# collaborating-with-claude

collaborating-with-claude consults Claude Code CLI as an advisor for diff reviews and tradeoffs while your primary agent builds.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 475 repo stars
- Author: cnfjlhj
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/cnfjlhj/ai-collab-playbook/tree/HEAD/skills/full/collaborating-with-claude/SKILL.md
- Updated: 2026-10-13
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/collaborating-with-claude

## What it does

This skill routes inquiries to the Claude Code CLI using a helper script named `scripts/claude_bridge.py`. It returns structured JSON and retains conversation state across rounds using `SESSION_ID`. Claude acts strictly as an advisor here: file writes remain locked down, and the script enforces replies formatted exclusively as unified diff patches.

Execution works via `--cd` at the project root, passing file references rather than entire file dumps. Routine runs lean on the `sonnet` model alias, reserving `opus` strictly for tricky debugging or explicit requests.

Without prior terminal authentication via `claude` and `/login`, headless script execution will fail immediately.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill collaborating-with-claude -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill collaborating-with-claude -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill collaborating-with-claude -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install cnfjlhj/ai-collab-playbook skills/full/collaborating-with-claude
```

2. **Manually: put the files in place**
- File: `.github/skills/collaborating-with-claude/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill collaborating-with-claude -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/cnfjlhj/ai-collab-playbook --path skills/full/collaborating-with-claude
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/collaborating-with-claude/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/cnfjlhj/ai-collab-playbook/tree/HEAD/skills/full/collaborating-with-claude/SKILL.md

## When to use it
- gather a second opinion on architecture tradeoffs and edge cases
- generate unified diff patches without modifying working directory files
- review existing diffs for missing automated tests and edge bugs
- maintain stateful multi-turn debugging sessions through a bridge script

## Example prompts
- Ask Claude via the bridge for a second opinion on `src/auth.py`
- Request a unified diff patch from Claude to fix the bug in session `s-12345`

## Similar
- [fallow-review](https://affpapa.org/en/nevibecode/skills/fallow-review.md) — skill · 1000 installs
- [open-code-review-delegate](https://affpapa.org/en/nevibecode/skills/open-code-review-delegate.md) — skill · 5000 installs
- [qodo-review](https://affpapa.org/en/nevibecode/skills/qodo-review.md) — skill · 107 installs
- [replica-diff](https://affpapa.org/en/nevibecode/skills/replica-diff.md) — skill · 1600 installs
- [03_code_review](https://affpapa.org/en/nevibecode/prompts/03-code-review.md) — prompt · ★ 2744 repo stars
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 437600 installs

From the same set: [cnfjlhj/ai-collab-playbook](https://affpapa.org/en/nevibecode/by/cnfjlhj/ai-collab-playbook.md) — 18 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
