roomi-fields
UserGoogle NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.
Categories
Indexed Skills (8)
notebooklm
This skill should be used when the user wants to query their Google NotebookLM notebooks for citation-backed, source-grounded answers, or manage notebooks, sources, and Studio content (audio, report, video, infographic, presentation, data table, flashcards, quiz, mind map). It drives the @roomi-fields/notebooklm-mcp engine — via the notebooklm MCP tools when they are available in the session, otherwise via its HTTP REST API — and covers Google login, citation formats, the daily-quota-aware batch/ingestion pattern, and source discovery.
notebooklm
This skill should be used when the user wants to query their Google NotebookLM notebooks for citation-backed, source-grounded answers, or manage notebooks, sources, and Studio content (audio, report, video, infographic, presentation, data table, flashcards, quiz, mind map). It drives the @roomi-fields/notebooklm-mcp engine — via the notebooklm MCP tools when they are available in the session, otherwise via its HTTP REST API — and covers Google login, citation formats, the daily-quota-aware batch/ingestion pattern, and source discovery.
install-pdf-full
Install the full PDF parser (pdftext + marker-pdf + CPU-only torch, ~1.5 GB) into an isolated venv. Needed for complex layouts — tables, figures, scanned documents. Skip this if /rtfm:install-pdf (~50 MB, text only) is enough.
install-pdf
Install the light PDF parser (pdftext, ~50 MB) into an isolated venv. Covers most PDFs with fast, accurate text extraction. For complex layouts (tables, figures, scanned docs), use /rtfm:install-pdf-full instead.
expand
Read the full content of a specific file or section previously returned by rtfm_search. Use when the user wants to see the actual content of a search result, not just metadata.
install-embeddings
Install the embeddings extra (fastembed, ~85 MB ONNX model) into an isolated venv. Required for semantic and hybrid search modes. The model runs on CPU, no GPU needed.
search
Search the RTFM-indexed corpus of the current project (code, docs, data). Use for any exploratory search — finding relevant files, modules, symbols, or content. Faster and more precise than Glob/Grep/find for broad queries.
osc-bridge
This skill should be used when the user wants to control music hardware or software from Claude via osc-bridge — playing or tweaking a hardware synthesizer over MIDI/SysEx (849 device drivers), driving a DAW (Ableton Live, Bitwig, Reaper) over OSC, or sending OSC to live-coding environments (Sonic Pi, SuperCollider, Pure Data, TouchDesigner, VCV Rack). It covers finding the right device driver, reading its OSC surface, the two-process architecture (MCP server plus the running bridge), MIDI port discovery, and the failure modes that are silent by design.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.