Turns NotebookLM into a research backend for Claude Code, letting you query your uploaded documents and get citation-backed answers without hallucination risk. The workflow is straightforward: authenticate once with Google, add notebooks to your library with discovered metadata, then ask questions that get answered exclusively from your sources. Responses come back as Tier 1 evidence with inline citations and bibliography entries, which makes this a clean path to verified statistics and quotes. The implementation uses headless Chrome sessions per query and falls back gracefully when not configured, so blog-write and blog-researcher can call it without blocking their workflows. If you're maintaining a notebook library of primary sources and want to pull from them during research, this does exactly that.
npx -y skills add agricidaniel/claude-blog --skill blog-notebooklm --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
supercent-io/skills-template
supercent-io/skills-template
huangjia2019/claude-code-engineering
remotion-dev/remotion
reactjs/react.dev