# traiage-review

Traiage-review prioritizes repository changes and pinpoints files that human reviewers must inspect first.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 381 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/traiage-review/SKILL.md
- Updated: 2026-08-26
- HTML: https://affpapa.org/en/nevibecode/skills/traiage-review

## What it does

The skill operates strictly as an orchestrator agent. It inspects repository state to pick the right review workflow: local working tree diffs, branch changes against `origin/main` or `origin/master`, or an isolated commit hash. It triggers four specialized sub-agents in parallel (`change-story-agent`, `change-impact-agent`, `change-failure-agent`, and `change-expectation-agent`) to score failure likelihood.

The final candidate list blends top picks from each agent with five random files selected by an internal Python sampling script. The orchestrator is restricted to read-only `git` operations and does not alter working tree files. If you run it on the clean default branch without local diffs, it terminates immediately.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NeoLabHQ/context-engineering-kit traiage-review
```

2. **Manually: put the files in place**
- File: `.github/skills/traiage-review/SKILL.md`

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill traiage-review -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/traiage-review/SKILL.md

## When to use it
- prioritize high-risk files across large git pull requests
- filter out routine edits during local diff inspection
- evaluate failure risk for a specific commit hash
- generate a balanced random sample of modified files for audit

## Example prompts
- Prioritize files needing review in my local git changes using traiage-review
- Run traiage-review on this branch against origin/main
- Use traiage-review to inspect the latest commit

## Similar
- [review](https://affpapa.org/en/nevibecode/skills/parcadei-review.md) — skill · 519 installs
- [ce-work](https://affpapa.org/en/nevibecode/skills/ce-work.md) — skill · 3600 installs
- [copilot-delegate](https://affpapa.org/en/nevibecode/skills/copilot-delegate.md) — skill · 3100 installs
- [open-code-review](https://affpapa.org/en/nevibecode/skills/open-code-review.md) — skill · 6900 installs
- [difit-review](https://affpapa.org/en/nevibecode/skills/difit-review.md) — skill · 1900 installs
- [hunk-review](https://affpapa.org/en/nevibecode/skills/hunk-review.md) — skill · 1800 installs

From the same set: [neolabhq/context-engineering-kit](https://affpapa.org/en/nevibecode/by/neolabhq/context-engineering-kit.md) — 55 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