Local AI Engineer Skills
| Skill | Use it when | id |
|---|---|---|
| gguf-quant-selection | when deploying an LLM on a laptop, workstation or edge device | SK-LOCAL-AI-ENGINEER-gguf-quant-selection |
| local-runtime-setup | when installing Ollama, llama.cpp or LM Studio, or exposing an OpenAI-compatible endpoint | SK-LOCAL-AI-ENGINEER-local-runtime-setup |
| offline-privacy-check | when privacy or compliance requires no data egress | SK-LOCAL-AI-ENGINEER-offline-privacy-check |