From llm-gateway
Use when the user runs /llm-login or wants to authenticate an LLM provider (GitHub Copilot, Kimi, MiniMax, GLM, Qwen), check auth status, or logout from a provider.
How this skill is triggered — by the user, by Claude, or both
Slash command
/llm-gateway:llm-loginThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Interactive authentication for LLM providers. After login, use `/model` to pick a model.
Interactive authentication for LLM providers. After login, use /model to pick a model.
llm_status({}) to show current auth state for all providers/model to pick a model from this provider"llm_login({ provider: "copilot" })userCode and verificationUriPlease open [verificationUri] and enter code: [userCode] Waiting for authorization...
llm_login({ provider: "<name>", apiKey: "<key>" })Run llm_status({}) once more to show the updated state, then remind the user:
Run
/modelto select a model — all authenticated provider models are now available.
If the user wants to logout: call llm_logout({ provider: "<name>" })
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub seufsg/llm-gateway --plugin llm-gateway