‹ 首页

problem-framing

@wellapp-ai · 收录于 5 天前 · 上游提交 1 个月前

Frame problems using JTBD Job Stories, HMW questions, and persona validation

适合你,如果需要在产品早期系统化地定义和验证问题

/ 通过 npx 安装 校验哈希
npx oh-my-skill add wellapp-ai/well/problem-framing
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- wellapp-ai/well/problem-framing
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify wellapp-ai/well/problem-framing
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
340GitHub stars
~612上下文体积 · 单文件
索引托管

怎么用

商店整理自技能原文 · 版本 782601c · 表述以原文为准
它做什么

按JTBD方法生成Job Story,再转为How Might We问题,从Notion数据库查找相关用户画像,最后从功能、情感、社交三维度验证问题完整性,输出格式化报告。

什么时候触发

在DIVERGE循环的Ask模式开始时,或当你探索新功能/问题空间时,或需要明确问题定义时触发。也可手动用“use problem-framing skill”调用。

装好后可以这样说
生成Job Story和HMW问题。
获取Personas并检查三维度。
技能原文 SKILL.md作者撰写 · MIT · 782601c

Problem Framing Skill

Frame problems effectively using Jobs-to-be-Done, How Might We questions, and persona validation from Notion.

When to Use
  • At the start of DIVERGE loop (Ask mode)
  • When exploring a new feature or problem space
  • Before ideation to ensure clear problem definition
Instructions
Phase 1: Job Story Definition

Create a Job Story in this format:

When [situation/context],
I want to [motivation/action],
So I can [expected outcome/benefit].

Example:

When I'm managing multiple client workspaces,
I want to switch between them quickly,
So I can respond to urgent requests without losing context.
Phase 2: How Might We (HMW) Question

Reframe the problem as an opportunity question:

How might we [opportunity that addresses the job story]?

Guidelines:

  • Start broad, then narrow if needed
  • Avoid suggesting solutions in the question
  • Focus on the user's goal, not the feature

Example:

How might we help users navigate between workspaces seamlessly?
Phase 3: Persona Lookup (Notion MCP)

Fetch relevant personas from Notion database:

  1. Search for personas database: ``` API-post-search with query "Personas" or "User Personas" ```
  1. Query the database: ``` API-query-data-source with database_id from search results ```
  1. Get persona details: ``` API-retrieve-a-page + API-get-block-children for each relevant persona ```

Extract these fields:

  • Name
  • Role / Job Title
  • Goals (what they want to achieve)
  • Pain Points (what frustrates them)
  • Context (environment, constraints)
Phase 4: Three Dimensions Check

Validate the problem addresses all three job dimensions:

| Dimension | Question | Example | |-----------|----------|---------| | Functional | What task are they completing? | "Switch between workspaces" | | Emotional | How do they want to feel? | "In control, not overwhelmed" | | Social | How do they want to be perceived? | "Responsive, professional" |

Output Format

After running this skill, output:

## Problem Framing

### Job Story
When [situation],
I want to [motivation],
So I can [outcome].

### How Might We
How might we [opportunity]?

### Relevant Personas

| Persona | Role | Goals | Pain Points |
|---------|------|-------|-------------|
| [Name] | [Role] | [Goals] | [Pain Points] |

### Three Dimensions

| Dimension | Definition |
|-----------|------------|
| Functional | [Task] |
| Emotional | [Feeling] |
| Social | [Perception] |
Invocation

Invoke manually with "use problem-framing skill" or follow Ask mode DIVERGE loop which references this skill's phases.

Related Skills
  • design-context - Run after problem-framing
  • competitor-scan - Research how others solve this problem
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。