Agent Skills
› xuiltul/animaworks
› local-llm-tool
local-llm-tool
GitHub本地LLM执行工具，通过Ollama或vLLM在GPU上调用模型进行文本生成、多轮聊天及状态检查。适用于私有化部署推理场景。
触发场景
需要本地运行LLM进行文本生成
调用Ollama或vLLM端点
使用本地模型进行摘要或对话
安装
npx skills add xuiltul/animaworks --skill local-llm-tool -g -y
SKILL.md
Frontmatter
{
"name": "local-llm-tool",
"tags": [
"llm",
"local",
"ollama",
"external"
],
"description": "A local LLM execution tool. Requests text generation and chat from models on GPU via Ollama or vLLM. Use when: Use when: on-premise inference, calling Ollama endpoints, or needing summaries and generation with local models."
}
Local LLM Tool
An external tool that performs text generation and chat via local LLMs (Ollama/vLLM）).
How to Call
Bash: Run with animaworks-tool local_llm <サブコマンド> [引数]
List of Actions
generate — Text Generation
animaworks-tool local_llm generate "プロンプト" [-S "システムプロンプト"]
chat — Chat (Multi-turn)
animaworks-tool local_llm chat [--messages JSON] [-S "システムプロンプト"]
models — List Models
animaworks-tool local_llm list
status — Check Server Status
animaworks-tool local_llm status
CLI Usage
animaworks-tool local_llm generate "プロンプト" [-S "システムプロンプト"]
animaworks-tool local_llm list
animaworks-tool local_llm status
Notes
- The Ollama server or vLLM server must be running
- -s/--server can be used to specify the server URL
- -m/--model can be used to specify the model
版本历史
-
0f2a80e
当前 2026-10-19 11:11
更新文档为英文版并修正调用示例格式
- 140e43b 2026-07-25 09:12
