What problem does it solve?
It resolves the uncertainty of whether an AI-completed Task Group is correct and review-ready by turning the review step into a structured, evidence-backed GitHub issues workflow with a mandatory human decision gate.
Core Features & Use Cases
- Evidence-first review workflow: Selects the right change, verifies the target Task Group is completed, and presents existing GitHub feedback before proceeding.
- Quality-check driven Review Report: Runs automated quality checks across code quality, spec coverage, functional verification, architecture, and performance risk detection, and compiles results into a Review Report for the human gate.
- Strict review guardrails: Prevents auto-approve/auto-reject, avoids label changes and issue closure until the user explicitly approves, and never fabricates test/screenshot results.
Quick Start
Have your AI run the review for the current completed Task Group on GitHub and then ask you to approve, reject, or discuss based on the generated Review Report.