minimal-run-and-audit
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized repro_outputs/ files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target…
- installs 8w
- 160,070
- 30-day movement
- starts with the next reading
- Related entries
- 1
- Connections
- 0
minimal-run-and-audit is a Rigor Run skill for README-first deep learning repo reproduction. It captures or normalizes evidence from a selected smoke test or documented inference/evaluation command and writes standardized `repro_outputs/` files, plus patch notes when repository files changed.
Reach for it when a reproduction target and setup plan already exist and you need standardized execution evidence and normalized output files rather than orchestration or setup.
Use it to
- Capture evidence from a selected smoke test command
- Normalize documented inference or evaluation command output into repro_outputs/
- Write patch notes after repository files changed
- Record scientific-meaning changes in SCIENTIFIC_CHANGELOG.md
- Produce comparability reporting for an attempted command
For AI coding agents doing deep learning repo reproduction runs
- Host repository
- lllllllama/RigorPilot-Skills
- Installs, lifetime
- 450k
- Installs, 8 weeks
- 160k
- Host stars
- 489
- Host language
- Python