Skill

run-train

From lllllllama-ai-paper-reproduction-skill

Executes documented training commands in deep learning research repos for startup verification, short-run checks, full kickoff, or resume, capturing status, checkpoints, and metrics to train_outputs/.

Python

ai-ml

npx claudepluginhub lllllllama/ai-research-workflow-skills

Tool Access

This skill uses the workspace's default tool permissions.

Preview

- When the training command has already been selected and should be executed conservatively.

Supporting Assets

agents/openai.yamlreferences/training-policy.mdscripts/run_training.pyscripts/write_outputs.py

SKILL.md

Similar Skills

model-checkpoint-manager

2.0k

Manages model checkpoints in ML training workflows using PyTorch, TensorFlow, or scikit-learn. Offers guidance, code generation, and best practices for saving/loading models during training, tuning, and tracking.

5 tools

jeremylongshore-claude-code-plugins-plus-skills

Auto Deep Researcher 24x7

Autonomously runs deep learning experiments 24/7 in a THINK-EXECUTE-REFLECT loop with zero-cost GPU monitoring, Leader-Worker architecture, and constant-size memory.

aradotso-trending-skills-37

minimal-run-and-audit

Executes smoke tests or documented inference/evaluation commands in AI repos, captures evidence, normalizes into repro_outputs/ files, and adds patch notes for repo changes.

4 files

lllllllama-ai-paper-reproduction-skill

Stats

Stars10

Forks0

Last CommitApr 1, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

run-train

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.

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/status.json

Notes

Use references/training-policy.md, scripts/run_training.py, and scripts/write_outputs.py.

run-train

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.

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/status.json

Notes

Use references/training-policy.md, scripts/run_training.py, and scripts/write_outputs.py.