AI Agent Skill for Code Review: Optimize Your Workflow

AI Agent Skill for Code Review: Optimize Your Workflow

The AI Agent Skill for Code Review organizes and executes code reviews by analyzing committed changes within draft pull requests. It dispatches a dependency-free review subagent, which processes the code difference using specified review criteria and returns structured findings for further action.

What this skill does

This skill operates within the implementation of committed work. It is specifically designed to run on code that has already been staged, never on unstaged changes. The review process within this skill involves the following steps:

• Accepting input as a diff, which can be a reference range or a pull request number.
• Optionally taking review criteria and context, such as plan-file paths or ticket acceptance criteria, to ensure comprehensive examination.
• Executing a structured review that analyzes correctness, logic errors, edge cases, and adherence to acceptance criteria.
• Returning structured findings highlighting severity, location, problems identified, and suggested fixes.
• Facilitating a review and re-review loop until the human gate exits the review process.

Who it is for

This skill is designed for developers and software development teams employing AI coding agents including Claude Code, Cursor, and Codex. It is beneficial for those looking to streamline and automate parts of their code review processes.

Use cases

Realistic use cases for this skill include:

• Automating the preliminary code review process for development teams, allowing them to streamline workflows and focus on critical issues.
• Facilitating a consistent review experience across multiple pull requests by using default and customizable review criteria.
• Providing structured feedback to developers for each draft pull request, enhancing the clarity and precision of code reviews.

Technical details

This AI agent skill utilizes agentic-workflows and aiapplication technologies for managing the code review process. It operates as a default, dependency-free, installable capability for Claude Code, Cursor, and Codex, ensuring that no additional installations are necessary beyond the essential dossier-mcp. An optional opt-in override is available via the pr-review-toolkit specialist panel for users seeking enhanced functionality.

Source & Licence

This package is built on open-source work published by ethanaubuchon (ethanaubuchon/dossier-tradecraft) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.