安裝本地 AI Ollama(Claude Code 版)

SkillAI & models

Lets your agent walk through installing Ollama and pulling AI models like Llama to run locally.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the 安裝本地 AI Ollama(Claude Code 版) skill

About this skill

Claude Code 安裝本地 AI Ollama。說「安裝 Ollama」「本地 AI」時載入。

What this skill tells your AI

The instructions your AI receives, as published by mathruffian-dot/claude-code-lazy-packs in skills/06-ollama/SKILL.md and read by ahel’s review.

  1. 下載安裝:https://ollama.com/download
  2. ollama --version
  3. 拉取模型:ollama pull llama3.2:latest 或 ollama pull gemma3:latest
  4. 如需 GPU 加速確認:ollama run llama3.2:latest "hello"

可選:加入 Claude Code MCP

若想讓 Claude 呼叫本地模型:

"mcpServers": { "ollama": { "command": "npx", "args": ["-y", "@ollama/mcp-server"] } }

回報:Ollama 版本、模型清單、GPU 狀態。

Signals

GitHub stars
251
Forks
114
Last commit
Sep 2026
Advanced
Item type
skill
Key
cc-ollama
Source
github.com/mathruffian-dot/claude-code-lazy-packs