Token导航 LogoToken导航

Agent Skill · 研究检索

hooked-model(钩模型)

hooked-model 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。

hooked-model 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 53,927。

总安装 519周安装 21GitHub Stars 8下载 163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:hooked-model(钩模型)
来源仓库:https://github.com/wdavidturner/product-skills
仓库路径:skills/hooked-model
安装命令:
npx skills add https://github.com/wdavidturner/product-skills --skill hooked-model
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/wdavidturner/product-skills --skill hooked-model

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。

hooked-model 用于查找、检索和筛选相关信息,支持关键词驱动的内容定位。适用于需要快速获取候选结果的研究型工作流场景。通过 npx 命令从 product-skills 仓库安装使用。安装前需确认是否涉及联网权限及外部命令执行能力。建议查阅原始文档了解具体实现机制与使用限制。

hooked-model 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/hooked-model

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/wdavidturner/product-skills --skill hooked-mod…;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

hooked-model 怎么安装?

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

hooked-model 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。

hooked-model 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。

hooked-model 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。

hooked-model 用的人多吗?

公开数据是累计安装 519 次,近一周安装 21 次,下载 163 次,GitHub 8 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。

hooked-model 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
hooked-model

钩模型 · 本页

5198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

The Hooked Model

What It Is

The Hooked Model is a framework for building products that create unprompted user engagement. The core insight: habit-forming products connect to internal triggers through a repeating cycle of trigger, action, reward, and investment.

When a product becomes a habit, users engage without external prompts. They don't need ads, emails, or notifications to come back. They return because the product has become their automatic response to an internal trigger like boredom, loneliness, uncertainty, or FOMO.

The key shift: Move from asking "How do we get users to open the app?" to asking "What internal trigger do we want to own, and how do we become the automatic response to it?"

When to Use It

Use the Hooked Model when you need to:

  • Design features that drive repeat engagement (not just one-time use)
  • Reduce dependency on external marketing to bring users back
  • Improve retention and decrease churn through habit formation
  • Understand why competitor products are so sticky (reverse-engineer their hooks)
  • Create ethical engagement that genuinely improves users' lives
  • Prioritize which features to build based on habit potential
  • Increase customer lifetime value through deeper product integration

When Not to Use It

  • The product is inherently infrequent (e.g., buying a house, annual insurance)
  • Users should consciously evaluate each decision (e.g., financial trading, medical diagnosis)
  • Habit formation would harm users rather than help them
  • You want to manipulate users into behaviors against their interests

Patterns

Detailed examples showing how to apply the Hooked Model correctly. Each pattern shows a common mistake and the correct approach.

Critical (get these wrong and you've wasted your time)

PatternWhat It Teaches
external-triggers-onlyProducts that rely only on notifications never form habits
action-too-hardIf the action requires effort, the habit loop breaks
predictable-rewardsPredictable rewards don't create craving; variable rewards do
no-investmentWithout investment, users have no stake in returning
wrong-internal-triggerTargeting the wrong emotion means the habit never sticks

High Impact

PatternWhat It Teaches
dark-patterns-vs-ethicalHooks should improve users' lives, not exploit them
rewards-of-the-tribeSocial validation is one of the most powerful variable rewards
rewards-of-the-huntThe search for resources and information drives engagement
rewards-of-the-selfPersonal mastery and completion drive intrinsic motivation
investment-loads-next-triggerThe best investments create reasons to come back
ability-before-motivationMake the action easier before amplifying motivation

Medium Impact

PatternWhat It Teaches
frequency-mattersHabits form faster with more frequent behaviors
vitamin-vs-painkillerThe best habit-forming products start as vitamins and become painkillers
manipulation-matrixUse the matrix to evaluate whether your hook is ethical

Deep Dives

Read only when you need extra detail.

  • references/hooked-model-playbook.md: Expanded framework detail, checklists, and examples.

Resources

Books:

  • *Hooked: How to Build Habit-Forming Products* by Nir Eyal — the complete framework
  • *Indistractable: How to Control Your Attention and Choose Your Life* by Nir Eyal — the flip side: helping users control habits

Concepts Referenced:

  • B.J. Fogg's Behavior Model (B = MAT)
  • Variable reinforcement from behavioral psychology
  • Carol Dweck's research on mindset and willpower

Related Frameworks:

  • Jobs-to-be-Done — Understanding why users "hire" products (complements the internal trigger analysis)
  • Fogg Behavior Model — The underlying model for the Action phase

From the Source: Nir Eyal on building ethical habit-forming products: "If it helps you become more productive, helps you live a happier, healthier life, that's wonderful... It's really about how do you get people to keep coming back to your product or service, not because they have to, but because they want to."

平台分布

Codex

35.65%
按下载量换算58

Claude

30.4%
按下载量换算50

Cursor

18.5%
按下载量换算30

Gemini CLI

10.17%
按下载量换算17

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