llm-generate

Generates text via OpenAI, Azure, Google Gemini, and Anthropic Claude with configurable parameters.

Updated Feb 26, 2026
One-click install
npx skills add https://github.com/Umbral-Bot/umbral-agent-stack --skill llm-generate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: llm-generate
Source: https://github.com/Umbral-Bot/umbral-agent-stack/tree/main/openclaw/workspace-templates/skills/llm-generate
Command: npx skills add https://github.com/Umbral-Bot/umbral-agent-stack --skill llm-generate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates text generation by leveraging various Large Language Models (LLMs) through a unified interface, simplifying complex AI interactions.

Core Features & Use Cases

  • Multi-Provider Support: Seamlessly generate text using models from OpenAI, Azure, Google (Gemini), and Anthropic (Claude) via direct APIs or a local proxy.
  • Automatic Provider Detection: The skill intelligently selects the correct LLM provider based on the model name specified.
  • Configurable Generation Parameters: Control output with parameters like max_tokens and temperature.
  • Use Case: Generate marketing copy, draft emails, summarize documents, or create code snippets by simply describing the desired output.

Quick Start

Use the llm-generate skill to create a summary of the provided document using the claude_pro model.

Frequently Asked Questions about llm-generate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate text using multiple LLMs like OpenAI and Claude through a single interface?

You can generate text using multiple LLMs by routing requests through a unified interface that supports OpenAI, Azure OpenAI, Google Gemini, and Anthropic Claude, simplifying complex AI interactions.

Does the skill automatically detect whether to use Azure OpenAI or Google Gemini based on the model name?

Yes, automatic provider detection intelligently selects the correct LLM provider, such as Azure OpenAI or Google Gemini, based solely on the specific model name you configure.

Can I configure generation parameters like max tokens and temperature for LLM text generation?

Yes, you can control LLM text generation output by configuring generation parameters including max_tokens and temperature to adjust response length and creativity.

What is the best way to use a local proxy like OpenClaw for LLM text generation?

For LLM text generation, you can integrate with local proxies like OpenClaw to route API requests, providing enhanced flexibility when generating marketing copy, emails, or code snippets.

Do I need separate API configurations for each LLM provider to generate text?

No, you do not need separate configurations for each LLM provider because the skill standardizes text generation across OpenAI, Azure, Gemini, and Claude via direct APIs or a local proxy.

Why use a unified interface for LLM text generation instead of direct provider APIs?

A unified interface for LLM text generation automates provider selection and standardizes parameters, preventing the need to manage distinct API integrations for OpenAI, Gemini, and Claude.