add-ollama-tool

npx skills add majiayu000/claude-skill-registry --skill add-ollama-tool-dingyanglyu-matclaw --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# Add Ollama Integration This skill adds a stdio-based MCP server that exposes local Ollama models as tools for the container agent. Claude remains the orchestrator but can offload work to local models. Tools added: - `ollama_list_models` — lists installed Ollama models - `ollama_generate` — sends a prompt to a specified model and returns the response ## Phase 1: Pre-flight ### Check if already applied Read `.matclaw/state.yaml`. If `ollama` is in `applied_skills`, skip to Phase 3 (Configure). The code changes are already in place. ### Check prerequisites Verify Ollama is installed and running on the host: ```bash ollama list ``` If Ollama is not installed, direct the user to https://ollama.com/download. If no models are installed, suggest pulling one: > You need at least one model. I recommend: > > ```bash > ollama pull gemma3:1b # Small, fast (1GB) > ollama pull llama3.2 # Good general purpose (2GB) > ollama pull qwen3-coder:30b # Best for code tasks (18GB) > ``` ## Phase 2: Apply Code Changes Run the skills engine to apply this skill's code package. ### Initialize skills system (if needed) If `.matclaw/` directory doesn't exist yet: ```bash npx tsx scripts/apply-skill.ts --init

ollama list
ollama pull gemma3:1b    # Small, fast (1GB)
ollama pull llama3.2     # Good general purpose (2GB)
ollama pull qwen3-coder:30b  # Best for code tasks (18GB)
npx tsx scripts/apply-skill.ts --init
npx tsx scripts/apply-skill.ts .claude/skills/add-ollama-tool
for dir in data/sessions/*/agent-runner-src; do
cp container/agent-runner/src/ollama-mcp-stdio.ts "$dir/"
cp container/agent-runner/src/index.ts "$dir/"
done