# interactive-requirements-gathering

interactive-requirements-gathering runs a structured questionnaire for requirements: one question at a time, A–E options, answers saved as you go. Useful before the first line of code.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 103 installs · ★ 45 repo stars
- Author: oimiragieo
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/oimiragieo/agent-studio/tree/HEAD/.claude/skills/interactive-requirements-gathering/SKILL.md
- Updated: 2026-07-14
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/interactive-requirements-gathering

## What it does

The skill turns requirement gathering into a scripted conversation. Before each question the agent labels it `Additive` (several answers allowed) or `Exclusive` (pick one), then offers A, B, C plus two escape hatches: D for your own wording, E to let the model decide and move on. Questions arrive one by one, and the agent waits for a reply before summarizing what it heard.

What ships is guidance rather than code: phrasing rules, the option layout, and the step order from intro to draft review, where you approve or list edits. Long questionnaires can be checkpointed in a JSON file with a `last_successful_step` key and the answers collected so far, so an interrupted session resumes where it stopped.

It relies on `Read`, `Write`, `Edit` and `AskUserQuestion`, and the config names `sonnet` as the model. Progress saving goes through `Write`, so an agent without file-write permission loses that part. One rule matters more than the rest: the generated document is built from the answers you actually picked, never from the full option list you were shown.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add oimiragieo/agent-studio --skill interactive-requirements-gathering -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add oimiragieo/agent-studio --skill interactive-requirements-gathering -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add oimiragieo/agent-studio --skill interactive-requirements-gathering -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install oimiragieo/agent-studio .claude/skills/interactive-requirements-gathering
```

2. **Manually: put the files in place**
- File: `.github/skills/interactive-requirements-gathering/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add oimiragieo/agent-studio --skill interactive-requirements-gathering -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/oimiragieo/agent-studio --path .claude/skills/interactive-requirements-gathering
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add oimiragieo/agent-studio --skill interactive-requirements-gathering -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/oimiragieo/agent-studio/tree/HEAD/.claude/skills/interactive-requirements-gathering/SKILL.md

## When to use it
- gather project requirements without a wall of clarifying messages
- separate multi-select questions from single-choice ones
- draft a spec from the wording you supplied
- resume a half-finished questionnaire from the saved step
- type a custom answer when none of the offered options fit

## Example prompts
- Run a requirements questionnaire for the new service, one question at a time with A–E options.
- Ask me about auth methods, tagging each question as `Additive` or `Exclusive`, and save progress to a JSON file.
- Draft the product vision using only the answers I picked.

## Similar
- [when-gathering-requirements-use-interactive-planner](https://affpapa.org/en/nevibecode/skills/when-gathering-requirements-use-interactive-planner.md) — skill · 1 install
- [requirements-gathering](https://affpapa.org/en/nevibecode/skills/requirements-gathering.md) — skill · 666 installs
- [requirements-clarity](https://affpapa.org/en/nevibecode/skills/requirements-clarity.md) — skill · 204 installs
- [requirements-analysis](https://affpapa.org/en/nevibecode/skills/requirements-analysis.md) — skill · 2300 installs
- [product-requirements](https://affpapa.org/en/nevibecode/skills/product-requirements.md) — skill · 1300 installs
- [requirements-writer](https://affpapa.org/en/nevibecode/skills/requirements-writer.md) — skill · ★ 8928 repo stars

From the same set: [oimiragieo/agent-studio](https://affpapa.org/en/nevibecode/by/oimiragieo/agent-studio.md) — 8 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
