This does exactly one thing: it fetches Cypress documentation from official sources and refuses to guess. It prioritizes the LLM-optimized markdown paths under /llm/* on docs.cypress.io, which means cleaner extraction and less HTML noise. The anti-hallucination rules are strict: if it can't verify an API or behavior in the docs, it says so instead of inventing syntax. You'd reach for this when you need to quote exact command signatures, confirm configuration options, or look up error messages rather than relying on memory. It's built for grounding answers in what Cypress actually documents, not what sounds plausible.
npx skills add https://github.com/cypress-io/ai-toolkit --skill cypress-docs