local-llm-tool
$
npx mdskill add xuiltul/animaworks/local-llm-toolExecute text generation and multi-turn conversations using self-hosted LLMs via Ollama or vLLM.
- Generates content or maintains dialogue when cloud API access is unavailable or restricted.
- Integrates with local inference servers like Ollama or vLLM endpoints.
- Determines the required function (generate, chat, models, status) based on the user's intent.
- Returns generated text or status information directly to the calling agent or user.
SKILL.md
.github/skills/local-llm-toolView on GitHub ↗
---
name: local-llm-tool
description: >-
Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints.
Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.
tags: [llm, local, ollama, external]
---
# Local LLM Tool
External tool for text generation and chat via local LLM (Ollama/vLLM).
## Invocation via Bash
Use **Bash** with `animaworks-tool local_llm <subcommand> [args]`. See Actions below for syntax.
## Actions
### generate — Text generation
```json
{"tool_name": "local_llm", "action": "generate", "args": {"prompt": "prompt text", "system": "system prompt (optional)", "temperature": 0.7, "max_tokens": 2048}}
```
### chat — Multi-turn chat
```json
{"tool_name": "local_llm", "action": "chat", "args": {"messages": [{"role": "user", "content": "question"}], "system": "system prompt (optional)"}}
```
### models — List available models
```json
{"tool_name": "local_llm", "action": "models", "args": {}}
```
### status — Server status
```json
{"tool_name": "local_llm", "action": "status", "args": {}}
```
## CLI Usage (S/C/D/G-mode)
```bash
animaworks-tool local_llm generate "prompt" [-S "system prompt"]
animaworks-tool local_llm list
animaworks-tool local_llm status
```
## Notes
- Ollama or vLLM server must be running
- Use -s/--server to specify server URL
- Use -m/--model to specify model