Weaviate Launches 'Agent Skills' for AI Coders

- Weaviate was founded in Amsterdam in 2019 by CEO Bob van Luijt and CTO Etienne Dilocker and has raised $67.7 million in total funding, including a $50 million Series B round in April 2023. - The "Agent Skills" initiative directly addresses the tendency for AI agents to "hallucinate" or generate incorrect code for specialized tools; studies have shown that a high percentage of enterprise AI agent projects fail, with one analysis noting GitHub Copilot-authored pull requests had a 43% merge rate. - The open-source repository is structured into two main parts: granular "Skills" for specific tasks like data import and schema inspection, and "Cookbooks" which provide end-to-end blueprints for building complete applications like a chatbot with a FastAPI backend and a Next.js frontend. - To streamline development, the repository equips AI agents with six slash commands, such as `/weaviate:ask` for natural language questions with citations and `/weaviate:search` to perform hybrid searches blending semantic and keyword retrieval. - The tools are designed for integration with popular AI coding assistants, including GitHub Copilot, Cursor, Claude Code, VS Code extensions, and the Gemini CLI. - This launch is part of a broader industry trend moving from the "Model Era," focused on building large models, to the "Execution Era," which emphasizes creating reliable tools and infrastructure for agents to perform real-world work. - Developers can experiment with the new skills by connecting to a free Weaviate Cloud Sandbox, which provides a small instance for 14 days. - The project builds upon Weaviate's Query Agent, a tool for natural language queries across data collections that reached general availability in September 2025.