Llm

A migration guide that helps update codebases using older Claude models (Sonnet 4.0, Sonnet 4.5, Opus 4.1) to Claude Opus 4.5. It provides model string mappings across platforms (Anthropic API, AWS Bedrock, Vertex AI, Azure), effort parameter configuration, and prompt adjustment snippets for handling Opus 4.5's behavioral differences like tool overtriggering and over-engineering tendencies.

This skill provides comprehensive documentation for designing LLM applications using the LangChain framework. It covers agent architectures (ReAct, OpenAI Functions), chain compositions, memory management patterns, document processing pipelines, and callback systems with production-ready examples and best practices.

This skill provides comprehensive documentation for building RAG (Retrieval-Augmented Generation) systems. It covers vector database selection (Pinecone, Weaviate, Chroma), embedding models, document chunking strategies, retrieval optimization techniques, and prompt engineering patterns for knowledge-grounded LLM applications.

A comprehensive guide to prompt engineering best practices covering few-shot learning, chain-of-thought prompting, template systems, and systematic optimization workflows. Includes reusable templates, example datasets, and an automated prompt testing framework to help developers maximize LLM performance in production applications.

Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks.

A comprehensive guide to prompt engineering patterns and best practices for working with LLMs. Covers techniques like few-shot learning, chain-of-thought prompting, template systems, and system prompt design, along with Anthropic's official agent prompting guidelines and persuasion principles for effective AI communication.