code-review

Review code changes against project standards and architecture rules.

3|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/Develonaut/bnto --skill code-review-develonaut
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/Develonaut/bnto/tree/main/.claude/skills/code-review
Command: npx skills add https://github.com/Develonaut/bnto --skill code-review-develonaut

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audits code changes against project standards to identify deviations, enforce quality, and prevent regressions.

Core Features & Use Cases

  • Automated checklist: validates conformity with CLAUDE.md, rules/code-standards.md, and architecture guidelines.
  • Persona-driven review: maps changed files to relevant skills and applies targeted checks across frontend, Rust engine, and core packages.
  • Actionable reports: generates a clear review report with violations and suggested fixes.

Quick Start

Review the latest changes against the project standards and generate a quality-focused code review report.

Frequently Asked Questions about code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate a code review for standards compliance and architecture rules?

Automate a code review by mapping changed files to relevant personas and checking diffs against CLAUDE.md and rules/code-standards.md. The process evaluates Rust engine, frontend, and core packages to enforce project standards and identify deviations.

What is a persona-driven code review and how does it work?

Persona-driven code review maps changed repository files to relevant skills and applies targeted checks across frontend, Rust engine, and core packages. It evaluates code changes against architecture guidelines to ensure adherence to project-specific standards.

Can I generate a code review report that suggests fixes for standards violations?

Yes, you can generate a code review report that identifies violations and suggests fixes. The review output provides actionable feedback by evaluating diffs against CLAUDE.md and rules/code-standards.md to prevent regressions.

Does the code review process require direct access to the repository to analyze diffs?

Repository access is required to analyze diffs, enforce rules, and produce a structured review report. The audit process needs to evaluate code changes directly against project standards and architectural rules.

What's the best way to enforce code quality and prevent regressions across Rust and frontend packages?

The best way to enforce code quality is applying an automated checklist that validates conformity with CLAUDE.md, rules/code-standards.md, and architecture guidelines. This maps changed files to relevant personas across Rust engine, frontend, and core packages.

When do I need a structured code review report instead of just running a linter?

You need a structured code review report when evaluating diffs for architectural compliance across Rust engine, frontend, and core packages. Unlike standard lint, it maps changed files to personas and applies targeted checks against project-specific standards.