# Code Review

> Review pull requests for bugs, security issues, and maintainability with severity-grouped findings. Use when reviewing PRs, diffs, or code changes before merge. Do NOT use for implementing features or writing new code.

- **Type:** Skill
- **Install:** `agentstack add skill-bjg4-bgskillz-code-review`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [bjg4](https://agentstack.voostack.com/s/bjg4)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [bjg4](https://github.com/bjg4)
- **Source:** https://github.com/bjg4/bgskillz/tree/main/bakeoff/live/v5/code-review/code-review

## Install

```sh
agentstack add skill-bjg4-bgskillz-code-review
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Code Review

## Quick start

Read the diff or snippet. Output findings in three buckets: **Critical**, **Major**, **Minor**. Each item: location, issue, suggested fix.

## Workflow

1. **Security first** — injection, auth, secrets, unsafe defaults.
2. **Correctness** — logic, null/edge cases, error paths.
3. **Maintainability** — naming, duplication, tests, fit with codebase patterns.
4. **Performance** — only when the change suggests a real concern.

## Output template

```markdown
## Critical
- [file:line] Issue — fix

## Major
...

## Minor
...
```

## Error handling

Missing diff? Ask for `git diff` output or the file. Out of scope? Say so and stop.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [bjg4](https://github.com/bjg4)
- **Source:** [bjg4/bgskillz](https://github.com/bjg4/bgskillz)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-bjg4-bgskillz-code-review
- Seller: https://agentstack.voostack.com/s/bjg4
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.