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 55,572。

总安装 474周安装 19GitHub Stars 239下载 154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/flpbalada/my-opencode-config
仓库路径:skills/hooked-model
安装命令:
npx skills add https://github.com/flpbalada/my-opencode-config --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/flpbalada/my-opencode-config --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。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 GitHub 仓库安装并使用。

安装前需确认权限范围、维护状态,注意是否触发联网、命令执行或文件读写。建议结合原始 README 和仓库内容核验具体用法和功能边界。

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/flpbalada/my-opencode-config --skill hooked-mo…;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

hooked-model 怎么安装?

在终端执行 npx skills add https://github.com/flpbalada/my-opencode-config --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。

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 474 次,近一周安装 19 次,下载 154 次,GitHub 239 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。

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
hooked-model

钩模型 · 本页

474239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

Hooked Model - Building Habit-Forming Products

The Hooked Model is a four-phase framework by Nir Eyal for creating products that form user habits. A habit is formed when users engage with a product repeatedly without conscious thought, driven by internal triggers rather than external marketing.

When to Use This Skill

  • Designing user engagement loops
  • Improving product retention metrics
  • Planning notification and re-engagement strategies
  • Building features that create lasting habits
  • Evaluating competitor engagement mechanisms
  • Auditing ethical implications of engagement design

Core Concepts

The Hook Cycle

    +-----------------+
    |                 |
    v                 |
 TRIGGER             |
 (Internal/External) |
    |                 |
    v                 |
 ACTION              |
 (Simple behavior)   |
    |                 |
    v                 |
 VARIABLE REWARD     |
 (Unpredictable)     |
    |                 |
    v                 |
 INVESTMENT          |
 (User effort)-------+

Phase 1: Trigger

External Triggers (initial hooks):

  • Push notifications
  • Email reminders
  • Advertising
  • Word of mouth
  • Social media mentions

Internal Triggers (goal state):

  • Boredom → Open TikTok
  • Loneliness → Check Instagram
  • Uncertainty → Google it
  • FOMO → Check Slack

Phase 2: Action

The simplest behavior in anticipation of reward.

Fogg Behavior Model alignment:

B = MAT (Behavior = Motivation + Ability + Trigger)

For habit formation:
- Motivation: Must exist (desire for reward)
- Ability: Must be HIGH (action must be easy)
- Trigger: Must be present
ProductTriggerSimplest Action
TwitterBoredomScroll feed
GoogleQuestionType query
InstagramFOMOOpen app
SlackAnxietyCheck messages

Phase 3: Variable Reward

Three types of variable rewards:

TypeDescriptionExample
TribeSocial validationLikes, comments, follows
HuntMaterial resourcesSearch results, deals, information
SelfPersonal achievementCompleting tasks, mastery, progress

Why "Variable"? Predictable rewards lose power. Slot machines use variable rewards - you never know which pull wins. Social feeds use the same psychology.

Phase 4: Investment

User puts something into the product that:

  1. Improves the product for them
  2. Increases likelihood of return
  3. Creates switching costs
Investment TypeExampleLock-in Effect
DataPreferences, historyPersonalization improves
ContentPosts, uploadsSocial capital
FollowersAudience builtNetwork effects
LearningSkills developedCompetency
ReputationReviews, karmaIdentity

Analysis Framework

Step 1: Map Current Hook

Your Product's Hook:

TRIGGER
External: _____________________
Internal (goal): _______________

ACTION
What's the simplest action? _______________
How many steps/taps? _______________

VARIABLE REWARD
Type: [ ] Tribe  [ ] Hunt  [ ] Self
What's unpredictable? _______________

INVESTMENT
What do users put in? _______________
How does it improve experience? _______________

Step 2: Identify Weak Links

Rate each phase (1-5):

PhaseScoreImprovement Needed
Trigger strength[/5]
Action simplicity[/5]
Reward variability[/5]
Investment depth[/5]

Step 3: Design Improvements

Focus on the weakest phase first. A hook is only as strong as its weakest link.

Output Template

## Hook Analysis

**Product:** [Name] **Date:** [Date] **Goal:** [Habit to form]

### Current Hook Cycle

**Trigger:**

- External: [Current external triggers]
- Internal target: [Emotion/situation → product]

**Action:**

- Current: [Steps to engage]
- Friction points: [Obstacles]

**Variable Reward:**

- Type: [Tribe/Hunt/Self]
- Variability source: [What changes]

**Investment:**

- Current: [What users contribute]
- Lock-in created: [Switching cost]

### Weakness Assessment

| Phase      | Score (1-5) | Issue |
| ---------- | ----------- | ----- |
| Trigger    |             |       |
| Action     |             |       |
| Reward     |             |       |
| Investment |             |       |

### Improvement Plan

1. **Trigger improvement:** [Specific change]
2. **Action simplification:** [Reduce steps to X]
3. **Reward enhancement:** [Add variability via]
4. **Investment deepening:** [New investment type]

### Ethical Check

- [ ] Product genuinely improves user's life
- [ ] User would recommend to friends
- [ ] We'd be comfortable if usage was public
- [ ] No dark patterns employed

Real-World Examples

Example 1: Instagram

PhaseImplementation
TriggerExternal: notifications. Internal: boredom, FOMO
ActionOpen app, scroll (one tap)
Variable RewardNew posts (Hunt), likes/comments (Tribe)
InvestmentFollowers, posts, profile, DM history

Example 2: Slack

PhaseImplementation
TriggerExternal: @mentions. Internal: anxiety about missing info
ActionCheck channel (one click)
Variable RewardNew messages (Hunt), recognition (Tribe)
InvestmentChannel history, integrations, workflows

Example 3: Duolingo

PhaseImplementation
TriggerExternal: streak reminders. Internal: guilt, achievement
ActionComplete one lesson (5 min)
Variable RewardXP, leaderboard (Self + Tribe)
InvestmentStreak, progress, course completion

Ethical Considerations

The Manipulation Test

Ask yourself:

  1. Materially improves life? Does the habit genuinely help users?
  2. User is the customer? Or are they the product?
  3. Would you use it yourself? And let your children use it?
  4. Transparent? Would users feel manipulated if they knew?

Ethical Spectrum

Facilitator -------- Entertainer -------- Dealer
(Helps users)       (Neutral)            (Exploits users)

Your product should be a Facilitator

Best Practices

Do

  • Start with internal trigger research (what emotion leads to use?)
  • Make first action as simple as possible
  • Vary rewards meaningfully, not randomly
  • Ensure investments create genuine value
  • Test hook cycle with real users

Avoid

  • Relying solely on external triggers (expensive, unsustainable)
  • Complex actions that require learning
  • Predictable rewards that become boring
  • Investments that feel like manipulation
  • Ignoring ethical implications

Integration with Other Methods

MethodCombined Use
Fogg Behavior ModelAction phase design
Self-Initiated TriggersInternal trigger development
Loss AversionInvestment and streak psychology
Jobs-to-be-DoneUnderstanding underlying motivations

Resources

平台分布

Codex

37.53%
按下载量换算58

Claude

29.67%
按下载量换算46

Cursor

19.75%
按下载量换算30

Gemini CLI

9.13%
按下载量换算14

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