training_hub: Skill for Claude Code

.claude/skills/training-guide/SKILL.md

training-guide is a skill for Claude Code from Red-Hat-AI-Innovation-Team/training_hub. It costs 38 tokens per session (326 once invoked), scanned A, original, Apache-2.0.

A procedure for running a language-model training job from a saved configuration. It checks whether the training software, configuration, and CUDA-capable GPU are ready before starting.

In plain words
What is it for?
Use it to execute configured training jobs, apply command-line overrides, and review the algorithm, checkpoint location, and available loss results.
Why use it?
It avoids starting a run in an unprepared environment and reports the training outcome and saved model checkpoint in one place.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is Red-Hat-AI-Innovation-Team/training_hub's own configuration. It tells Claude Code how to work on training_hub itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything training_hub configures →

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the training-hub plugin — 4 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to Red-Hat-AI-Innovation-Team/training_hub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Red-Hat-AI-Innovation-Team/training_hub/main/.claude/skills/training-guide/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Red-Hat-AI-Innovation-Team/training_hub

Made for: Claude Code.

Or install training-hub, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for training-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/red-hat-ai-innovation-team/training_hub/training-guide/github.svg)](https://agentmods.dev/skills/red-hat-ai-innovation-team/training_hub/training-guide)
Your own site
<a href="https://agentmods.dev/skills/red-hat-ai-innovation-team/training_hub/training-guide"><img src="https://agentmods.dev/badge/skills/red-hat-ai-innovation-team/training_hub/training-guide/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for training-guide

Your own site · 80×15
<a href="https://agentmods.dev/skills/red-hat-ai-innovation-team/training_hub/training-guide"><img src="https://agentmods.dev/badge/skills/red-hat-ai-innovation-team/training_hub/training-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 326 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00326
Opus 5 $0.00019 $0.00163
Sonnet 5 $0.00008 $0.00065
Haiku 4.5 $0.00004 $0.00033

Measured 11d ago against content hash 04e6f2f7dd21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

training-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/training-guide/SKILL.md · 44 lines

What it actually says

Run Training

Execute LLM training using a saved configuration.

Step 1: Check Environment

"${CLAUDE_PLUGIN_ROOT}/scripts/th_detect.sh"

If not ready

  • library=missing or config=missing: invoke the setup-guide skill.
  • gpu=unavailable: warn that training requires CUDA-capable GPUs.

If ready (library=installed, config=found)

Proceed to Step 2.

Step 2: Execute Training

Run the training script with any user-provided overrides:

"${CLAUDE_PLUGIN_ROOT}/scripts/th_train.sh" $ARGUMENTS

Step 3: Present Results

  1. Training status — Whether training completed successfully
  2. Algorithm used — Which algorithm and backend were used
  3. Checkpoint location — Where the trained model was saved
  4. Loss summary — If available, show final loss values

If training failed, consult the training-hub-guide skill for troubleshooting (OOM, loss interpretation, backend-specific issues).

Remind the user they can visualize training loss with training_hub.plot_loss().

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 44 lines · 38 tokens per session scan A 04e6f2f7dd21

Subscribe to this mod's changes

training-guide is a skill published in the GitHub repository Red-Hat-AI-Innovation-Team/training_hub (95 stars, last pushed yesterday), licensed Apache-2.0. It adds 38 tokens to every session and 326 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

ml-training-recipes

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning…

Orchestra-Research/AI-Research-SKILLs · 88 tokens

tao-run-automl

Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation…

NVIDIA-TAO/tao-skill-bank · 235 tokens

unsloth

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.

davila7/claude-code-templates · 39 tokens

unsloth

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.

OpenLAIR/dr-claw · 39 tokens

hugging-face-model-trainer

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…

synthetic-sciences/openscience · 131 tokens

Training

Guides fine-tuning and post-training work with explicit data, objective, hardware, and rollback assumptions.

agentic-in/elephant-agent · 23 tokens