# do-and-judge

This skill sends a task to an implementation sub-agent, checks the result with an independent judge, and retries with feedback when needed.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 1787
- Author: NeoLabHQ
- License: GPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/NeoLabHQ/context-engineering-kit/tree/HEAD/skills/do-and-judge/SKILL.md
- Updated: 2026-08-26
- HTML: https://affpapa.org/en/nevibecode/skills/do-and-judge

## What it does

do-and-judge separates implementation from verification. The orchestrator sends the task to an implementation sub-agent, asks a second sub-agent to prepare evaluation criteria in parallel, then gives the result to an independent judge. The judge returns a score and issues to address.

When verification fails, the skill starts another implementation attempt with the judge's feedback. You can select a model with `--model` or require a passing score of at least `4.0` with `--strict`. Check the retry limit before using it: after `3` failed attempts, the workflow requires a user decision.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill do-and-judge -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill do-and-judge -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill do-and-judge -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NeoLabHQ/context-engineering-kit do-and-judge
```

2. **Manually: put the files in place**
- File: `.github/skills/do-and-judge/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill do-and-judge -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/do-and-judge
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill do-and-judge -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/NeoLabHQ/context-engineering-kit/tree/HEAD/skills/do-and-judge/SKILL.md

## When to use it
- delegate a task to a separate implementation sub-agent
- generate task-specific evaluation criteria
- check a result with an independent judge
- retry work using the judge's feedback

## Example prompts
- \`/do-and-judge Refactor the UserService class to use dependency injection`
- \`/do-and-judge Review error handling in the API --strict`
- \`/do-and-judge Add tests for the new function --model sonnet`

## Similar
- [write-judge-prompt](https://affpapa.org/en/nevibecode/skills/write-judge-prompt.md) — skill · 1100 installs
- [math-proof-judge](https://affpapa.org/en/nevibecode/agents/math-proof-judge.md) — subagent · ★ 44635
- [principal-engineering](https://affpapa.org/en/nevibecode/skills/principal-engineering.md) — skill · 18000 installs
- [bmad-agent-dev](https://affpapa.org/en/nevibecode/skills/bmad-agent-dev.md) — skill · 11900 installs
- [printing-press-score](https://affpapa.org/en/nevibecode/skills/printing-press-score.md) — skill · 6400 installs
- [principle-prove-it-works](https://affpapa.org/en/nevibecode/skills/principle-prove-it-works.md) — skill · 5200 installs

From the same set: [neolabhq/context-engineering-kit](https://affpapa.org/en/nevibecode/by/neolabhq/context-engineering-kit.md) — 64 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