Token导航 LogoToken导航

Agent Skill · 研究检索

self-initiated-triggers(自启动触发器)

self-initiated-triggers 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。

self-initiated-triggers 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 57,766。

总安装 424周安装 17GitHub Stars 235下载 137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:self-initiated-triggers(自启动触发器)
来源仓库:https://github.com/flpbalada/my-opencode-config
仓库路径:skills/self-initiated-triggers
安装命令:
npx skills add https://github.com/flpbalada/my-opencode-config --skill self-initiated-triggers
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 self-initiated-triggers

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。

self-initiated-triggers 用于查找、检索和筛选相关信息,支持快速定位候选结果。适用于基于关键词、任务场景或来源线索的信息筛选需求。通过 npx skills add 命令安装,建议结合原始 README 了解具体实现。安装前应确认权限范围和维护状态,避免触发不必要的网络或文件操作。

涉及命令执行时需注意运行目录和数据边界。

来源仓库内路径:skills/self-initiated-triggers

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 self-init…;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

self-initiated-triggers 怎么安装?

在终端执行 npx skills add https://github.com/flpbalada/my-opencode-config --skill self-initiated-trig…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

self-initiated-triggers 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。

self-initiated-triggers 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。

self-initiated-triggers 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。

self-initiated-triggers 用的人多吗?

公开数据是累计安装 424 次,近一周安装 17 次,下载 137 次,GitHub 235 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。

self-initiated-triggers 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
self-initiated-triggers

自启动触发器 · 本页

424235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

Self-Initiated Triggers - From External Prompts to Internal Motivation

Self-Initiated Triggers (Internal Triggers) are emotional states or situations that prompt users to engage with a product without any external reminder. They represent the goal state of habit formation - when users think of your product automatically in response to specific feelings or contexts.

When to Use This Skill

  • Designing for long-term retention
  • Reducing dependency on push notifications
  • Building sustainable engagement loops
  • Understanding user motivation patterns
  • Creating products that become "default" solutions
  • Reducing user acquisition costs through organic return

Core Concepts

External vs. Internal Triggers

External Triggers              Internal Triggers
(Pushed to user)               (Pulled by user)
      |                              |
      v                              v
+-------------+               +-------------+
| - Push      |               | - Boredom   |
|   notif     |   Journey     | - Anxiety   |
| - Email     | ----------->  | - FOMO      |
| - Ads       |               | - Loneliness|
| - WOM       |               | - Curiosity |
+-------------+               +-------------+
      |                              |
      v                              v
   Expensive                     Free
   Interruptive                  Seamless
   Declining effect              Strengthening

The Trigger-Product Association

Emotion/Situation          Product Association
       |                          |
       v                          v
   "I feel bored"    -->    "I'll check Instagram"
   "I have a question" -->  "I'll Google it"
   "I feel anxious"   -->   "I'll check Slack"
   "I'm waiting"      -->   "I'll open TikTok"

Trigger Types

TriggerEmotionExample Products
NegativeBoredom, anxiety, loneliness, FOMOSocial media, news, messaging
PositiveCuriosity, excitement, anticipationLearning apps, games
SituationalWaiting, commuting, winding downPodcasts, reading apps
RoutineMorning, mealtime, bedtimeNews, meditation, fitness

Building Internal Triggers

Phase 1: External Trigger
   "We sent you a notification"
              |
              v
Phase 2: Association Forming
   Repeated: Trigger → Action → Reward
              |
              v
Phase 3: Internal Trigger Emerging
   Emotion alone triggers action
              |
              v
Phase 4: Automatic Habit
   No conscious thought needed

Analysis Framework

Step 1: Identify Target Emotions

Research questions:

  • What emotional state precedes product use?
  • What are users feeling when they reach for the product?
  • What situation or context triggers engagement?
User SegmentPrimary EmotionSecondary EmotionContext
[Segment 1][Emotion][Emotion][When/Where]
[Segment 2][Emotion][Emotion][When/Where]

Step 2: Map Current Trigger Mix

External Triggers          Internal Triggers
[_____________________]    [_____________________]
        80%                         20%

