Gr User Interview
- 108 installs
- 66 repo stars
- Updated August 4, 2026
- gingiris-1031/gingiris-skills
Run user interviews to find PMF with a framework for recruitment, question design, execution, and data synthesis based on 937 HeyGen interviews.
About
A user-interview framework for finding product-market fit, covering recruitment, question design, execution, and synthesis. A developer uses it during customer discovery to run interviews that surface real behavior rather than opinions.
- Five principles including asking behavior not opinion
- Pause-and-review after 5 interviews and mirror the user's words
Gr User Interview by the numbers
- 108 all-time installs (skills.sh)
- Ranked #1,332 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/gingiris-1031/gingiris-skills --skill gr-user-interviewAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 108 |
|---|---|
| repo stars | ★ 66 |
| Last updated | August 4, 2026 |
| Repository | gingiris-1031/gingiris-skills ↗ |
What it does
Run user interviews to find PMF with a framework for recruitment, question design, execution, and data synthesis based on 937 HeyGen interviews.
Files
gr-user-interview — 用户访谈
什么时候用
- "我要找 PMF，怎么做访谈"
- "用户反馈很杂，不知道抓哪个"
- "我采访了 5 个人，都没 insight"
- "怎么避免用户说假话"
---
核心原则（5 条）
1. 问 behavior，不问 opinion ❌ "你会用这个功能吗？" → 会得到礼貌性"yes" ✅ "上次遇到 X 问题是什么时候？你当时做了什么？" → 得到真实行为
2. 20 分钟访谈 >> 5 个 feature 问题 深度一个场景，比问 5 个浅问题更有价值
3. 录音 / 整稿 > 当场记笔记 当场记会错过微表情和语气
4. 5 人后暂停，复盘 不要连访 20 人才总结，5 人后大概率已看到模式
5. 用词镜像 用户用什么词，你也用什么词 —— 不要替换成产品语言
---
访谈结构模板（20-30 分钟）
| 阶段 | 时长 | 问什么 |
|---|---|---|
| Warm-up | 2 min | "你今天做了什么？"（开放式，松弛下来） |
| Discover | 5 min | "上次做 X 是什么时候？能讲讲吗？" |
| Deep-dive | 10 min | "当时你用了什么工具？怎么用的？哪里卡住？" |
| Alternative | 5 min | "有没有试过其他方法？为什么没继续？" |
| Wrap-up | 3 min | "如果有一个魔法能解决这个问题，它会怎么工作？" |
---
深度参考
📂 https://github.com/Gingiris/gingiris-user-interview
references/templates.md— 不同阶段（Discovery / Validation / Retention）的问题模板- HeyGen 937 访谈案例拆解
---
合成流程
1. 每次访谈后 24h 内整理 3 张卡片：
- Pain（用户的真实痛）
- Workaround（他们目前怎么凑合）
- Quote（可引用的原话）
2. 每 5 个访谈做一次复盘：
- 重复出现 ≥ 3 次的 Pain → 候选 PMF 方向
- 重复出现 ≥ 2 次的 Workaround → 竞品信号
3. 每 20 个访谈做一次决策：
- 继续这个假设 / 换方向 / 需要更多数据
---
级联推荐
- 访谈发现新 PMF 方向 →
gr-blog-post写一篇（验证市场反应） - 访谈发现对手名字被提 ≥ 3 次 →
gr-competitor深度分析 - PMF 明确 →
gr-b2b-growth或gr-oss-marketing启动增长 - 需要招募访谈对象 → 从
gr-seo-patrol的 GSC 流量挑读者
---
反模式
- ❌ 问 "你愿意付费吗" → 100% 是假答案
- ❌ 发问卷替代访谈（信息密度差 10x）
- ❌ 只访现有用户不访流失用户（流失才是真金）
- ❌ 一次访谈超过 45 分钟（疲劳 → 敷衍）
- ❌ 访谈中推销自己产品（污染答案）
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493k