Token导航 LogoToken导航

Agent Skill · 研究检索

jtbd-analysis(JTBD 分析)

jtbd-analysis 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。

jtbd-analysis 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;许可证为 MIT,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 64,379。

总安装 303周安装 13GitHub Stars 61下载 106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
MIT

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:jtbd-analysis(JTBD 分析)
来源仓库:https://github.com/melodic-software/claude-code-plugins
仓库路径:skills/jtbd-analysis
安装命令:
npx skills add https://github.com/melodic-software/claude-code-plugins --skill jtbd-analysis
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/melodic-software/claude-code-plugins --skill jtbd-analysis

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。

jtbd-analysis 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。可结合来源仓库和原始 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或命令执行。使用时需注意其功能边界,避免过度依赖自动化结果。

来源仓库内路径:skills/jtbd-analysis

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/melodic-software/claude-code-plugins --skill j…;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

jtbd-analysis 怎么安装?

在终端执行 npx skills add https://github.com/melodic-software/claude-code-plugins --skill jtbd-analys…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

jtbd-analysis 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。

jtbd-analysis 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。

jtbd-analysis 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

jtbd-analysis 用的人多吗?

公开数据是累计安装 303 次,近一周安装 13 次,下载 106 次,GitHub 61 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。

jtbd-analysis 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 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

  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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
jtbd-analysis

JTBD 分析 · 本页

30361只读MIT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

Jobs to Be Done (JTBD) Analysis

Jobs to Be Done is a framework for understanding why customers "hire" products to help them make progress in specific circumstances.

When to Use This Skill

Keywords: jobs to be done, JTBD, customer jobs, functional jobs, emotional jobs, social jobs, job statements, outcome-driven innovation, Clayton Christensen, hiring products, customer progress

Use this skill when:

  • Understanding the underlying motivation behind feature requests
  • Reframing requirements from features to customer outcomes
  • Discovering unmet needs that competitors haven't addressed
  • Prioritizing features based on importance vs satisfaction
  • Interviewing customers about their struggles and desired progress
  • Analyzing why customers switch to or from competitors

Core Concepts

The JTBD Framework

Customers don't buy products.
Customers HIRE products to get a JOB done.

Classic Example: People don't buy a 1/4" drill. They hire it to make a 1/4" hole. But even deeper: they hire it to hang a picture, which helps them feel at home.

Job Dimensions

DimensionDescriptionExample
FunctionalThe practical task to accomplish"Hang a picture on the wall"
EmotionalHow the person wants to feel"Feel proud of my decorated home"
SocialHow they want to be perceived"Be seen as having good taste"

Job Statement Format

When [situation], I want to [motivation], so I can [expected outcome].

Examples:

job_statements:
  - context: "When I'm starting a new project"
    motivation: "I want to quickly find qualified freelancers"
    outcome: "so I can get work done without spending weeks recruiting"

  - context: "When I'm cooking dinner for guests"
    motivation: "I want a recipe that's impressive but not complex"
    outcome: "so I can enjoy the evening without stress"

  - context: "When my flight is delayed"
    motivation: "I want real-time updates on my phone"
    outcome: "so I can plan my connections and notify people waiting"

JTBD Interview Technique

The Switch Interview

Understand why customers switched to your product:

switch_interview_flow:
  1. First thought:
     "When did you first start thinking you needed [solution]?"

  2. Passive looking:
     "What did you do about it initially?"

  3. Active looking:
     "When did you start actively looking for alternatives?"

  4. Deciding:
     "What made you finally choose [product]?"

  5. Consuming:
     "What happened after you started using it?"

  6. Satisfaction:
     "How is it working out? What's still frustrating?"

Push/Pull Forces

PUSH (Away from current situation)
├── Problems with current solution
├── Frustrations and pain points
└── Triggering events

PULL (Toward new solution)
├── Attraction to new way
├── Hoped-for outcomes
└── Perceived improvements

INERTIA (Keeping current behavior)
├── Habits and familiarity
├── Switching costs
└── "Good enough" mentality

ANXIETY (About new solution)
├── Will it actually work?
├── Learning curve
└── Risk of wrong choice

For change to happen: Push + Pull > Inertia + Anxiety

Mapping Jobs to Requirements

Job Map Structure

Break down the main job into stages:

job_map:
  main_job: "Prepare a healthy meal for my family"

  stages:
    1_define:
      name: "Define what to make"
      sub_jobs:
        - "Decide on dietary constraints"
        - "Consider what's in the fridge"
        - "Find a suitable recipe"

    2_prepare:
      name: "Prepare ingredients"
      sub_jobs:
        - "Gather all ingredients"
        - "Prep vegetables and proteins"
        - "Measure quantities"

