Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

causal-interview-protocol因果访谈协议

Agent Skill

causal-interview-protocol 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。

总安装

8,224

周安装

427

GitHub Stars

2

下载量

2,805
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:causal-interview-protocol(因果访谈协议)
来源仓库:https://github.com/coowoolf/insighthunt-skills
仓库路径:skills/causal-interview-protocol
安装命令:
npx skills add https://github.com/coowoolf/insighthunt-skills --skill 'Causal Interview Protocol'
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/coowoolf/insighthunt-skills --skill 'Causal Interview Protocol'

简介

该技能提供一种深度访谈方法,用于还原用户购买决策的时间线与因果机制。

  • 适合在产品发现阶段理解“为何被雇佣”、验证零到一概念或补充浅层调研不足时启用。
  • 采用类似犯罪调查或心理治疗的方式提问,引导受访者回溯行为动机与上下文。
  • 使用时需注意访谈对象的表达习惯与隐私边界,避免诱导性提问或信息过度整理。
  • causal-interview-protocol 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

The Causal Interview Protocol

"It's criminal and intelligence interrogation that feels like therapy because most people don't actually know why they bought." — Bob Moesta

What It Is

A specific interviewing technique designed to reconstruct the customer's timeline and uncover the causal mechanisms behind a purchase, resembling a criminal investigation or therapy session rather than a standard survey.

When To Use

  • During customer discovery
  • Validating zero-to-one product concepts
  • Understanding why a product is being "hired"
  • When survey data seems unreliable or shallow

The Protocol

┌──────────────────────────────────────────────────────┐
│  STEP 1: RECRUIT                                     │
│  → Interview ONLY people who already switched        │
│  → Recent behavior > Hypothetical intent             │
├──────────────────────────────────────────────────────┤
│  STEP 2: RECONSTRUCT TIMELINE                        │
│  → Work backwards from purchase moment               │
│  → "Walk me through when you first thought about..." │
├──────────────────────────────────────────────────────┤
│  STEP 3: PENETRATE LAYERS                            │
│  → Layer 1: Pablum (polite surface answers)          │
│  → Layer 2: Fantasy/Nightmare (hypothetical fears)   │
│  → Layer 3: Reality (actual causal mechanism)        │
├──────────────────────────────────────────────────────┤
│  STEP 4: CLUSTER CAUSAL PATHWAYS                     │
│  → Group by WHY they switched, not WHO they are      │
│  → Ignore demographics initially                     │
└──────────────────────────────────────────────────────┘

Core Principles

1. Interview Only Actual Switchers

People who have already made the progress (purchased/switched), not prospects.

2. No Discussion Guide

Follow the story and the energy. Don't force a script.

3. Penetrate the Pablum

Get past polite surface answers to the real story.

4. Cluster by Causality

Group interviews by causal pathways, not demographic segments.

5. Find the Struggling Moment

Listen for what triggered the search.

Key Questions

❌ AVOID: "Why did you buy this?"
   (Invites post-hoc rationalization)

✅ USE: "Walk me through what happened..."
   "What was going on in your life when you first thought about this?"
   "Tell me about the moment you decided to actually purchase..."
   "What did you try before this?"

Common Mistakes

❌ Asking "Why?" repeatedly (invites rationalization)

❌ Believing customers' hypothetical claims ("I would buy this")

❌ Segmenting by demographics instead of causal pathways

Real-World Example

Discovering why people buy Snickers (meal replacement/masticaton for energy) vs. Milky Way (emotional reward/melting texture), leading to completely different competitive sets.


*Source: Bob Moesta, Co-creator of Jobs-to-be-Done, Lenny's Podcast*

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.77%
按下载量换算1,087

Claude

30%
按下载量换算842

Cursor

18.18%
按下载量换算510

Gemini CLI

9.49%
按下载量换算266

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills