Judges Code Review
Version updated for https://github.com/KevinRabun/judges to version v3.107.0.
- This action is used across all versions by 0 repositories.
Action Type
This is a Composite action.
Go to the GitHub Marketplace to find the latest changes.
Action Summary
The “Judges Panel” GitHub Action evaluates AI-generated code across 45 specialized domains, including security, compliance, accessibility, and architectural design, using a combination of offline deterministic analysis and LLM-powered deep reviews. It automates quality assessment by identifying and addressing common AI code failure modes, generating plain-language risk summaries, and providing auto-fix patches. Key capabilities include context-aware evaluation, SARIF and markdown report generation, and integration with MCP-native tools for streamlined workflows.
Release notes
Full Changelog: https://github.com/KevinRabun/judges/compare/v3.106.0...v3.107.0