Version updated for https://github.com/markhuangai/ai-pr-reviewer to version v1.1.5. This action is used across all versions by 1 repositories. Action Type This is a Node action using Node version 24. Go to the GitHub Marketplace to find the latest changes. Action Summary This GitHub Action automates the review process by leveraging the Claude Agent SDK to generate AI reviews for pull requests in any repository. It ensures that each review runs in an isolated session and is based on a pristine head checkout, using read-only tools to inspect the repository’s history without affecting the current state. The action allows specifying multiple prompts for different types of checks and handles sensitive information securely through environment variables or secrets.

Version updated for https://github.com/markhuangai/ai-pr-reviewer to version v1.1.2. This action is used across all versions by 1 repositories. Action Type This is a Node action using Node version 24. Go to the GitHub Marketplace to find the latest changes. Action Summary This action is a goal-driven AI-powered GitHub Action designed to review pull requests automatically. It uses Claude Agent SDK sessions for isolated reviews, supporting multiple goals and configurations. The action automates security checks, code correctness verification, and other tasks by inspecting the repository history and relevant conversation. Users can configure model parameters and effort levels for optimal performance.

Version updated for https://github.com/markhuangai/ai-pr-reviewer to version v1.1.0. This action is used across all versions by 1 repositories. Action Type This is a Node action using Node version 24. Go to the GitHub Marketplace to find the latest changes. Action Summary The AI PR Reviewer GitHub Action automates pull request reviews using Goal-driven, MCP-enabled JavaScript. It leverages a pre-installed Anthropic Claude Agent SDK to analyze code changes and suggest improvements based on user-defined prompts. The action runs isolated review sessions with automated compaction, read-only repository tools, and HTTP MCP servers. Reviewed findings are merged and deduplicated before posting as a single GitHub pull request review or written to the workflow run summary.