// Ingest and vectorize PDFs or text files for RAG retrieval. Use when the user provides a PDF, document, or text file they want to analyze, study, or generate content from.
Generate rich outputs from ingested sources — flashcards, quizzes, reports, slide decks, mind maps, infographics, data tables, or audio overviews. Use when the user wants to create any output from their documents.
Launch a live NotebookLM-style dashboard for managing sources and generating outputs. Use when the user wants a visual interface, dashboard, or UI for their notebook.
| name | ingest |
| description | Ingest and vectorize PDFs or text files for RAG retrieval. Use when the user provides a PDF, document, or text file they want to analyze, study, or generate content from. |
| argument-hint | <file-path> |
| compatibility | Requires Bun 1.0+. First run downloads ~23MB embedding model. |
| allowed-tools | Bash(bash *) Bash(bun *) Bash(node *) Read |
Ingest a PDF or text file into the local vector store for retrieval-augmented generation.
bun "${CLAUDE_SKILL_DIR}/scripts/ingest.mjs" $ARGUMENTS
bun "${CLAUDE_SKILL_DIR}/scripts/list.mjs"
To retrieve relevant chunks for any generation task:
bun "${CLAUDE_SKILL_DIR}/scripts/query.mjs" "<question>" --top-k 15
--no-ocr to skip.~/.notebook-plugin/ across sessions. Use clear to reset.