massgen/massgen-refinery

evaluate

Quick one-shot evaluation of work against quality criteria. Generates criteria, runs the round-evaluator, and presents the verdict. Lighter than /refine — does not auto-improve, just evaluates. Use for pre-PR quality checks or getting a critical assessment.

Idioma do texto original: inglês

massgen-run

Launch a MassGen multi-agent run. Multiple LLM backends (codex, gemini, claude, grok) collaborate on a task via voting and consensus. Runs in Docker containers by default.

Idioma do texto original: inglês

refine

Run a MassGen-style quality refinement loop. Generates eval criteria, produces/improves answers with subagent help, regression-guards before submission, then evaluates with round-evaluator and trace-analyzer in parallel. Invoke with /refine.

Idioma do texto original: inglês

team-massgen-run

Launch parallel MassGen step mode processes — the lead manages all background tasks directly, tracks answers/votes, detects consensus, and synthesizes the result.

Idioma do texto original: inglês

read-media

Analyze media files (images, video, audio) using AI vision and audio models with a critical-first lens. Use for output-first verification — render your deliverable, then read_media to see what it actually looks like. Distinguishes fundamental issues from…

Idioma do texto original: inglês