Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

run-train — Claude Code skill: training runs

Runs a selected training command and organizes the resulting evidence. Use it for startup checks, short-run verification, full training kickoff, or resume handling.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add lllllllama/RigorPilot-Skills --skill run-train -a claude-code
Open on GitHub

What run-train does

Have a training goal, runnable command, and environment and asset assumptions ready first. The skill runs the selected command; it does not choose the research goal. Check those assumptions before starting, since environment setup is outside its scope.

It organizes run evidence under train_outputs/, including the command, config, seed, logs, checkpoints, status, and metrics. The output set includes SUMMARY.md, COMMANDS.md, LOG.md, SCIENTIFIC_CHANGELOG.md, COMPARABILITY_REPORT.md, and status.json.

The training policy is in references/training-policy.md; scripts/run_training.py runs training and scripts/write_outputs.py writes the outputs. This skill is not for exploratory sweeps, speculative code changes, or end-to-end orchestration. It also does not handle inference-only or evaluation-only runs.

What it helps with

  • check that a training run starts
  • verify a short training run
  • kick off a selected full training run
  • resume training and record its status
  • organize run logs, checkpoints, and metrics

Example prompts for the agent

  • Run the selected training command in startup verification mode and record the results under `train_outputs/`.
  • Do a short-run verification with the current config; capture the command, seed, and metrics.
  • Resume training with the selected command and update the status, logs, and checkpoint record.

How to install run-train

1Skills CLI (Vercel)

npx skills add lllllllama/RigorPilot-Skills --skill run-train -a claude-code

2Manually: put the files in place

~/.claude/skills/run-train/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/run-train/

From the same set9

The whole set →
repo-intake-and-plan lllllllama Scans a repository through its README and project files, then builds a small reproduction plan. Use it before running experiments. Claude Code CX Codex Cursor +1 474,500installs minimal-run-and-audit lllllllama Captures and normalizes execution evidence from deep learning smoke tests and inference commands into standardized repro_outputs/ files. Claude Code CX Codex Cursor +1 474,400installs env-and-assets-bootstrap lllllllama Prepares environment and checkpoint/dataset paths before the first run of a README-documented repo. Claude Code CX Codex Cursor +1 474,300installs ai-research-explore lllllllama Governs deep learning research exploration on top of an existing baseline. It isolates candidate experiments and generates structured comparison reports. Claude Code CX Codex Cursor +1 335,600installs analyze-project lllllllama Reads a deep learning repository and maps its structure, entrypoints and suspicious spots. Changes nothing, runs no heavy jobs. Claude Code CX Codex Cursor +1 335,500installs ai-research-reproduction lllllllama This skill guides a repository-grounded reproduction run from its README to an evidence bundle. Use it to test a documented model run without quietly changing the experiment. Claude Code CX Codex Cursor +1 335,300installs explore-code lllllllama A skill for cautious code experiments in deep learning repositories: it transplants modules and adapts architectures on an isolated branch, with rollback-aware records. Claude Code CX Codex Cursor +1 335,000installs explore-run lllllllama Plans bounded exploratory machine learning runs with comparability caveats and saves summaries to explore_outputs. Claude Code CX Codex Cursor +1 334,700installs

Similar

eval-harness affaan-m A skill for eval-driven development: it sets pass/fail criteria before you write code and tracks agent reliability with pass@k and pass^k. Claude Code CX Codex Cursor +1 4,700installs agent-architecture-audit affaan-m This skill checks agent and LLM applications across 12 layers. Use it when an agent degrades and the failing layer is hard to locate. Claude Code CX Codex Cursor +1 4,700installs pytorch-patterns affaan-m This skill guides PyTorch model, training-loop, and data-loading work with practical patterns. Use it when reviewing code or tracking down runs that fail to reproduce. Claude Code CX Codex Cursor +1 4,700installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. Claude Code Claude.ai 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. Claude Code CX Codex 237,746installs

Questions about run-train

How do I install run-train in Claude Code?

Run npx skills add lllllllama/RigorPilot-Skills --skill run-train -a claude-code. The skill file is at ~/.claude/skills/run-train/SKILL.md.

What does run-train do?

It runs a selected training command and records run status, config, seed, logs, checkpoints, and metrics under train_outputs/.

What should I have ready before using run-train?

Prepare the training goal, a runnable command, environment and asset assumptions, and a run mode: startup check, short-run verification, full kickoff, or resume.

Source text

SKILL.md · MIT 
---
name: run-train
description: Rigor 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 evidence written to standardized `train_outputs/`. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.
---

# 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`.

© lllllllama · MIT · lllllllama/RigorPilot-Skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor