# discovery-interviews-surveys

discovery-interviews-surveys is a Claude Code skill for planning user interviews and surveys to test product assumptions and uncover customer problems, before building or when exploring why people switch products.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 109 installs · ★ 203 repo stars
- Author: lyndonkl
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lyndonkl/claude/tree/HEAD/skills/discovery-interviews-surveys/SKILL.md
- Updated: 2026-09-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/discovery-interviews-surveys

## What it does

The skill lays out a research process: set objectives and hypotheses, choose participants and a method, draft questions, collect responses, then analyze what people said. Its guidance favors neutral prompts and accounts of past behavior over guesses about what someone might do.

For interviews, it suggests grouping findings by theme and extracting quotes; survey analysis can include statistical review and comparisons between groups. Separate approaches cover jobs-to-be-done and concept tests. Get permission before recording an interview, and pilot a survey before sending it out.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill discovery-interviews-surveys -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/discovery-interviews-surveys/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/discovery-interviews-surveys/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill discovery-interviews-surveys -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/discovery-interviews-surveys/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill discovery-interviews-surveys -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/discovery-interviews-surveys/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lyndonkl/claude skills/discovery-interviews-surveys
```

2. **Manually: put the files in place**
- File: `.github/skills/discovery-interviews-surveys/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill discovery-interviews-surveys -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lyndonkl/claude --path skills/discovery-interviews-surveys
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/discovery-interviews-surveys/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill discovery-interviews-surveys -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/lyndonkl/claude/tree/HEAD/skills/discovery-interviews-surveys/SKILL.md

## When to use it
- test assumptions about user problems
- identify what triggers a product switch
- draft neutral interview questions
- check whether people understand a concept
- compare interview findings with survey responses

## Example prompts
- Create an interview plan to learn how users currently handle this problem.
- Draft questions about why customers move to another product.
- Build a survey to check interview findings and rank feature priorities.

## Similar
- [customer-interviews](https://affpapa.org/en/nevibecode/skills/customer-interviews.md) — skill · 581 installs
- [signals-scout-surveys](https://affpapa.org/en/nevibecode/skills/signals-scout-surveys.md) — skill · 319 installs
- [debugging-surveys](https://affpapa.org/en/nevibecode/skills/debugging-surveys.md) — skill · 197 installs
- [Weavely AI Forms & Surveys](https://affpapa.org/en/nevibecode/mcp/weavely-ai-forms-surveys.md) — MCP server · 2515 installs
- [user-interviews](https://affpapa.org/en/nevibecode/skills/user-interviews.md) — skill · ★ 900 repo stars
- [code-pair-interviews](https://affpapa.org/en/nevibecode/rules/code-pair-interviews.md) — rule · ★ 41178 repo stars

From the same set: [lyndonkl/claude](https://affpapa.org/en/nevibecode/by/lyndonkl/claude.md) — 49 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
