ml-training-recipes

ml-training-recipes is a skill for Claude Code from Orchestra-Research/AI-Research-SKILLs. It costs 88 tokens per session (3,038 once invoked), scanned A, original, MIT.

A set of PyTorch training recipes for teaching or fine-tuning machine-learning models for text, images, diffusion, medical data, proteins, drugs, and genomics.

In plain words
What is it for?
Use it to design and run training loops, fine-tune language or vision models, handle domain-specific data, and manage checkpoints and experiments.
Why use it?
It provides patterns for choosing model designs, optimizers, learning-rate schedules, mixed-precision training, debugging, and experiments.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the optimization plugin — 7 skills shipped together

Good fit Use it to design and run training loops, fine-tune language or vision models, handle domain-specific data, and manage checkpoints and experiments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orchestra-research/ai-research-skills/ml-training-recipes
About the project

AI Research Skills Library is a collection of reusable instructions that guide AI agents through research and machine-learning engineering tasks, from finding ideas and writing papers to training, evaluation, and deployment. It is for configuring agents such as Claude Code, Codex, and Gemini to perform research workflows.

Orchestra-Research/AI-Research-SKILLs · 12,567 stars · on GitHub · orchestra-research.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Orchestra-Research/AI-Research-SKILLs --skill ml-training-recipes
Clone the repo
git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs

Made for: Claude Code.

Or install optimization, the plugin that ships this one along with the rest of its 7 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 ml-training-recipes

README.md
[![agentmods](https://agentmods.dev/badge/skills/orchestra-research/ai-research-skills/ml-training-recipes/github.svg)](https://agentmods.dev/skills/orchestra-research/ai-research-skills/ml-training-recipes)
Your own site
<a href="https://agentmods.dev/skills/orchestra-research/ai-research-skills/ml-training-recipes"><img src="https://agentmods.dev/badge/skills/orchestra-research/ai-research-skills/ml-training-recipes/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 ml-training-recipes

Your own site · 80×15
<a href="https://agentmods.dev/skills/orchestra-research/ai-research-skills/ml-training-recipes"><img src="https://agentmods.dev/badge/skills/orchestra-research/ai-research-skills/ml-training-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,038 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. Third-party audits
  • Socket pass 2 Apr 2026
  • Snyk pass 2 Apr 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00088 $0.03038
Opus 5 $0.00044 $0.01519
Sonnet 5 $0.00018 $0.00608
Haiku 4.5 $0.00009 $0.00304

Measured 13d ago against content hash 1cb661b0d3ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ml-training-recipes 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 13d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

10-optimization/ml-training-recipes/SKILL.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ML Training Recipes

Battle-tested patterns for PyTorch training across domains. Drawn from production codebases (Karpathy's autoresearch/nanochat, torchvision, HuggingFace) and modern training practice.

Reference files (read when needed)

  • references/architecture.md — Transformer/LLM architecture code patterns, weight init
  • references/optimizers.md — Muon, AdamW hybrid, per-group LR, compiled optimizer steps
  • references/domain-specific.md — Vision, diffusion, contrastive, distributed, checkpointing, data loading
  • references/scaling-and-selection.md — Scaling laws, compute budget tables, decision trees, DGX Spark
  • references/biomedical.md — Drug discovery, protein models, medical imaging, genomics, clinical NLP
  • references/experiment-loop.md — Autonomous experiment loop (autoresearch keep/discard/revert)

Architecture Selection

Pick the right model by data type and data scale:

Data Type < 10K samples 10K-100K > 100K
Images Pretrained CNN + fine-tune Fine-tune ViT or CNN ViT from scratch
Text (gen) Few-shot prompting Fine-tune GPT/LLaMA (LoRA) Pretrain from scratch
Tabular XGBoost/LightGBM Still XGBoost Neural viable
Audio Pretrained Whisper Fine-tune AST Train from scratch
Molecules Pretrained GNN Fine-tune molecular LM Train GNN from scratch
Proteins ESM-2 embeddings + head Fine-tune ESM-2 Train protein LM
Medical img Pretrained CNN nnU-Net (auto-config) Swin-UNETR / MedSAM

Key principle: architecture matters less than training recipe at equal compute. A well-tuned ResNet beats a poorly-tuned ViT (ref: "ResNet Strikes Back", Wightman 2021).

For biomedical domains, see references/biomedical.md. For sequence model selection and compute planning, see references/scaling-and-selection.md.


Scaling Laws

Chinchilla rule (Hoffmann et al., 2022)

Read the full file on GitHub · 320 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 13d ago First seen · 320 lines · 88 tokens per session scan A 1cb661b0d3ba

Subscribe to this mod's changes

ml-training-recipes is a skill published in the GitHub repository Orchestra-Research/AI-Research-SKILLs (12,567 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 3,038 once invoked, about $0.0004 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…

TTAWDTT/elegant-researcher-skill · 88 tokens

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…

OpenRaiser/NanoResearch · 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

data-scientist

!cat Claude-Production-Grade-Suite/.protocols/ux-protocol.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/input-validation.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/tool-efficiency.md 2>/dev/null || true !cat Claude-Production-Grade-Suite/.protocols/visual-identity.md…

nagisanzenin/production-grade · 43 tokens

saelens

Train sparse autoencoders to interpret model features.

NousResearch/hermes-agent · 14 tokens

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…

NVIDIA/physicsnemo · 124 tokens