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.
curl -O https://raw.githubusercontent.com/Red-Hat-AI-Innovation-Team/training_hub/main/.claude/skills/setup-guide/SKILL.mdgit clone --depth 1 https://github.com/Red-Hat-AI-Innovation-Team/training_hubWrote 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.
[](https://agentmods.dev/skills/red-hat-ai-innovation-team/training_hub/setup-guide)<a href="https://agentmods.dev/skills/red-hat-ai-innovation-team/training_hub/setup-guide"><img src="https://agentmods.dev/badge/skills/red-hat-ai-innovation-team/training_hub/setup-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.
<a href="https://agentmods.dev/skills/red-hat-ai-innovation-team/training_hub/setup-guide"><img src="https://agentmods.dev/badge/skills/red-hat-ai-innovation-team/training_hub/setup-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00988 |
| Opus 5 | $0.00017 | $0.00494 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
setup-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
training_hub Setup Guide
You are helping the user set up LLM training. For algorithm selection guidance, hyperparameter tuning, and troubleshooting, consult the training-hub-guide skill.
Step 1: Detect Environment
"${CLAUDE_PLUGIN_ROOT}/scripts/th_detect.sh"
Step 2: Install if Needed
If library=missing:
- Ask permission: "training_hub isn't installed. I can install it for you — want me to proceed?"
- If yes and
installer=uv: runuv pip install training-hub - If yes and
installer=pip: runpip install training-hub - If
installer=none: tell the user they need Python and pip/uv installed first - Ask about extras:
- CUDA:
training-hub[cuda]— flash-attn, bitsandbytes for GPU acceleration - LoRA:
training-hub[lora]— Unsloth, TRL for parameter-efficient fine-tuning - GRPO:
training-hub[grpo]— ART, veRL for reinforcement learning
- CUDA:
For installation issues, consult the training-hub-guide skill (installation-troubleshooting section).
Step 3: Check GPU
If gpu=unavailable, warn: "No GPU detected. Training requires CUDA-capable GPUs. You can still configure, but training will fail without a GPU."
Report GPU count if available.
Step 4: Quick Setup or Custom
If the user has a clear task ("fine-tune Llama on my data"), offer a fast path with sensible defaults:
"I detected N GPU(s). I can set up with these defaults:
- Algorithm:
lora_sft(parameter-efficient, works on a single GPU)- Learning rate:
1e-5- Epochs:
2- Batch size:
64- Max sequence length:
4096You'll just need to provide your model path and data path. Accept these defaults, or customize?"
If the user accepts, ask only for model path and data path, then skip to Step 7.
If the user wants to customize, proceed with the full configuration.
Full Configuration
Ask these questions one at a time:
- Algorithm: "Which training algorithm do you want to use?" — consult the
training-hub-guideskill for algorithm selection guidance if the user is unsure. - Model path: "What's the model identifier?" — e.g.,
meta-llama/Llama-3.1-8B-Instruct, or a local path. - Data path: "Where is your training data?" — Path to a JSONL file with
messagesfield. - Output directory: "Where should checkpoints be saved?" — Default:
./output - GPU count: "How many GPUs should be used?" — Default: detected count or 1.
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.
- 10d ago First seen · 103 lines · 35 tokens per session scan A 5e51a6f1570d
setup-guide is a skill published in the GitHub repository Red-Hat-AI-Innovation-Team/training_hub (95 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 988 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.
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…
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…
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.
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…
Training
Guides fine-tuning and post-training work with explicit data, objective, hardware, and rollback assumptions.