skills/notebooklm/SKILL.md
# Skill: NotebookLM (The Researcher) --- name: notebooklm version: 1.0 category: intelligence owner: antigravity sot: true mandatory_read: NO capabilities: filesystem: read process: exec network: scoped (NotebookLM API) scope: - "~/0luka" --- ## 1. Identity - **Role**: Intelligence Synthesis & Research Specialist. - **Purpose**: - Leverage Google's NotebookLM for deep document analysis and creative synthesis. - Perform autonomous web and drive research to expand codebase knowledge.
npx skillsauth add ic1558/0luka skills/notebooklmInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
name: notebooklm version: 1.0 category: intelligence owner: antigravity sot: true mandatory_read: NO capabilities: filesystem: read process: exec network: scoped (NotebookLM API) scope:
| Tool | Description/Contract |
| :--- | :--- |
| notebook_list | List all available notebooks. |
| notebook_create | Create a new notebook with an optional title. |
| notebook_get | Retrieve full notebook details including source metadata. |
| notebook_describe | Get an AI-generated summary and suggested topics for a notebook. |
| notebook_rename | Update the title of an existing notebook. |
| notebook_delete | Permanently delete a notebook (requires confirm=True). |
| Tool | Description/Contract |
| :--- | :--- |
| notebook_add_url | Add a website or YouTube video as a source. |
| notebook_add_text | Add raw text content as a source. |
| notebook_add_drive | Add a Google Drive document (Doc, Slides, Sheet, PDF) as a source. |
| source_describe | Get AI-generated summary and keywords for a specific source. |
| source_get_content | Export raw text content from a source (high speed). |
| source_list_drive | Check freshness status of Drive-linked sources. |
| source_sync_drive | Sync stale Drive sources with latest content. |
| source_delete | Permanently delete a source from a notebook. |
| Tool | Description/Contract |
| :--- | :--- |
| notebook_query | Ask targeted questions against established sources. |
| chat_configure | Set specific goals or custom prompts for the notebook AI. |
| research_start | Launch "Deep" or "Fast" research tasks (Web/Drive). |
| research_status | Monitor the progress of ongoing research tasks. |
| research_import | Ingest completed research findings into the notebook. |
| Tool | Description/Contract |
| :--- | :--- |
| audio_overview_create | Generate podcasts/audio deep dives. |
| video_overview_create | Generate visual explainer videos in various styles. |
| infographic_create | Create structured visual representations of data. |
| slide_deck_create | Synthesize sources into presentation-ready slides. |
| report_create | Generate Briefing Docs, Study Guides, or Blog Posts. |
| flashcards_create | Create study aids from notebook content. |
| quiz_create | Generate interactive assessments. |
| data_table_create | Extract structured data into tabular format. |
| mind_map_create | Map relationships between notebook concepts. |
| studio_status | Retrieve status and URLs for generated artifacts. |
| studio_delete | Clean up studio artifacts. |
| Tool | Description/Contract |
| :--- | :--- |
| refresh_auth | Reload tokens or trigger headless re-auth. |
| save_auth_tokens | Manual token injection (Fallback method). |
delete) and token-heavy operations (sync, studio) require explicit confirm=True after user review.start -> status -> import sequence.refresh_auth is called if session expires.studio_status or notebook_get for output evidence.AUTH_EXPIRED: Requires notebooklm-mcp-auth manual intervention.SOURCE_NOT_READY: Attempting to query before indexing is complete.SYNC_CONFLICT: Drive permissions changed or file moved.STUDIO_TIMEOUT: Generation took longer than 300s.development
--- name: auto-workflow-creator description: Create a new skill from a workflow you just performed. Generates a valid 3-layer Anthropic-style skill — YAML frontmatter (name + description + triggers), imperative instruction body, and optional scripts/ subdirectory — and prints the registration commands per target runtime (Claude Code auto-discovers from ~/.claude/skills/; Codex needs an explicit [[skills.config]] entry in ~/.codex/config.toml; OpenCode needs a registry entry in ~/.opencode/openco
tools
# Cost-Control Skill Enforce token discipline and model routing optimization (Flash vs Pro) via the Gemini CLI 0.40 Gemma local router for governed-agent workflows. ## Guidelines - **Preference for Local/RTK/File Tools:** Always prioritize local tools (ls, read_file, grep_search) and RTK for initial data gathering before calling model logic. - **Flash-First Routing:** - Route all routine code analysis, file reads, summarization, search, and classification tasks to `gemini-3.5-flash-preview` o
development
--- name: verify-first description: Run verification gates before and after code changes, prioritize health and regressions, and fail closed on missing evidence. Mandatory Read: YES --- # Verify First Mandatory Read: YES ## Workflow 1. Capture baseline verify results. 2. Apply minimal changes. 3. Re-run targeted and system-level verify commands. 4. Report explicit pass/fail evidence. ## Caps - Run deterministic verification commands. - Compare before/after outcomes. - Block claims without pr
testing
Use this skill when you need to perform a READ-ONLY forensic validation of a completed task (evidence), verify compliance against a TaskSpec, or issue a formal verdict (PASS/FAIL) before GMX approval. Strictly forbids modification or execution.