Target state:
[_____________________]    [_____________________]
        30%                         70%

Step 3: Design Trigger Strengthening

StrategyImplementation
Repeated pairingConsistent context → action → reward
Emotional resonanceDesign for target emotion
Ritual creationEncourage routine usage
Social reinforcementOthers validate the behavior

Step 4: Measure Trigger Strength

MetricWeak TriggerStrong Trigger
Return frequency without promptsLowHigh
Time to return after absenceLongShort
Usage without notificationsRareCommon
Self-reported "automatic" useNeverOften

Output Template

## Internal Trigger Analysis

**Product:** [Name] **Date:** [Date]

### Target Internal Trigger

**Primary emotion:** [Emotion] **Trigger context:** [Situation when emotion
occurs] **Desired association:** "When I feel [emotion], I [product action]"

### Current State

| Engagement Type          | % of Sessions |
| ------------------------ | ------------- |
| Push notification driven | [X%]          |
| Email driven             | [X%]          |
| Self-initiated           | [X%]          |

### User Research Findings

**Interview insight 1:** "[Quote about when/why they open the product]"
**Interview insight 2:** "[Quote about emotional state]"

### Trigger Strengthening Plan

| Strategy     | Action            | Expected Outcome |
| ------------ | ----------------- | ---------------- |
| [Strategy 1] | [Specific action] | [Metric impact]  |
| [Strategy 2] | [Specific action] | [Metric impact]  |

### Success Metrics

| Metric                      | Current | Target | Timeframe |
| --------------------------- | ------- | ------ | --------- |
| Self-initiated sessions     | [X%]    | [Y%]   | [Months]  |
| Return without notification | [X%]    | [Y%]   | [Months]  |

Real-World Examples

Example 1: Twitter/X

Target emotion: Boredom + need for stimulation Association built: "I have a spare moment → I'll check Twitter"

Mechanisms:

  • Variable reward (always new content)
  • Quick dopamine hits
  • FOMO reinforcement
  • Endless scroll removes end point

Example 2: Slack

Target emotion: Anxiety about missing information Association built: "I feel out of the loop → I'll check Slack"

Mechanisms:

  • @mentions create urgency
  • Channel activity visible
  • "Unread" counts create incompleteness
  • Professional FOMO

Example 3: Duolingo

Target emotion: Guilt + achievement desire Association built: "I should be productive → I'll do a lesson"

Mechanisms:

  • Streak creates obligation
  • Short lessons fit spare moments
  • Progress visualization rewards
  • Guilt as internal trigger (healthy or not)

Ethical Considerations

Healthy vs. Unhealthy Triggers

AspectHealthyUnhealthy
Emotion exploitedCuriosity, growth desireAnxiety, loneliness, FOMO
User outcomeFeels better after useFeels worse or unchanged
SustainabilityLong-term satisfactionShort-term with regret
ControlUser feels in controlUser feels compelled

Design for Wellbeing

  • Target positive emotions where possible
  • Ensure product delivers on emotional promise
  • Provide usage awareness tools
  • Allow notification customization
  • Design satisfying end points

Best Practices

Do

  • Research actual emotional triggers (don't assume)
  • Design reward to match the emotional need
  • Create consistent context-action pairings
  • Make first action extremely simple
  • Measure self-initiated engagement separately

Avoid

  • Relying solely on external triggers long-term
  • Exploiting negative emotions irresponsibly
  • Breaking user trust with manipulative patterns
  • Ignoring the emotional aftermath of use
  • Designing without usage boundaries

Integration with Other Methods

MethodCombined Use
Hooked ModelInternal triggers are the goal state
Fogg Behavior ModelTrigger is the T in B=MAT
Jobs-to-be-DoneEmotional jobs are internal triggers
Loss AversionFear of loss as internal trigger

Resources

平台分布

Codex

37.7%
按下载量换算52

Claude

26.26%
按下载量换算36

Cursor

18.92%
按下载量换算26

Gemini CLI

8.69%
按下载量换算12

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