deep-learning
100 / 100 · Low risk
Fine to try.
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`).
Partially scanned — some files couldn't be read; we'll retry on the next scan
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'deep-learning' ] || [ -L ~/.agents/skills/'deep-learning' ]; then echo 'A skill folder named deep-learning already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/ericrisco/rsc-harness' "$d" && git -C "$d" checkout --quiet 'f3765d35e91690c0c7e511447da6cd0176ab38e0' -- 'skills/deep-learning' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/deep-learning' ~/.agents/skills/'deep-learning' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'deep-learning' ~/.claude/skills/'deep-learning' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/ericrisco/rsc-harness/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-12 | f3765d3 | 100 |
| 2026-11-08 | 726aaf3 | 100 |
| 2026-11-07 | 726aaf3 | 45 |