Does it integrate with standard Elixir tools?

Yes, the verification runner automatically executes mix compile, mix format, Credo, and your test suite to validate changes against standard community benchmarks.

How does it reduce 'AI noise' in code reviews?

The skill uses a context supervisor to compress findings and applies senior-level filters to remove duplicates, low-complexity suggestions, and noise on unchanged code.

Can I target specific parts of my application for review?

Yes, you can use specific arguments like 'security', 'test', 'oban', or 'deploy' to trigger focused reviews by specialized agents.

What are the 'Iron Laws' mentioned in the skill?

Iron Laws are project-specific architectural and coding standards that the 'Iron Law Judge' agent enforces to ensure consistency across the entire codebase.

Does this skill automatically fix my code?

No, the review skill is strictly read-only. It identifies and explains issues without making unauthorized modifications, ensuring you maintain full control over the implementation.

Phoenix & Elixir Code Reviewer

Name: Phoenix & Elixir Code Reviewer
Author: oliver-kriska

byoliver-kriska

•

보안 및 테스팅

Performs deep, multi-agent code reviews for Elixir and Phoenix projects to identify security risks, anti-patterns, and architectural violations.

This skill automates comprehensive code audits for Elixir and Phoenix applications by spawning parallel specialist agents focused on testing, security, Ecto patterns, and Oban workers. It enforces project-specific 'Iron Laws' to ensure architectural consistency while utilizing a sophisticated noise-filtering process to ensure only high-value, senior-level feedback is presented. By integrating with the project's planning phase and prior reviews, it provides context-aware analysis that catches complex bugs and deployment issues before they reach production.

주요 기능

01Automated verification using Mix, Credo, and ExUnit integration

02Iron Law enforcement for strict project architectural standards

03Smart noise filtering to prioritize critical blockers over trivial suggestions

04Context-aware reviews that leverage plan scratchpads and prior findings

0562 GitHub stars

06Parallel multi-agent audits for security, testing, and deployment

사용 사례

01Validating complex Oban background worker logic and deployment configurations

02Running targeted security scans on authentication and session management code

03Auditing new feature implementations before merging into the main branch

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add oliver-kriska/claude-elixir-phoenix review

For use in Claude.ai and ChatGPT

Download Skill