MANDATORY recipe for every Caffeine build that calls an LLM, chatbot, GPT, or ChatGPT **on Caffeine Inference** (no user-pasted OpenAI key). The ONLY supported path is the `caffeineai-inference-client` mops package with `Config.fromEnv<system>()`, which hands the canister a ready-to-use authenticated config — the app never asks for, stores, or returns a key.
Install
npx skills add caffeinelabs/skills --skill extension-inferencenpx skills add caffeinelabs/skills --skill extension-inference -a claude-code -gnpx skills add caffeinelabs/skills --skill extension-inference -a codex -ggemini skills install https://github.com/caffeinelabs/skills.git --path skills/extension-inferencegh skill install caffeinelabs/skills extension-inferencegit clone --depth 1 https://github.com/caffeinelabs/skills /tmp/caffeinelabs__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/caffeinelabs__skills/skills/extension-inference ~/.claude/skills/extension-inference # Claude Code
cp -R /tmp/caffeinelabs__skills/skills/extension-inference ~/.agents/skills/extension-inference # Codex, Cursor, Gemini CLI, Copilot, OpenCode