Token导航 LogoToken导航

Agent Skill · 研究检索

loss-aversion-psychology(损失厌恶心理)

loss-aversion-psychology 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。

loss-aversion-psychology 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 50,488。

总安装 612周安装 25GitHub Stars 239下载 198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:loss-aversion-psychology(损失厌恶心理)
来源仓库:https://github.com/flpbalada/my-opencode-config
仓库路径:skills/loss-aversion-psychology
安装命令:
npx skills add https://github.com/flpbalada/my-opencode-config --skill loss-aversion-psychology
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 loss-aversion-psychology

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。

loss-aversion-psychology 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。适用于研究检索类任务,如信息搜集、资料筛选和线索整理,尤其适合需要自动化处理重复性搜索的场景。

通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限范围和实际维护状态后再使用。使用前应检查是否会触发联网、命令执行或文件读写操作,避免在不安全环境中运行。建议结合原始 README 和仓库内容进一步核验具体用法和功能边界。

来源仓库内路径:skills/loss-aversion-psychology

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 loss-aver…;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

loss-aversion-psychology 怎么安装?

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

loss-aversion-psychology 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。

loss-aversion-psychology 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。

loss-aversion-psychology 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。

loss-aversion-psychology 用的人多吗?

公开数据是累计安装 612 次,近一周安装 25 次,下载 198 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。

loss-aversion-psychology 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
loss-aversion-psychology

损失厌恶心理 · 本页

612239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

Loss Aversion Psychology - Losses Loom Larger Than Gains

Loss Aversion is a cognitive bias discovered by Daniel Kahneman and Amos Tversky showing that people feel losses approximately twice as strongly as equivalent gains. This asymmetry profoundly influences decision-making and behavior.

When to Use This Skill

  • Designing retention and anti-churn features
  • Crafting pricing and upgrade messaging
  • Creating urgency in conversion funnels
  • Building streak and progress features
  • Writing copy for landing pages
  • Framing feature benefits

Core Concepts

The 2:1 Ratio

        Psychological Impact
              ^
              |         Gains
              |        /
              |      /
     +--------|----/---------> Value
              |  /
           Loss|/
              |
              |  The loss curve is ~2x steeper
              v

A $100 loss feels as bad as a $200 gain feels good.

Prospect Theory Framework

ConceptDescriptionExample
Reference PointCurrent state as baseline"You currently have X"
Loss FrameEmphasis on what could be lost"Don't lose your progress"
Gain FrameEmphasis on what could be gained"Get 50% more"
Endowment EffectValuing owned things higherFree trial creates ownership

When Loss Framing Works Best

SituationLoss Frame Effective?
High stakes decisionsYes
Preventing bad outcomesYes
Risk-averse audiencesYes
Building habitsYes
Low-involvement decisionsLess effective
Exploratory behaviorLess effective

Analysis Framework

Step 1: Identify Loss Opportunities

Map user journey for potential loss frames:

StageWhat User HasPotential Loss
TrialAccess to featuresLosing access
ActiveProgress/dataLosing progress
At-riskStreak/statusBreaking streak
ChurnedHistory/investmentLosing history

Step 2: Choose Frame Appropriately

Decision: Frame as loss or gain?

Consider:
├── User relationship stage
│   └── New users: Gains more welcoming
│   └── Existing users: Losses more motivating
├── Action reversibility
│   └── Reversible: Lighter touch OK
│   └── Irreversible: Loss frame powerful
└── Ethical considerations
    └── Does this genuinely help the user?

Step 3: Implement Ethically

ApproachEthicalManipulative
"Your streak will reset"Honest reminderManufactured guilt
"Unused credits expire"Clear policyHidden deadline
"Limited time offer"Genuine scarcityFake urgency

Output Template

## Loss Aversion Analysis

**Feature/Message:** [Name] **Date:** [Date]

### Current Framing

**As gain:** [Current copy/design] **User response:** [Current metrics]

### Loss Frame Opportunity

**What user has:** [Established value] **Potential loss:** [What could be lost]
**Loss frame version:** [Proposed copy/design]

### Ethical Check

- [ ] User genuinely benefits from taking action
- [ ] Loss is real, not manufactured
- [ ] Messaging is honest and transparent
- [ ] Would we be comfortable if users knew the psychology?

### Implementation Plan

| Element  | Current   | Proposed | Expected Impact |
| -------- | --------- | -------- | --------------- |
| [Copy 1] | [Text]    | [Text]   | [Estimate]      |
| [Design] | [Current] | [Change] | [Estimate]      |

Real-World Examples

Example 1: Duolingo Streaks

Mechanism: Users build daily learning streaks Loss frame: "Don't lose your 47-day streak!" Psychology:

  • Streak = accumulated investment (endowment)
  • Breaking it = losing days of effort
  • Effect: 2x stronger than "Build a 48-day streak!"

Example 2: LinkedIn Profile Completion

Gain frame: "Complete your profile to get more views" Loss frame: "You're missing out on 40% more profile views"

The loss frame outperforms because it highlights what you're currently losing.

Example 3: Trial Expiration

Weak: "Your trial ends tomorrow" Strong: "Tomorrow you'll lose access to:

  • 47 saved projects
  • 12 team members
  • All your custom settings"

Making the loss concrete and specific amplifies the effect.

Ethical Guidelines

Do

  • Use loss framing for genuinely beneficial actions
  • Be honest about what's at stake
  • Give users real control and options
  • Balance loss frames with positive experiences
  • Test that users feel good after taking action

Avoid

  • Manufacturing fake urgency or scarcity
  • Guilt-tripping for engagement metrics
  • Hiding information to create loss anxiety
  • Using loss aversion on vulnerable users
  • Dark patterns that exploit psychology

The Ethics Test

Ask: "If users knew exactly how this works psychologically, would they:

  1. Thank us for the helpful reminder?
  2. Feel manipulated and resentful?"

If (2), reconsider the approach.

Best Practices

Effective Loss Messaging

ElementExample
Specific"Lose your 23 saved items" not "Lose your data"
Immediate"Expires tonight" not "Expires soon"
Personal"Your progress" not "Progress"
RecoverableShow how to prevent the loss

Timing Matters

TimingEffectiveness
Too earlyFeels irrelevant, ignored
Just rightMotivates action
Too lateCreates resentment
After lossRecovery opportunity

Integration with Other Methods

MethodCombined Use
Hooked ModelInvestment phase creates loss potential
Fogg Behavior ModelLoss increases motivation
Cognitive BiasesCombine with other biases carefully
Progressive DisclosureReveal loss implications gradually

Resources

平台分布

Codex

33.62%
按下载量换算67

Claude

32.76%
按下载量换算65

Cursor

18.97%
按下载量换算38

Gemini CLI

8.96%
按下载量换算18

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