# discovery-research-stinger

discovery-research-stinger is a Claude Code skill that shapes discovery before development by examining assumptions and defining a first version.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 96 repo stars
- Author: Legion Code Inc.
- License: AGPL-3.0-or-later · policy=link-only · description only; the file stays with the author
- Source: https://github.com/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/business-and-product-tools/skills/discovery-research-stinger/SKILL.md
- Updated: 2026-10-18
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/discovery-research-stinger

## What it does

The skill keeps discovery focused on one measurable outcome. It guides the agent through an opportunity-solution tree, a JTBD interview script, an assumption map, and an experiment aimed at a high-risk belief. Project artifacts go into files such as `library/discovery/interview-scripts/` and `library/discovery/experiments/`.

A demand test needs a declared assumption, metric, threshold, and sampling conditions before it is authorized; a planned test is not treated as completed. The skill then gives one scoped recommendation: continue discovery, pivot, or stop. Continuing discovery does not authorize implementation, and at least one assumption test must be validated before building. It prepares a discovery handoff rather than a PRD or implementation plan.

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add legioncodeinc/vibe-coding-tools
```
In the agent chat (not a shell):
```text
/plugin install business-and-product-tools@wasp-nest
```
This installs the whole business-and-product-tools plugin with all its skills

2. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill discovery-research-stinger -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill discovery-research-stinger -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill discovery-research-stinger -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install legioncodeinc/vibe-coding-tools plugins/business-and-product-tools/skills/discovery-research-stinger
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add legioncodeinc/vibe-coding-tools --skill discovery-research-stinger -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/legioncodeinc/vibe-coding-tools --path plugins/business-and-product-tools/skills/discovery-research-stinger
```

### Windsurf (Devin Desktop)

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

### 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/legioncodeinc/vibe-coding-tools/tree/HEAD/plugins/business-and-product-tools/skills/discovery-research-stinger/SKILL.md

## When to use it
- set a measurable outcome for product discovery
- draft a JTBD interview around an opportunity
- map the assumptions behind a proposed solution
- plan an experiment for a high-risk assumption
- define first-version scope from discovery evidence

## Example prompts
- Help me choose a measurable outcome for discovery before we start building.
- Draft a JTBD interview script for this opportunity and save it in the project.
- Plan a demand test for this assumption and recommend whether to continue, pivot, or stop.

## Similar
- [product-discovery](https://affpapa.org/en/nevibecode/skills/product-discovery.md) — skill · 715 installs
- [discovery-interview-prep](https://affpapa.org/en/nevibecode/skills/discovery-interview-prep.md) — skill · 3200 installs
- [suede-customer-research](https://affpapa.org/en/nevibecode/skills/suede-customer-research.md) — skill · ★ 121 repo stars
- [identify-assumptions-new](https://affpapa.org/en/nevibecode/skills/identify-assumptions-new.md) — skill · 3100 installs
- [identify-assumptions-existing](https://affpapa.org/en/nevibecode/skills/identify-assumptions-existing.md) — skill · 3000 installs
- [identify-assumptions](https://affpapa.org/en/nevibecode/skills/identify-assumptions.md) — skill · 102 installs

From the same set: [legioncodeinc/vibe-coding-tools](https://affpapa.org/en/nevibecode/by/legioncodeinc/vibe-coding-tools.md) — 172 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
