# chain-roleplay-debate-synthesis

chain-roleplay-debate-synthesis — a skill for Claude Code, Cursor, Codex and other IDEs runs structured debate between roles with competing priorities and synthesizes a unified decision.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 161 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/chain-roleplay-debate-synthesis/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/chain-roleplay-debate-synthesis

## What it does

Breaks a problem into roles (engineer, product manager, finance, customer), each states their position with arguments and concerns, then structured debate follows: point-counterpoint, assumption surfacing, edge case testing. Final step integrates all views into one recommendation with explicit tradeoffs.

Fits decisions with two to five roles. More than five makes synthesis unwieldy. The repository includes a template in `resources/template.md`, methodology for complex cases in `resources/methodology.md`, and a synthesis quality rubric in JSON. Without roles that have real conflicting interests, the process becomes theater.

Each role must see success and failure differently, rely on their own metrics, and acknowledge their own limits. Debate surfaces cruxes — what evidence would make a role change its mind — and focuses on those instead of restating positions.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill chain-roleplay-debate-synthesis -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill chain-roleplay-debate-synthesis -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/chain-roleplay-debate-synthesis/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill chain-roleplay-debate-synthesis -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/chain-roleplay-debate-synthesis/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lyndonkl/claude skills/chain-roleplay-debate-synthesis
```

2. **Manually: put the files in place**
- File: `.github/skills/chain-roleplay-debate-synthesis/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill chain-roleplay-debate-synthesis -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lyndonkl/claude --path skills/chain-roleplay-debate-synthesis
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/chain-roleplay-debate-synthesis/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill chain-roleplay-debate-synthesis -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/chain-roleplay-debate-synthesis/SKILL.md

## When to use it
- choose between fast launch and long-term maintainability
- test an architectural decision from developer, designer and finance angles
- merge conflicting expert opinions into strategy
- find the right balance between privacy and personalization
- surface assumptions a single viewpoint would miss

## Example prompts
- Run a roleplay debate: engineer for new framework, tech lead for stability, PM for timeline. Synthesize the decision.
- Analyze cloud provider choice from DevOps, finance and security perspectives.
- Test a monetization idea from marketer, lawyer and customer viewpoints. Show the tradeoffs.

## Similar
- [judge-with-debate](https://affpapa.org/en/nevibecode/skills/judge-with-debate.md) — skill · 1400 installs
- [debate-review](https://affpapa.org/en/nevibecode/skills/debate-review.md) — skill · 705 installs
- [knowledge-synthesis](https://affpapa.org/en/nevibecode/skills/knowledge-synthesis.md) — skill · 6600 installs
- [debate-practice-coach](https://affpapa.org/en/nevibecode/skills/debate-practice-coach.md) — skill · 157 installs
- [decision-debate](https://affpapa.org/en/nevibecode/skills/decision-debate.md) — skill · 383 installs
- [research-synthesis](https://affpapa.org/en/nevibecode/skills/research-synthesis.md) — skill · 4400 installs

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
