaders.

How to Help

When the user asks for help with product taste:

  1. Understand their current exposure - Ask about the products they use and analyze regularly
  2. Identify gaps in their intuition - Determine where their product judgment feels weakest
  3. Suggest deliberate practice - Recommend specific activities to build taste over time
  4. Help them trust their gut - Guide them on when to rely on intuition vs. data

Core Principles

Intuition is a hypothesis generator

Dylan Field: "I think intuition is like a hypothesis generator and you're constantly generating these hypotheses and others are generating hypotheses as well." Intuition isn't about being right - it's about generating good hypotheses quickly that you can then validate.

Taste is the differentiator in an AI world

Alex Komoroske: "In this cacophony, how do you stand out? You stand out by having good taste. I think taste is the most important thing." As AI makes production easier, taste becomes the critical differentiator that separates great products from "slop."

Taste is a developable skill

Guillermo Rauch: "Taste, sometimes I think we think of as this inaccessible thing that, 'Oh, that person was born with taste.' I see it as a skill that it can develop." Taste is built through "exposure hours" and deliberately analyzing the best products in the world, not innate talent.

Build taste through self-observation

Julie Zhuo: "The number one advice... is it's just really about observation and it's about curiosity and can start by first observing yourself." Build product sense by noticing your own reactions to products, then validating those observations qualitatively and quantitatively.

Be a voracious user of products

Kayvon Beykpour: "The best cheat codes for getting better at building products is just being a voracious user of products... There's just no replacement for that." Building great consumer products relies on "muscle memory" developed by using many products deeply.

Taste means knowing what to remove

Great taste isn't just about what to add - it's about knowing what to cut. The ability to simplify and focus is a core expression of product taste.

Questions to Help Users

  • "What products do you use daily that you think are exceptionally well-designed? What makes them great?"
  • "When was the last time you analyzed a competitor's product in detail? What did you learn?"
  • "When you use a new app, what do you notice first? What bothers you?"
  • "How often do you experiment with products outside your industry or domain?"
  • "When your intuition and data conflict, how do you decide what to do?"

Common Mistakes to Flag

  • Treating taste as innate - Believing some people just "have it" rather than developing it deliberately
  • Not using enough products - Limited exposure leading to limited intuition
  • Ignoring your own reactions - Not paying attention to what delights or frustrates you as a user
  • Over-relying on data - Never making decisions based on judgment when data is unavailable
  • Copying without understanding - Adopting patterns from successful products without understanding why they work

Deep Dive

For all 11 insights from 10 guests, see references/guest-insights.md

Related Skills

  • problem-definition
  • running-design-reviews
  • positioning-messaging

平台分布

Codex

39.13%
按下载量换算3,478

Claude

30.01%
按下载量换算2,667

Cursor

18.15%
按下载量换算1,613

Gemini CLI

9.18%
按下载量换算816

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