mcpField
R
run-train

run-train

github.com/lllllllamaDocuments486339.2k installsUpdated 5w ago
Repository

About run-train

run-train is the Rigor Train skill for conservatively executing a selected training command and normalizing the resulting evidence. It is aimed at researchers who need startup checks, short runs, full kickoffs, or resumes.

Key features

  1. 01Executes a selected training command conservatively
  2. 02Supports startup, short-run, full, and resume modes
  3. 03Records partial, blocked, resumed, and kicked-off states
  4. 04Produces structured checkpoint, metric, and log evidence
  5. 05Preserves configs, seeds, and runtime assumptions

Use cases

  1. 01Running startup or short-run verification on a chosen training command
  2. 02Kicking off full training with status and metric reporting
  3. 03Resuming an interrupted training run from checkpoints

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/lllllllama/rigorpilot-skills --skill run-train

After installing, type/run-trainin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
training-policy.md
scripts/
run_training.py
write_outputs.py

Details

From the project README

run-train

Use this as the Rigor Train skill. The installed slug remains run-train for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should keep training evidence bounded while leaving repository-specific monitoring details to the model.

When to apply

  • When the training command has already been selected and should be executed conservatively.
  • When the researcher wants startup verification, short-run verification, full training kickoff, or resume handling.
  • When the run needs structured training status, checkpoint, and metric reporting.

When not to apply

  • When the main task is environment setup or asset download.
  • When the researcher wants inference-only or evaluation-only execution.
  • When the task is speculative exploration, multi-variant sweeps, or autonomous idea implementation.
  • When the user still needs repository intake or paper gap resolution.

Clear boundaries

  • This skill executes a selected training command and normalizes the resulting evidence.
  • It does not choose the overall research goal on its own.
  • It does not own exploratory branching or speculative code adaptation.
  • It should record partial, blocked, resumed, and kicked-off states clearly.
  • It should preserve reproducibility context such as configs, seeds, checkpoints, logs, metrics, and runtime assumptions when available.

Input expectations

  • selected training goal
  • runnable training command
  • environment and asset assumptions
  • run mode such as startup verification, short-run verification, full kickoff, or resume

Output expectations

  • train_outputs/SUMMARY.md
  • train_outputs/COMMANDS.md
  • train_outputs/LOG.md
  • train_outputs/SCIENTIFIC_CHANGELOG.md
  • train_outputs/COMPARABILITY_REPORT.md
  • train_outputs/status.json

Notes

Use references/training-policy.md, ../ai-research-reproduction/references/deep-learning-experiment-principles.md, scripts/run_training.py, and scripts/write_outputs.py.

Comments

Markdown supported