Individual skill
deep-learning
Use when training or debugging a neural net in PyTorch — the forward/loss/backward/step loop and its silent bugs, mixed precision (AMP), AdamW/LR schedules, DDP/FSDP/ZeRO, checkpoints and seeds. NOT LoRA/QLoRA on a pretrained LLM (that is `finetuning`), NOT tabular sklearn/XGBoost (that is `machine-learning`), NOT tokenization or NLP metrics (that is `nlp`).
skills/deep-learning/SKILL.md
Source commit d9d6bb338f66cc1e23998585e580a0ea45bbcb82
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 559
- Repository last updated
- Nov 4, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-agents Repository topic
- ai-coding Repository topic
- claude-code Repository topic
- cli Repository topic
- cline Repository topic
- codex Repository topic
- coding-assistant Repository topic
- cursor Repository topic
- pytorch Declared skill tag
- deep-learning Declared skill tag
- neural-networks Declared skill tag
- training-loop Declared skill tag
- autograd Declared skill tag
- mixed-precision Declared skill tag
- amp Declared skill tag
- ddp Declared skill tag
- fsdp Declared skill tag
- optimizer Declared skill tag
- lr-scheduler Declared skill tag
- reproducibility Declared skill tag
- torch-compile Declared skill tag
- testing Derived category
- education Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 13,818 bytesSKILL.mdcore · 13,818 bytesSKILL.mdcore · 13,818 bytesSKILL.mdcore · 13,818 bytesSKILL.mdcore · 13,818 bytesSKILL.mdcore · 13,818 bytesSKILL.mdcore · 13,818 bytesevals/README.mddoc · 860 bytesevals/cases.yamlasset · 4,444 bytesreferences/distributed.mddoc · 5,133 bytesreferences/training-recipes.mddoc · 6,288 bytes
Read excerpt
# deep-learning — train a neural net in PyTorch without the silent bugs
You own **training and understanding neural networks in PyTorch**: the loop, autograd, mixed
precision, optimizers/schedulers, multi-GPU, and the reproducibility/checkpoint hygiene that
separates a real result from a lucky one. Nets from scratch, vision, custom architectures — all
here. This is PyTorch-first by design: JAX and TensorFlow are real and fine, but the patterns,
APIs, and gotchas below are Torch's.
**Version reality (verify at author time).** Current stable is PyTorch **2.x** — ~**2.13** as of
mid-2026 (`pytorch.org/get-started`, releases move fast; don't hard-pin a minor). Everything below
is stable 2.x API. The one namespace shift to know: AMP now lives under `torch.amp`
(`torch.amp.GradScaler("cuda")`), not the old `torch.cuda.amp.*`.
## Am I in the right skill?