LM Studio
Installation
SKILL.md
When to Use
User wants to run local models with LM Studio, connect an app to its local server, or debug weak local inference behavior.
Use this for server readiness, model loading, OpenAI-compatible API integration, embeddings, MCP setup, and local-first operating decisions.
Architecture
Memory lives in ~/lm-studio/. If ~/lm-studio/ does not exist, run setup.md. See memory-template.md for structure.
~/lm-studio/
├── memory.md # Activation, preferred port, known-good defaults
├── server-notes.md # Reachability checks and server mode notes
├── model-profiles.md # Verified models by workload
└── incidents.md # Repeated failures and confirmed fixes