llmintegration
LLM integration patterns for Claude, GPT, Gemini, and Ollama. Activate for AI API integration, prompt engineering, token management, extended thinking, and multi-model orchestration.
npx skills add majiayu000/claude-skill-registry --skill llm-integration-lobbi-docs-claude-3 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill outlines integration patterns for multiple LLM providers (Claude, GPT, Gemini, Ollama) and orchestration across models. It covers prompt engineering, token budgeting, extended thinking, and a multi-provider abstraction to switch between providers.
How it works
It includes code examples for each provider:
- Claude integration: basic completion, system prompts, streaming, tool usage, and a sample tool definition.
- OpenAI GPT integration: basic completion, streaming, and function calling with defined functions.
- Google Gemini integration: basic generation, chat, and streaming.
- Ollama local models: basic completion, streaming, model pulling, and listing.
- Multi-Model Abstraction: defines an abstract LLMProvider with ClaudeProvider, GPTProvider, GeminiProvider, OllamaProvider, and an LLMFactory to instantiate a provider by name.
- Prompt Engineering Best Practices: examples for structured prompts, using XML tags, few-shot prompting, and chain-of-thought prompts.
- Extended Thinking Integration: describes how extended thinking can be enabled for Claude (with thinking budget) including streaming support, plus a multi-provider abstraction for extended thinking (claude and gpt paths).
- Claude Prompt Engineering Best Practices: concrete guidelines including clear instructions, structured prompts with XML, and few-shot templates.
When to use it
Activate when integrating Claude Anthropic, OpenAI GPT, Google Gemini, Ollama local models, multi-model orchestration, and prompt engineering tasks. Extended thinking sections indicate when to enable thinking budgets and streaming for Claude-based workflows.
What it can touch
Declared tools include Bash, Read, Write, Edit, Glob, Grep. The skill presents code and API usage across multiple providers but does not specify runtime tool calls beyond language libraries (Anthropic, OpenAI, google.generativeai, ollama) in the examples.
Caveats
License is MIT. The skill includes sample code snippets that rely on environment variables (ANTHROPIC_API_KEY, OPENAI_API_KEY, GOOGLE_API_KEY). No explicit risk or limitation statements are provided beyond the content of the examples and the general capabilities described.
# LLM Integration Skill Provides comprehensive LLM integration capabilities for the Golden Armada AI Agent Fleet Platform, including advanced features like extended thinking, sophisticated prompt engineering, and intelligent token budget management. ## When to Use This Skill Activate this skill when working with: - Claude/Anthropic API integration - OpenAI GPT integration - Google Gemini integration - Ollama local models - Multi-model orchestration - Prompt engineering ## Anthropic Claude Integration \`\`\`python import anthropic client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"]) # Basic completion message = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[ {"role": "user", "content": "Hello, Claude!"} ] ) print(message.content[0].text) # With system prompt message = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, system="You are a helpful coding assistant.", messages=[ {"role": "user", "content": "Write a Python function to sort a list."} ] ) # Streaming with client.messages.stream( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[{"role": "user", "content": "Tell me a story."}] ) as stre
- When to Use This Skill
- Anthropic Claude Integration
- OpenAI GPT Integration
- Google Gemini Integration
- Ollama Local Models
- Multi-Model Abstraction
- Prompt Engineering Best Practices
- Extended Thinking Integration
- When to Use Extended Thinking
- Basic Extended Thinking
- Extended Thinking with Streaming
- Multi-Provider Extended Thinking Abstraction
- Claude Prompt Engineering Best Practices
- 1. Clear and Direct Instructions
What does the llmintegration skill do?
LLM integration patterns for Claude, GPT, Gemini, and Ollama. Activate for AI API integration, prompt engineering, token management, extended thinking, and multi-model orchestration.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill llm-integration-lobbi-docs-claude-3 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.