    3_execute:
      name: "Cook the meal"
      sub_jobs:
        - "Follow recipe steps"
        - "Time multiple dishes"
        - "Adjust seasoning"

    4_complete:
      name: "Serve and clean up"
      sub_jobs:
        - "Plate attractively"
        - "Clean as you go"
        - "Store leftovers properly"

From Jobs to Features

translation_pattern:
  job: "Find a suitable recipe quickly"

  requirements:
    functional:
      - "Search recipes by ingredient"
      - "Filter by dietary restrictions"
      - "Sort by prep time"

    emotional:
      - "Show confidence ratings"
      - "Display success photos"
      - "Offer beginner-friendly options"

    social:
      - "Enable sharing on social media"
      - "Show what friends have made"
      - "Community ratings and reviews"

Outcome-Driven Innovation (ODI)

Outcome Statements

More precise than job statements:

[Direction] + [measure] + [object of control] + [context]

Examples:

outcome_statements:
  - "Minimize the time it takes to find a relevant recipe"
  - "Increase the likelihood that ingredients are in stock"
  - "Reduce the effort required to clean up after cooking"
  - "Minimize the risk of burning or overcooking food"

Importance vs Satisfaction Matrix

                    HIGH IMPORTANCE
                          │
     OVER-SERVED          │         UNDERSERVED
     (Don't invest)       │         (Opportunity!)
                          │
  ──────────────────────────────────────────────
                          │
     APPROPRIATELY        │         APPROPRIATELY
     SERVED               │         SERVED
     (Low value area)     │         (Maintain)
                          │
                    LOW IMPORTANCE
                          │
            LOW SATISFACTION ───────── HIGH SATISFACTION

Opportunity Score = Importance + (Importance - Satisfaction)

Integration with Elicitation

JTBD-Enhanced Interview Questions

Add these to stakeholder interviews:

jtbd_questions:
  context:
    - "When do you typically need to [activity]?"
    - "What triggers you to start this process?"

  motivation:
    - "What are you ultimately trying to achieve?"
    - "Why is this important to you?"

  current_solution:
    - "How do you handle this today?"
    - "What's frustrating about the current approach?"

  desired_progress:
    - "In an ideal world, how would this work?"
    - "What would success look like?"

  emotional:
    - "How do you feel when this goes wrong?"
    - "How would you feel if this was effortless?"

  social:
    - "Who else is affected by how you do this?"
    - "How do others perceive this activity?"

Synthesizing JTBD from Requirements

# After elicitation, analyze through JTBD lens
/requirements-elicitation:discover "inventory management"

# Then apply JTBD framework
# Load this skill and analyze:
# 1. What job are users hiring this system to do?
# 2. What are the functional/emotional/social dimensions?
# 3. Which jobs are underserved?

Output Format

JTBD Analysis Report

jtbd_analysis:
  domain: "inventory management"
  date: "2025-12-26"

  main_job:
    statement: "Keep the right products in stock without excess inventory"
    context: "As a retail manager responsible for product availability"

  job_dimensions:
    functional:
      - "Predict demand accurately"
      - "Reorder at the right time"
      - "Track stock levels"

    emotional:
      - "Feel confident about stock decisions"
      - "Avoid the stress of stockouts"
      - "Pride in efficient operations"

    social:
      - "Be seen as competent by leadership"
      - "Maintain customer satisfaction"
      - "Demonstrate data-driven decisions"

  job_map:
    - stage: "Monitor inventory levels"
      jobs: [...]
      opportunities: [...]

  opportunity_scores:
    - job: "Predict seasonal demand"
      importance: 9
      satisfaction: 4
      score: 14  # High opportunity

    - job: "Generate reorder reports"
      importance: 6
      satisfaction: 7
      score: 5   # Low priority

Related Commands

  • /interview - Conduct JTBD-style interviews
  • /simulate - Simulate stakeholders for JTBD exploration
  • /discover - Full elicitation workflow
  • /prioritize - Use JTBD opportunity scores for prioritization

References

For detailed guidance:

External:

  • Clayton Christensen's "Competing Against Luck"
  • Bob Moesta's "Demand-Side Sales 101"
  • JTBD.info

Version History

  • v1.0.0 (2025-12-26): Initial release - JTBD Analysis skill

Last Updated: 2025-12-26

平台分布

trae

27.4%
按下载量换算29

Antigravity

25.48%
按下载量换算27

windsurf

16.1%
按下载量换算17

Claude Code

14.21%
按下载量换算15

Codex

7.93%
按下载量换算8

Gemini CLI

3.61%
按下载量换算4

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。

继续浏览同类 Skills