grok-prompts is a library of system prompts and templates used to define the personality, safety boundaries, and operational logic of large language models. It provides a framework for managing model personas and the integration of external tools through structured configurations.
The project focuses on persona management to ensure consistent response styles and professional tones. It includes specific configurations for safety guardrails to prevent harmful outputs and a tool integration framework that enables models to interact with services for web search, image generation, and document analysis.
The library also defines schemas for structured data output, specifically for rendering interactive charts via JSON and formatting mathematical expressions using LaTeX syntax. It covers the extraction and summarization of external content, such as user profiles and social posts.