Explore Run

When you want to run quick experiments on a deep learning repo without committing to full training runs, this handles the planning and execution of exploratory trials like small-subset validation, short-cycle probes, or batch sweeps. It ranks candidate runs by cost, success rate, and expected gain, then writes structured summaries to explore_outputs/ with fair-comparison caveats so you don't accidentally overstate results. The boundary is clear: this is for explicit exploratory work only, not trusted baselines or production training. It pairs well with minimal-run-and-audit for actual execution and keeps experiment state isolated from your main research branch.

skills.sh installs: 232
GitHub stars: 289
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add lllllllama/ai-paper-reproduction-skill --skill explore-run --agent claude-code

Installs into .claude/skills of the current project.

Files

explore-run

Use this as the Rigor Improve / Rigor Explore run leaf skill. The installed slug remains explore-run for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide candidate run planning while preserving model judgment about the active repo.

When to apply

When the researcher explicitly authorizes exploratory runs.
When the task is a small-subset validation, short-cycle training probe, batch sweep, idle-GPU search, or quick transfer-learning trial.
When the output should rank candidate runs rather than certify trusted success.