run-train
installsforks
How to install run-train?
lllllllama/rigorpilot-skills/run-train
$npx -y skills add lllllllama/RigorPilot-Skills --skill run-trainRigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric ev
SKILL.md
| 1 | # run-train |
| 2 | |
| 3 | Use this as the Rigor Train skill. The installed slug remains `run-train` for |
| 4 | compatibility. |
| 5 | |
| 6 | Use the shared operating principles in |
| 7 | `../../references/agent-operating-principles.md`; this skill should keep |
| 8 | training evidence bounded while leaving repository-specific monitoring details |
| 9 | to the model. |
| 10 | |
| 11 | ## When to apply |
| 12 | |
| 13 | - When the training command has already been selected and should be executed conservatively. |
| 14 | - When the researcher wants startup verification, short-run verification, full training kickoff, or resume handling. |
| 15 | - When the run needs structured training status, checkpoint, and metric reporting. |
| 16 | |
| 17 | ## When not to apply |
| 18 | |
| 19 | - When the main task is environment setup or asset download. |
| 20 | - When the researcher wants inference-only or evaluation-only execution. |
| 21 | - When the task is speculative exploration, multi-variant sweeps, or autonomous idea implementation. |
| 22 | - When the user still needs repository intake or paper gap resolution. |
| 23 | |
| 24 | ## Clear boundaries |
| 25 | |
| 26 | - This skill executes a selected training command and normalizes the resulting evidence. |
| 27 | - It does not choose the overall research goal on its own. |
| 28 | - It does not own exploratory branching or speculative code adaptation. |
| 29 | - It should record partial, blocked, resumed, and kicked-off states clearly. |
| 30 | - It should preserve reproducibility context such as configs, seeds, |
| 31 | checkpoints, logs, metrics, and runtime assumptions when available. |
| 32 | |
| 33 | ## Input expectations |
| 34 | |
| 35 | - selected training goal |
| 36 | - runnable training command |
| 37 | - environment and asset assumptions |
| 38 | - run mode such as startup verification, short-run verification, full kickoff, or resume |
| 39 | |
| 40 | ## Output expectations |
| 41 | |
| 42 | - `train_outputs/SUMMARY.md` |
| 43 | - `train_outputs/COMMANDS.md` |
| 44 | - `train_outputs/LOG.md` |
| 45 | - `train_outputs/SCIENTIFIC_CHANGELOG.md` |
| 46 | - `train_outputs/COMPARABILITY_REPORT.md` |
| 47 | - `train_outputs/status.json` |
| 48 | |
| 49 | ## Notes |
| 50 | |
| 51 | Use `references/training-policy.md`, `../../references/deep-learning-experiment-principles.md`, `scripts/run_training.py`, and `scripts/write_outputs.py`. |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
