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.
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.
npx skills add Orchestra-Research/AI-Research-SKILLs --skill ml-training-recipesgit clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLsWrote 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/orchestra-research/ai-research-skills/ml-training-recipes)<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.
<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>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00088 | $0.03038 |
| Opus 5 | $0.00044 | $0.01519 |
| Sonnet 5 | $0.00018 | $0.00608 |
| Haiku 4.5 | $0.00009 | $0.00304 |
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.
Copies of this mod
2 near-identical copies found in the catalogue:
- ml-training-recipes — 100% identical, 638 lines differ
- ml-training-recipes — 100% identical, 0 lines differ
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 initreferences/optimizers.md— Muon, AdamW hybrid, per-group LR, compiled optimizer stepsreferences/domain-specific.md— Vision, diffusion, contrastive, distributed, checkpointing, data loadingreferences/scaling-and-selection.md— Scaling laws, compute budget tables, decision trees, DGX Sparkreferences/biomedical.md— Drug discovery, protein models, medical imaging, genomics, clinical NLPreferences/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)
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.
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.
- 13d ago First seen · 320 lines · 88 tokens per session scan A 1cb661b0d3ba
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.
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…
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…
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…
saelens
Train sparse autoencoders to interpret model features.
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…