7 tagged reinforcement learning, measured the same way as everything else here.
Command Claude Code
Rebase from the latest origin/main, squash the commits from it, and then create a PR on github with intelligent commit messages based on staged changes. Invoke with /create-pr.
Command Claude Code
Generate intelligent commit messages based on staged changes. Invoke with /gen-commit-msg.
Command Claude Code
Intelligent PR code review with dynamic agent allocation based on domains and signals.
Command Claude Code
Suggest a clear and simple commit message for the current changes.
Command Claude Code
Commit, push, and open a PR.
Command Claude Code
Review the comments in a given range and cut them down to only what is needed.