Pavel-Tk

Pavel-Tk/auto-data-scientist

Agent Claude Code

ML experiment execution worker. Receives a hypothesis, writes a self-contained Python training script, executes it, self-debugs on failure (up to 3 attempts), and returns structured results. Use when the auto-research skill needs to run an ML experiment.

Pavel-Tk/auto-data-scientist

Skill Claude CodeCodex

Autonomous ML research loop. Handles initialization (interactive dataset scan, EDA, user interview, strategy planning) and autonomous iteration (hypothesis selection, experiment execution via worker agent, state updates). Use when the user says "start research", "auto research", "run ML research", "initialize…