What problem does it solve? AI agents often lack access to documentation they were not trained on, leading to hallucinated APIs and outdated answers. This Skill fetches external sources and converts them into durable, structured reference documents that other AI workflows can reuse. ## Core Features & Use Cases - Source Ingestion: Fetches web pages (with sub-page crawling and targeted search gap-filling) or reads local files such as Markdown, HTML, JSON, and YAML specs. - Structured Synthesis: Produces dense reference documents with overview, core concepts, API signatures, usage patterns, configuration tables, best practices, and pitfalls, always with source attribution. - Lifecycle Management: Supports listing, showing, deleting, and updating references, plus an INDEX.md registry for discovery by other skills. - Use Case: Before implementing a feature with an unfamiliar library, run the skill on the library's docs URL to create a grounded reference that planning and implementation skills can consult. ## Quick Start Ask the AI to create a reference from a documentation URL, for example: create a reference named zod-validation from https://zod.dev.
