# code-review-assistant

code-review-assistant walks a change through review goals, heuristics, tooling and team rituals. Handy when reviews run on gut feeling instead of a shared checklist.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 1 install · ★ 21 repo stars
- Author: sandraschi
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/sandraschi/advanced-memory-mcp/tree/HEAD/skills/technical/code-review-assistant/SKILL.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/code-review-assistant

## What it does

Reviews happen in passes here. `modules/core-guidance.md` sets the goal and scope of a change and lists what to ask the author before opening the diff. The checklist, heuristics and language-specific pointers sit in `modules/review-techniques.md`.

Tooling gets its own file: `modules/automation-and-tooling.md` covers bots, static analysis and review metrics. `modules/team-practices.md` deals with written guidelines and onboarding. Open questions are tracked in `modules/known-gaps.md`, and `modules/research-checklist.md` holds the periodic refresh routine.

The material was checked against Google and Microsoft guidance and GitHub metrics from 2024. Last validation is dated 2025-11-08 and the next pass is due 2026-02-01. The licence is proprietary, so read it before dropping this into a company repo.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add sandraschi/advanced-memory-mcp --skill code-review-assistant -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add sandraschi/advanced-memory-mcp --skill code-review-assistant -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add sandraschi/advanced-memory-mcp --skill code-review-assistant -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install sandraschi/advanced-memory-mcp skills/technical/code-review-assistant
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add sandraschi/advanced-memory-mcp --skill code-review-assistant -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/sandraschi/advanced-memory-mcp --path skills/technical/code-review-assistant
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add sandraschi/advanced-memory-mcp --skill code-review-assistant -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/sandraschi/advanced-memory-mcp/tree/HEAD/skills/technical/code-review-assistant/SKILL.md

## When to use it
- triage a change before reading the diff
- build a review checklist for a specific language
- add static analysis and bots to the review flow
- track review metrics instead of guessing
- bring a new reviewer up to speed

## Example prompts
- Review the changes in `src/api` against the checklist in `modules/review-techniques.md`.
- What should I ask the author before I start reading this diff?
- Suggest bots and linters for our review flow, using `modules/automation-and-tooling.md`.

## Similar
- [code-review-pro](https://affpapa.org/en/nevibecode/skills/code-review-pro.md) — skill · 2600 installs
- [mantis-review](https://affpapa.org/en/nevibecode/skills/mantis-review.md) — skill · 1600 installs
- [code-review](https://affpapa.org/en/nevibecode/skills/llama-farm-code-review.md) — skill · 1200 installs
- [review-resolution](https://affpapa.org/en/nevibecode/skills/review-resolution.md) — skill · 2600 installs
- [trailmark-review-gate](https://affpapa.org/en/nevibecode/skills/trailmark-review-gate.md) — skill · 1900 installs
- [go-code-review](https://affpapa.org/en/nevibecode/skills/go-code-review.md) — skill · 1800 installs

From the same set: [sandraschi/advanced-memory-mcp](https://affpapa.org/en/nevibecode/by/sandraschi/advanced-memory-mcp.md) — 3 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
