Command Claude Code
Runs a Briefing + multi-agent discussion on the training script and config, and optionally applies improvements automatically via a Code Modifier. This is a command that runs the analyze mode of /train independently.
Command Claude Code
Loads research logs and architecture documents into context and starts a research discussion.
Command Claude Code
Updates the project's research state snapshot — a single-file "where we are right now" document designed for fast re-entry and external LLM sharing.
Command Claude Code
Runs the multi-agent review pipeline independently on experiment results. Can be used standalone outside the /train loop; performs a one-time review without ralph-loop integration.
Command Claude Code
Saves the discussion from the current conversation session as a structured discussion document. Runs a single sub-agent in the background so the discussion can continue while saving.
Command Claude Code
A command for automating repeated deep-learning training experiments from a script and configuration file.
Skill Claude CodeCodex
Templates, directory structure, and sync rules for writing research logs and updating README.
Skill Claude CodeCodex
Generate weekly summary. Triggered by requests like "weekly summary", "this week's recap", etc.
Instructions file
Instructions for Hwiyeon/claude-sisyphus-grad, covering claude-sisyphus-grad — project configuration, required settings (modify to fit your project), experiment environment, research directory settings and if research/ is a separate git repo.