Archived 2026-10-23 · Source updated 2026-08-19 · License: MIT. Check the original repository for the latest version.
SKILL.md instructions
## Mixed Precision Training Best Practice
Use torch.cuda.amp for automatic mixed precision:
- Wrap forward pass in torch.cuda.amp.autocast()
- Use GradScaler for loss scaling
- BF16 preferred over FP16 on Ampere+ GPUs (RTX 3xxx, A100, RTX 4xxx)
- Watch for NaN gradients — reduce learning rate if needed
- Do NOT use amp with custom CUDA kernels unless tested
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy…
Generates technical guides that teach real-world use cases through progressive examples. **Auto-activation:** User asks to write, create, or draft a guide or tutorial. Also use when converting feature…
Use when asked to brainstorm, evaluate whether an idea is worth building, run office hours, or think through a new product idea or design direction before any code is written.
Skills DirectorySearch all skills ↗