mrge-io

Fetches unresolved AI review comments on the current pull request, decides which issues are real and worth addressing, fixes the worthwhile ones, commits and pushes the changes, and resolves the reviewed threads. Use when the user asks to check all PR comments, refers to PR comments or issues, or wants PR review feedback handled end to end.

Iteratively improves code by running cubic AI reviews, fixing issues, and re-reviewing until clean or a maximum number of iterations is reached. Use when the user wants to polish their changes, says "loop until clean", "keep reviewing", or wants to fully optimize code quality before merging.

Queries cubic's AI-generated wiki to provide architectural context about the codebase. Answers questions about how systems work, how components connect, and codebase design. Use when the user asks about architecture, system design, onboarding, or "how does X work".

Surfaces the team's coding patterns and conventions learned by cubic from senior reviewer feedback and codebase analysis. Use when the user is writing code, asking about team standards, or wondering "how does this team do X".

Runs a local cubic AI code review using the CLI on uncommitted changes or the current branch diff. Surfaces issues grouped by priority and offers to fix them. Use when the user wants a pre-commit or pre-PR quality check, says "review my code", or asks "anything I should fix".