Llm Integration skills for AI agents
8 practitioner-grade llm integration skills, each a focused Markdown document your agent loads into context on demand. Search them from Claude Desktop, Cursor or any MCP client, or pull one with the CLI.
All 8 skills
- Anthropic API
Anthropic Claude API integration for messages, streaming, and tool use
272 lines - Embeddings
Text embeddings and semantic search with vector databases for LLM applications
269 lines - Function Calling
Function/tool calling patterns for connecting LLMs to external APIs and data sources
319 lines - Langchain
LangChain orchestration for chains, agents, memory, and retrieval workflows
262 lines - Openai API
OpenAI API integration patterns for chat completions, embeddings, and assistants
208 lines - Rag Pipeline
Building retrieval-augmented generation pipelines with document ingestion, retrieval, and synthesis
394 lines - Streaming
Streaming LLM responses with SSE, WebSockets, and backpressure handling
350 lines - Vercel AI SDK
Vercel AI SDK for streaming LLM responses in React, Next.js, and edge runtimes
283 lines