Learning Loop

The session-side surface of robium's learning engine: consolidate captured flags and learnings into evidence-counted observations, absorb ready observations into anchor-targeted skill-edit PRs via the deterministic delta pipeline, refine (prune/dedup/staleness) through the same pipeline, run blind variant A/B on contested edits ('experiment', 'A/B this edit', 'try competing fixes'), deep-verify unverified examples in pinned fixtures ('deep verify', 'verify the examples'), and report loop health. Use when: 'consolidate', 'absorb', 'run the loop', 'update my skills', 'absorb these learnings', 'refine the skills', 'learning loop status', end-of-block retros, promoting .robium/queue.jsonl flags, or drafting an absorb/refine PR. Everything before git merge may run autonomously; nothing lands on main skills/** without a human merge. Not for: mining external repos (mining), fresh skill authoring or the quality bar (skill-author), building robot applications (architect).

robium-ai Updated 108 repo stars
robium

File contents

robium-ai/robium commit f5ab0e4374 Runs: robium-ai/mining

Frequently asked questions

npx get-skill add robium-ai/learning-loop-4