If you use AI coding agents like Claude Code, Cursor, or GitHub Copilot, you've probably run into SKILL.md files - markdown documents that teach these agents how to perform specific tasks within your codebase. Until now, creating them meant hand-writing YAML frontmatter and markdown with no preview, no validation, and no way to test before deploying.
UberSKILLS is a new open-source web app that adds structure to that process. It offers AI-assisted skill creation where you describe what you want in plain English, a live preview so you can see the rendered output before committing, and built-in validation to catch formatting errors. Think of it as a dedicated IDE for the instruction files that make AI agents useful in practice.
The tool targets a real friction point. As AI coding agents have matured, the quality of their custom instructions has become a genuine differentiator between a helpful assistant and one that flails at project-specific tasks. But writing good skills is tedious and error-prone when you're working in a plain text editor with no feedback loop.
UberSKILLS supports the major agent platforms - Claude Code, GitHub Copilot, Cursor, and Windsurf - and is available now on GitHub under an open-source license. It's early-stage, so expect rough edges, but the core authoring workflow is functional.