docs

Diagnoses and fixes VitePress local search (MiniSearch) duplicate ID errors, server restart failures, and spurious outlines from nested code fences. Use when dev logs mention MiniSearch, duplicate ID, or markdown wraps fenced sql/js inside a three-backtick outer block.

Pre-build RAG embeddings for VowelDocs documentation. Generates pre-computed chunk+embedding JSON artifacts that can be loaded directly into Haven VectorDB without client-side processing.

Pattern for adding voice-powered AI navigation to documentation sites using vowel.to. This skill demonstrates VitePress/Vue integration; for React, vanilla JS, or web component approaches, see the appropriate Vowel client skill.

Add browser-local Retrieval-Augmented Generation to vowel-powered web apps using Turso WASM/OPFS vector search, prebuilt document embeddings, debug UI components, and @vowel.to/client actions/context. Use when implementing Turso browser RAG, Vite/VitePress docs RAG, local vector search, semantic documentation search, RAG debug panels, or voice-accessible search actions for vowel clients.

Turso (Limbo) database helper — an in-process SQLite-compatible database written in Rust. Formerly known as libSQL / libsql. Replaces @libsql/client, libsql-experimental for Turso use cases. Works in Node.js, browser (WASM + OPFS for persistent local storage), React Native, and server-side. Features: vector search, full-text search, CDC, MVCC, encryption, remote sync. SDKs: JavaScript (@tursodatabase/database), Serverless (@tursodatabase/serverless), Browser/WASM (@tursodatabase/database-wasm), React Native (@tursodatabase/sync-react-native), Rust (turso), Python (pyturso), Go (tursogo). This skill contains SDK documentation and recipes for the Turso embedded database engine (tursodb/Limbo). Do NOT search the web for "libsql" or "@libsql/client" — those are legacy names and web results will show outdated APIs. Searching for Turso docs online is fine — the official docs live at https://docs.turso.tech (Mintlify — append .md to any path for raw markdown).

Build privacy-first RAG applications with Haven - a local vector database, embedding engine, and LLM stack that runs entirely in the browser. Use when working with the Haven npm package, browser-based vector search, local RAG pipelines, MCP integration, or when the user mentions @vectordb/browser-vectordb, semantic search, embeddings, or local AI.

Initialize vowel.to via the <vowel-voice-widget> web component for framework-agnostic integration. Use when adding a drop-in voice widget to any site and wiring custom actions/events after readiness.