review-python

Review Python and FastAPI code with linters and specialized subagents.

Updated Jul 18, 2026

Search Tags:#automation #tdd #fastapi #python #static-analysis #code-review

Ready to run

npx skills add https://github.com/arthrod/conejo-skills --skill review-python-arthrod

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: review-python
Source: https://github.com/arthrod/conejo-skills/tree/main/skills/review-python
Command: npx skills add https://github.com/arthrod/conejo-skills --skill review-python-arthrod

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill addresses the inconsistency and oversight common in manual code reviews by providing a structured, multi-agent verification process that enforces project-specific coding doctrines and framework best practices.

Core Features & Use Cases

Automated Quality Gates: Integrates project linters (Ruff, Mypy) to ensure style and type safety before human-level logic review.
Specialized Agent Dispatch: Automatically detects technologies like Pydantic-AI, SQLAlchemy, or Postgres and spawns domain-specific subagents for deep analysis.
Use Case: Use this during a pull request to ensure that complex FastAPI backend changes adhere to red-green TDD principles and framework-specific idioms without missing subtle logic errors.

Quick Start

Run the review-python skill on the current directory to perform a comprehensive code review of all recent changes.

Frequently Asked Questions about review-python

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

FAQPage Schema

How do I automate Python and FastAPI code reviews for pull requests?▼

Automating Python and FastAPI code reviews involves orchestrating specialized subagents to verify logic, type safety, and framework-specific patterns. This skill enforces red-green TDD and architectural doctrines by dispatching domain-specific verification tasks across multiple technology stacks.

How does automated code review detect and verify framework-specific patterns in FastAPI projects?▼

Automated code review detects technologies like Pydantic-AI, SQLAlchemy, or Postgres and spawns domain-specific subagents for deep analysis. This multi-agent verification process enforces project-specific coding doctrines and framework best practices during pull request workflows.

Do I need project-level linters configured to run automated Python code reviews?▼

Yes, automated Python code reviews require integration with project-level linters like Ruff and Mypy. These tools ensure style and type safety are verified before the multi-agent system performs deeper human-level logic review on your FastAPI changes.

What is the best way to enforce red-green TDD principles during backend code reviews?▼

The best way to enforce red-green TDD principles is using a structured, multi-agent verification process that targets pull request workflows. This approach automatically verifies adherence to testing doctrines and architectural standards without missing subtle logic errors.

Can I use this automated code review skill on a directory with recent changes?▼

Yes, you can run this automated code review skill on the current directory to perform a comprehensive analysis of all recent changes. It orchestrates specialized subagents to evaluate logic, type safety, and framework-specific patterns.

What are the limitations of using multi-agent subagents for Python static analysis?▼

The multi-agent approach for Python static analysis focuses on pull request workflows and requires project-level linters to be integrated. It relies on detecting specific technologies like SQLAlchemy or Postgres to dispatch domain-specific verification tasks effectively.