minimal-run-and-audit
We need to translate the given English text into Japanese, preserving the name "minimal-run-and-audit" if it appears. The text is a description of a skill. The instruction says: "Translate only the text inside <text>. Do not include the name unless it appears in the source text." The name "minimal-run-and-audit" does not appear in the source text. So we just translate the description. Also preserve product names, protocol names, URLs, numbers, technical terms. The text includes "Rigor Run skill", "README-first deep learning repo reproduction", "smoke test", "documented inference or evaluation command", "repro_outputs/", "patch notes", etc. We need to translate naturally into Japanese while keeping those terms as is or with appropriate Japanese equivalents? The instruction says "preserve product names, protocol names, URLs, numbers, and technical terms." So "Rigor Run skill" might be a product name? It says "Rigor Run skill" - likely a proper name. Keep as is. "README-first
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill minimal-run-and-auditminimal-run-and-audit
Use this as the Rigor Run skill. The installed slug remains
minimal-run-and-audit for compatibility.
Use the shared operating principles in
../../references/agent-operating-principles.md; this skill should make run
evidence auditable without turning every command into a rigid protocol.
When to apply
- After a reproduction target and setup plan exist.
- When the main skill needs execution evidence and normalized outputs.
- When a smoke test, documented inference run, documented evaluation run, or other short non-training verification is appropriate.
- When the user already knows what command should be attempted and wants execution plus reporting only.
When not to apply
- During initial repo scanning.
- When environment or assets are still undefined enough to make execution meaningless.
- When the task is a literature lookup rather than repository execution.
- When the user is still deciding which reproduction target should count as the main run.
Clear boundaries
- This skill owns normalized reporting for an attempted command.
- It may receive execution evidence from the main skill or a thin helper.
- It does not choose the overall target on its own.
- It does not perform broad paper analysis.
- It does not own training startup, resume, or long-running training state.
- It should not normalize risky code edits into acceptable practice.
- It must not hide changes that alter evaluation, preprocessing, checkpoints, metrics, or other scientific meaning.
Input expectations
- selected reproduction goal
- runnable commands or smoke commands
- environment and asset assumptions
- optional patch metadata
Output expectations
- execution result summary
- standardized
repro_outputs/files SCIENTIFIC_CHANGELOG.mdfor changed scientific meaning and evidence statusCOMPARABILITY_REPORT.mdfor README/paper/baseline comparability- clear distinction between verified, partial, and blocked states
PATCHES.mdwhen repo files changed
Notes
Use references/reporting-policy.md, ../../references/research-rigor-principles.md, scripts/run_command.py, and scripts/write_outputs.py.