Loading...
Loading...
Found 4 Skills
Runs ML experiments reproducibly — single runs or autonomous BFS batches. Single mode: isolated venv, time-budgeted, failure-handled, logs to RESEARCH.md. BFS mode (opt-in): designs N hypotheses, runs each for a fixed budget, compares via a single verifiable metric, keeps improvements and git-resets failures — fully autonomous until done. Respects the RESEARCH.md supervision policy for notifications, approvals, and stop limits. Trigger phrases: "run experiment", "train model", "explore design space", "find best config", "autoresearch".
Use when resolving non-trivial merge conflicts, choosing a merge strategy, or undoing a merge — covers -X options, diff3 markers, strategy vs option, reset vs revert -m, and re-merging reverted branches
Reset the working directory for the next task by ensuring no uncommitted changes exist, then switching to the main branch and pulling latest.
Undo the last commit while keeping changes staged. Use when you need to fix a commit message or add missing files.