From buymeagoat-skills
Install a model from a URL into local Ollama with a practical quantization for this host, verify availability for API/OpenWebUI, and sync Continue config to all currently installed models. Trigger with `/llm-install <MODEL_URL>`.
How this skill is triggered — by the user, by Claude, or both
Slash command
/buymeagoat-skills:llm-installThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when user asks to install an LLM from a URL (Hugging Face or Ollama) and wants it ready for local use.
Use this skill when user asks to install an LLM from a URL (Hugging Face or Ollama) and wants it ready for local use.
/llm-install <URL>/llm-install https://huggingface.co/HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive/llm-install https://huggingface.co/TrevorJS/gemma-4-E2B-it-uncensored-GGUF/llm-install https://ollama.com/library/qwen2.5-coderhttp://172.31.192.1:11434Given a repository with multiple GGUF quantizations, choose in this order:
Q6_K / Q6_K_P when available (best quality/speed balance for local use).Q5_K_M / Q5_K_S.Q4_K_M (safe fallback for constrained disk/VRAM).Q8_0 only when user explicitly asks for maximum quality and space allows.BF16 by default on this host (large footprint).Q2 / Q3 unless they are the only options.For repos without GGUF files:
.env keys in this order: HF_TOKEN, HUGGINGFACEHUB_API_TOKEN, HUGGING_FACE_HUB_TOKEN./api/tags./api/chat non-stream) to confirm runtime usability.After each successful install, sync both files to current installed models:
~/.continue/config.yaml.continue/config.yaml (workspace)Sync rules:
Ollama /api/tags.embed -> embedqwen2.5-coder:7b-Fallback_Coding -> autocompletechattabAutocompleteModel set to qwen2.5-coder:7b-Fallback_Coding when present.http://172.31.192.1:11434.Always return:
/api/tags and chat probe)npx claudepluginhub buymeagoat/agent-skills --plugin buymeagoat-skillsGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.