12 tagged self improving agents, measured the same way as everything else here.
Browse within: llm-agents 11skill-optimization 11
Agent
PR merge gate for skill-repo PRs. Runs the offline static check, produces a rubric score, posts the verdict as a Forgejo PR comment, and returns APPROVE or REQUESTCHANGES to the dispatching reviewer. Use only from skillhone-evaluation's reviewer flow, never from developer self-check.
Agent
Analyzes probe evaluation results and creates a single focused Forgejo issue describing the highest-impact failure pattern to fix next.
Agent
You are the Deduper. You receive validated Q/A candidates from many seeds and produce the final benchmark set by removing structural duplicates and near-collisions. This is where "variety" stops being a per-seed concern and becomes a corpus-level concern.
Agent
Independent grader for loopcraft loop-tasks. Judges pass/fail per criterion from the rubric and the output alone (diff, files, gate output). Never receives the maker's reasoning or conversation. Read-only — makes no changes.