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 mxslr/mlcraft --skill training-optimizationgit clone --depth 1 https://github.com/mxslr/mlcraftWrote 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/mxslr/mlcraft/training-optimization)<a href="https://agentmods.dev/skills/mxslr/mlcraft/training-optimization"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/training-optimization/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/mxslr/mlcraft/training-optimization"><img src="https://agentmods.dev/badge/skills/mxslr/mlcraft/training-optimization.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 | $0.00123 | $0.00662 |
| Opus 5.5 | $0.00049 | $0.00265 |
| Sonnet 5.5 | $0.00025 | $0.00132 |
| Haiku 4.5 | $0.00012 | $0.00066 |
Grade A, and why
training-optimization 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 1mo 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Training & Fine-Tuning
Best-practice recipe for transfer-learning a strong model, and how to fix over/under-fitting.
Fine-tuning recipe (default that works)
- Transfer learning: start from ImageNet/pretrained weights; train from scratch only with lots of data.
- Two phases: (1) freeze backbone, train the new head; (2) unfreeze and fine-tune end-to-end at a lower LR.
- Discriminative / layer-wise LR: small LR for early backbone layers, higher for the head. Biggest single fine-tuning win.
- Schedule: cosine decay with a short warmup. Log the LR curve.
- Optimizer: AdamW (decoupled weight decay). Gradient clipping ~1.0.
- Selection: checkpoint the best epoch by the validation metric; early stopping.
Diagnose then regularize (don't guess)
- Overfitting (train accuracy keeps rising while val loss rises or plateaus): raise weight decay, dropout, label smoothing; add MixUp; stronger-but-domain-appropriate augmentation; reduce epochs/patience; smaller/less-capacity head.
- Underfitting (train acc low too): reduce regularization, raise LR / capacity / resolution, train longer, check data quality.
- Match augmentation to the domain - do not use aggressive photometric/geometric ops that destroy the signal (e.g., harsh color/solarize on medical scans, or flips that change semantics).
Compute & memory (fit the budget)
- Mixed precision (AMP) always on GPU.
- Gradient checkpointing to fit high resolution / big models in limited VRAM (~3× memory saving, ~30% slower).
- Small batch + gradient accumulation to keep an effective batch size when VRAM is tight; freeze BatchNorm stats at very small batch (LayerNorm backbones like ConvNeXt are safer there).
- Preprocess once to disk if per-epoch CPU work (decode/enhance) starves the GPU - huge speedups.
- Budget = seconds/epoch × epochs × models. Measure on a quick run first; pick resolution/epochs to fit the quota. Prefer one honest fit over a run that dies mid-way.
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.
- 1mo ago First seen · 33 lines · 123 tokens per session scan A c76e88520c70
training-optimization is a skill published in the GitHub repository mxslr/mlcraft (8 stars, last pushed 3mo ago), licensed MIT. It adds 123 tokens to every session and 662 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.
reinforcement-learning
Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) Creating custom Gymnasium environments Training, debugging, or evaluating RL agents Setting up hyperparameter tuning for RL Deploying RL models…
ml-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design.
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…
torch-geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…