Plugin Claude Code
Automate Google NotebookLM at scale. Citation-backed Q&A, full Studio generation (audio, video, infographic, report, presentation, data table), multi-account rotation with auto-reauth, and batchtovault for offline RTFM-ingestable answer caching.
Skill Claude CodeCodex
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…
MCP server Claude CodeCodexCursor +2
Automate Google NotebookLM — Q&A with citations, audio, video, content generation. Runs locally from the @roomi-fields/notebooklm-mcp npm package.
Plugin Claude Code
The open retrieval layer for AI agents — indexes code, docs, data. Search via MCP.
MCP server Claude CodeCodexCursor +2
MCP server "rtfm" as configured in roomi-fields/rtfm. Launched with rtfm-serve. Needs 1 environment variable to run.
Command
Enable persistent OCR fallback for scanned PDFs and run the OCR pass in the background.
Command
Show full RTFM index status (with pending-sync counts and health signals).
Hook
Runs when a session starts, running an inline shell check. From roomi-fields/rtfm.
Hook
Runs after a tool call finishes for Write, Edit, MultiEdit and NotebookEdit tool calls, running an inline shell check. From roomi-fields/rtfm.
Hook
Runs when you submit a prompt, before the agent sees it, running an inline shell check. From roomi-fields/rtfm.
Hook
Runs when the agent finishes a response, running an inline shell check. From roomi-fields/rtfm.
Skill Claude CodeCodex
Read the full content of a specific file or section previously returned by rtfmsearch. Use when the user wants to see the actual content of a search result, not just metadata.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
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.
Plugin Claude Code
Declarative OSC ↔ MIDI/SysEx bridge for 849 hardware synthesizers and music software (Ableton, Bitwig, Reaper, Sonic Pi, SuperCollider, Pure Data). A MIDI MCP and OSC MCP — discover the device catalogue, read a device's OSC surface, and send OSC to synths and DAWs from Claude.
MCP server Claude CodeCodexCursor +2
OSC ↔ MIDI bridge — 849 synthesizers and DAWs. A MIDI MCP and OSC MCP for controlling them. Runs locally from the @roomi-fields/osc-bridge npm package.
Plugin Claude Code
Plugin Claude Code anti-hallucination pour la recherche scientifique. Cree des SOTAs (etats de l'art) garantis sans fabrication, audite les SOTAs/articles existants (purge ou warnings), avec un moteur de validation strict (FSM 8 etats + cascade d'acquisition PDF + page 1 anti-homonymie + 19 invariants de coherence).…
Agent
Sub-agent that orchestrates the PDF acquisition cascade for a batch of refs. Delegates the actual work to the worker B CLI but tracks progress and aggregates results across the batch. Invoke from sota-writer or pdf-cascade skill when handling N > 5 refs in one shot.
Agent
Sub-agent that parses bibliographic sections and inline citations from SOTA / article text. Takes raw text (a section header + content, or an inline excerpt) and returns structured JSON [{author, year, title, doi?, venue?, raw}]. Isolates the LLM extraction from the main agent context. Invoke from the INGEST pipeline…
Agent
Sub-agent that audits a specific claim against the PDF cited. Invoked by citation-receipts skill for deep PDF↔claim verification. Returns structured verdict (VALID/ADJUST/INVALID/UNVERIFIABLE) with evidence quoted from the source. Isolates the heavy PDF reading from the main agent's context.
Agent
Sub-agent that validates whether a downloaded PDF matches the expected metadata (author, title, year). Anti-homonymy check on page 1. Invoke when a manual page 1 verification is needed on an acquired PDF, separate from the cascade's automatic validation.
Agent
Sub-agent that performs exhaustive multi-source academic search (paper-search MCP across 22 platforms + optional NotebookLM + optional WebSearch). Returns structured JSON of candidate refs for sota-writer phase A. Invoke when broad literature search is needed without polluting the main agent's context.