explore-run
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with fair-comparison caveats and no-overclaim summaries in explore_outputs/. Do not use for end-to-end…
- installs 8w
- 186,665
- 30-day movement
- starts with the next reading
- Related entries
- 1
- Connections
- 0
explore-run is a leaf skill in the Rigor Improve / Rigor Explore suite for running bounded exploratory experiments in deep learning research repositories. It handles explicitly authorized small-scale runs — subset validations, short training probes, batch sweeps, idle-GPU searches — and writes fair-comparison summaries into `explore_outputs/`.
It gives you a scoped, non-overclaiming path for exploratory runs without touching trusted baseline execution or end-to-end exploration orchestration.
Use it to
- Run small-subset validation probes
- Execute short-cycle guess-and-check training runs
- Plan batch sweeps with variant_axes and subset_sizes
- Use idle GPUs for quick transfer-learning trials
- Generate comparability and top-runs reports
For Researchers running authorized exploratory deep learning experiments
- Host repository
- lllllllama/RigorPilot-Skills
- Installs, lifetime
- 311k
- Installs, 8 weeks
- 187k
- Host stars
- 487
- Host language
- Python