---
name: 'review'
description: 'Performs a structured code review of staged changes, a specific PR, or a range of commits. Evaluates code quality, adherence to domain rules, security concerns, test coverage, and architectural alignment.'
generated_by: 'agentkit-forge'
last_model: 'sync-engine'
last_updated: '2026-03-01'
# Format: YAML frontmatter + Markdown body. Claude skill definition.
# Docs: https://docs.anthropic.com/en/docs/claude-code/memory
---

<!-- GENERATED by AgentKit Forge v0.2.2 — DO NOT EDIT -->
<!-- Source: .agentkit/spec + .agentkit/overlays/chaufher -->
<!-- Regenerate: pnpm -C .agentkit agentkit:sync -->

# review

Performs a structured code review of staged changes, a specific PR, or a range of commits. Evaluates code quality, adherence to domain rules, security concerns, test coverage, and architectural alignment.

## Usage

Invoke this skill when you need to perform the `review` operation.

## Instructions

1. Parse any arguments provided
2. Scan relevant files to understand the current state
3. Execute the task following project conventions
4. Validate the output against quality gates
5. Report results clearly

## Project Context

- Repository: chaufher
- Default branch: main
- Tech stack: typescript, csharp

## Conventions

- Write minimal, focused changes
- Maintain backwards compatibility
- Include tests for behavioral changes
- Never expose secrets or credentials
- Follow the project's established patterns