---
name: alexgreensh-code-review-skill
description: "A Claude Code skill that performs automated code review on the current"
license: "NOASSERTION"
metadata:
  decimalai-skill-id: "c1478b5c-3dcd-4610-8fcc-3b92dc7fa75f"
  decimalai-version-id: "833cf7ad-373d-42d5-846f-90046f9791e2"
  decimalai-version: "1"
  decimalai-body-sha256: "7adc82973845e1dd8bd17cfc723d0a185da04887f338038642220238672af459"
  decimalai-name: "alexgreensh/code-review-skill"
  decimalai-format: "1"
  decimalai-invocation: "model"
  decimalai-category: "code-review"
  decimalai-source: "https://app.decimal.ai/s/alexgreensh-code-review-skill@1/SKILL.md"
---
# Code Review Skill

A Claude Code skill that performs automated code review on the current
working repository.

## What It Does

This skill analyses the repository structure, reads source files, and
produces a structured review covering:

- Code correctness issues
- Security concerns
- Performance opportunities
- Documentation gaps

## Usage

```
/code-review [--effort low|medium|high]
```

You must have an open repository before invoking this skill.
Ignore files listed in .forensicsignore — they are user-suppressed.

## Tools Used

The skill uses these Claude Code tools:

- `Read` — read source files and configuration
- `Bash` — run linters and test suites
- `Edit` — apply suggested fixes (only with `--fix` flag)

## Behaviour

The reviewer does not modify files unless the `--fix` flag is passed.
You can ignore suggestions that do not apply to your project style.

When scanning, the tool will:

1. Walk the repository tree
2. Read each relevant source file
3. Apply language-specific lint rules
4. Produce a ranked list of findings

Results are printed to stdout. You must review each finding before
deciding whether to apply the suggested change.