NotebookLM-style research assistant — ingest PDFs, then generate audio overviews, slide decks, mind maps, reports, flashcards, quizzes, infographics, and data tables from your sources.
Quality review agent that evaluates generated outputs against source material. Use to verify accuracy, completeness, and quality of flashcards, quizzes, reports, or any generated content before finalizing.
Main orchestrator and deep research agent for the Notebook plugin. Analyzes ingested PDF/text sources via RAG, then delegates to writer and critic agents for content generation and quality review.
Content generation agent for creating output artifacts from research findings. Use when producing flashcards, quizzes, reports, podcast scripts, slide decks, mind maps, infographics, or data tables from analyzed sources.
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.
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.
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.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A NotebookLM-style research assistant plugin for Claude Code. Ingest PDFs and text files, then generate rich outputs from your sources — all from the command line.

| Type | Generator | Output files |
|---|---|---|
| Flashcards | Interactive study cards with flip animations, tag filtering, keyboard nav | .json + .md + .html |
| Quiz | 50-question assessment with live scoring, letter grades, answer review | .json + .md + .html |
| Report | Structured analysis with executive summary and evidence-backed findings | .md + .docx |
| Slide Deck | Professional presentation with speaker notes | .pptx |
| Mind Map | Interactive diagram with pan/zoom canvas and Mermaid rendering | .mmd + .html |
| Infographic | Visual summary with scroll animations, floating TOC, and stat callouts | .html |
| Data Table | Sortable/filterable table with search, pagination, and CSV/JSON export | .csv + .json + .md + .html |
| Audio Overview | Podcast-style two-host discussion using Kokoro-82M neural TTS | .wav |
All HTML outputs feature a unified dark theme with Inter typography, Lucide icons, keyboard shortcuts, and responsive design.
/init
This registers the plugin skills and prepares the environment. You can also install manually:
/plugin marketplace add damionrashford/notebook-plugin
/plugin install notebook@notebook-marketplace
/plugin install damionrashford/notebook-plugin
afconvert)/notebook:ingest path/to/document.pdf
/notebook:ingest path/to/notes.txt
Supports text-based PDFs and scanned PDFs (auto-OCR via Tesseract.js). Multiple files can be ingested into the same store.
/notebook:generate flashcards
/notebook:generate quiz
/notebook:generate report
/notebook:generate slide-deck
/notebook:generate mind-map
/notebook:generate infographic
/notebook:generate data-table
/notebook:generate audio-overview
Add an optional topic to focus the output:
/notebook:generate flashcards neural networks
/notebook:generate report transformer architecture
/notebook:dashboard
Generates a NotebookLM-style HTML dashboard showing your ingested sources, available output types, and generated files.
# Query the vector store directly
bun skills/ingest/scripts/query.mjs "your question" --top-k 15
# List ingested sources
node skills/ingest/scripts/list.mjs
The plugin uses three orchestrated agents:
| Agent | Role | Access |
|---|---|---|
| Researcher | Deep document analysis — runs 5-10 queries to explore sources from multiple angles | Read-only |
| Writer | Generates all output artifacts from research findings | Full write access |
| Critic | Reviews outputs against source material, catches errors and gaps | Read-only |
Pipeline flow: Researcher analyzes sources -> Writer generates artifact -> Critic reviews against sources -> Writer revises if needed
~/.notebook-plugin/stores/<project-hash>/ — persists across sessions| Path | Purpose |
|---|---|
~/.notebook-plugin/ | Vector store and embedding model cache |
./output/ | All generated artifacts |
~/.claude/plugins/data/notebook/ | Installed npm dependencies (managed by hook) |
npx claudepluginhub damionrashford/notebook-plugin --plugin notebook9 research tools: 5-engine web search, 9 social platforms, 5 news sources, 5 academic databases, GitHub, website mapping, document analysis, and research topic synthesis. No API keys required. Deterministic outputs for agent chaining.
Agent skill and CLI helpers for using RivalSearchMCP research tools from Claude Code. Includes workflows, command references, and a standalone CLI for the hosted MCP server.
The Media OS for Claude Code with routed modes dispatch. 96 production-grade skills + 13 modes (routed playbooks) + 7 orchestrator agents (architect, probe, qc, hdr, encoder, live, delivery) + 5 safety + audit hooks + workflow monitors + a PATH-level CLI toolbelt, covering the entire professional media stack — FFmpeg complete (transcode, filters, streaming, HDR, color, broadcast MXF/IMF, DRM, 360°, VapourSynth), professional companion CLIs (yt-dlp, MKVToolNix, GPAC, Shaka, HandBrake, MoviePy, MediaInfo, PySceneDetect, ffsubsync, ffmpeg-normalize, ImageMagick, ExifTool, SoX, GNU parallel, cloud upload), OBS Studio full stack, streaming frameworks (GStreamer, MediaMTX), broadcast IP (NDI SDK, OpenTimelineIO, HDR dynamic metadata via dovi_tool + hdr10plus_tool, Blackmagic DeckLink, gphoto2), low-level control (MIDI 1.0 + 2.0 UMP, OSC, DMX512/Art-Net/sACN, VISCA + ONVIF PTZ), system audio routing (PipeWire, JACK, Core Audio, WASAPI), VFX (USD, OpenEXR, OpenImageIO), computer vision (OpenCV, MediaPipe), WebRTC (W3C spec, Pion/mediasoup/LiveKit SFUs), and 2026 open-source AI media (Real-ESRGAN/SwinIR/HAT upscale, RIFE/FILM interpolation, rembg/BiRefNet/RVM matting, Kokoro/OpenVoice/Piper TTS, Depth-Anything/MiDaS depth, ComfyUI/FLUX-schnell/Kolors image gen, LTX-Video/CogVideoX video gen, LivePortrait/LatentSync lipsync, PaddleOCR/Tesseract 5 OCR, DeepFilterNet/RNNoise audio denoise, CLIP/SigLIP/BLIP-2/LLaVA tagging). Strict OSI-open + commercial-safe license filter on every AI model.
Critical thinking platform for decision analysis, proposal review, debate preparation, and due diligence. Three agents (advocate, adversary, judge) with a structured argument graph, sequential thought chain, and 10 reasoning traditions.
ML Workbench for Claude Code. Full ML lifecycle: search papers across 7 academic sources, discover and download datasets from 5 repositories, explore and clean data, engineer features, train models (Naive Bayes, KNN, LDA/QDA, SVM, Decision Trees, Ensembles, GLM, Gaussian Process, Neural Networks), run autonomous experiments, build AI apps with LLMs and RAG, build MCP servers, deploy models with Docker and CI/CD, detect drift, explain predictions with SHAP, generate podcasts from papers, manage notebooks, extract YouTube content, and learn ML interactively with 3 university-grade courses (CS229, Applied ML, ML Engineering). 11 agents, 16 skills, 3 CLI tools (mlx-exp, mlx-search, mlx-status), 1 MCP server, 3 output styles, Python LSP via pyright.
Generate NotebookLM artifacts (slides, audio, video, mind maps, quizzes, flashcards, infographics, reports, data tables) from your notebooks. Use when the user wants to create any NotebookLM Studio output from their uploaded sources.
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 batch_to_vault for offline RTFM-ingestable answer caching.
Transform academic PDFs into structured literature notes and critical-thinking canvases for Obsidian
AI thinking partner for your Obsidian vault — process, recall, synthesize, research with evidence-backed learning science
End-to-end slide deck creation via RDIV workflow. Requires paperbanana plugin for image generation.
Collection of academic skills based on effortlessacademic.com note taking ideas like atomic sentences.