skills.rest
dige04
dige04COMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai-tools

Orchestrate Gemini and NotebookLM capabilities within Claude Code for multimodal tasks.

Updated Dec 23, 2025
Search Tags:#automation#multimodal#gemini#code-review#notebooklm#web-grounding#google-genai
One-click install
npx skills add https://github.com/dige04/hieu-ccsetup --skill ai-tools-dige04
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-tools
Source: https://github.com/dige04/hieu-ccsetup/tree/main/config/skills/ai-tools
Command: npx skills add https://github.com/dige04/hieu-ccsetup --skill ai-tools-dige04

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires patchright, google-genai, python-dotenv, Pillow, and includes references (resource) components.

What problem does it solve?

This integration aggregates Google's Gemini ecosystem (Gemini API, Gemini CLI) with NotebookLM into a single, coherent toolkit that reduces context switching for multimodal AI workflows.

Core Features & Use Cases

  • Gemini API (multimodal): transcribe, analyze, extract, and generate across audio, images, videos, PDFs.
  • Gemini CLI: orchestrates code reviews, web grounding, and second opinions.
  • NotebookLM: grounded Q&A from uploaded documents with source references.
  • Typical use cases include media processing, web research grounding, and document-based questioning.

Quick Start

Run a simple workflow by querying a NotebookLM notebook with Gemini outputs to get grounded, multimodal results.

Frequently Asked Questions about ai-tools

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I process audio, video, and PDF files for multimodal analysis in Claude Code?▼

Multimodal analysis of audio, video, and PDF files is handled by orchestrating the Gemini API to transcribe, extract, and generate content directly within Claude Code workflows.

Can I use NotebookLM for document-grounded Q&A with source references?▼

Yes, NotebookLM enables grounded Q&A from uploaded documents, providing answers backed by source references to ensure accuracy for text and media-based queries.

How do I run code reviews and get second opinions using Gemini CLI?▼

Gemini CLI orchestrates code reviews and provides second opinions by leveraging web grounding, allowing you to validate outputs and context directly during your software engineering tasks.

What dependencies are required to integrate Gemini and NotebookLM capabilities?▼

Integration requires the patchright, google-genai, python-dotenv, and Pillow dependencies, along with proper environment setup for Gemini API/CLI and NotebookLM access.

Does this toolkit support web research grounding for multimodal tasks?▼

Web research grounding is fully supported through the Gemini CLI, enabling teams to anchor multimodal queries and code reviews in real-time web data alongside local document processing.

What is the best way to combine Gemini outputs with NotebookLM queries?▼

The recommended quick start workflow feeds Gemini API multimodal outputs directly into a NotebookLM notebook query, producing grounded results that reference original source documents.

Related Skills

Explore More Software Engineering Skills→
nguyenvanlinh1902nguyenvanlinh1902

ai-multimodal

Extract insights from images, audio, and video using Gemini multimodal APIs.

Community
Advanced
math-incmath-inc
1.2k

youtube-content

Extract YouTube transcripts and convert them into JSON or text formats.

Official
Intermediate
muskie9muskie9

visual-regression-upgrade

Capture full-page screenshots with Playwright and compare pixel differences using numpy.

Community
Advanced
allenhutchisonallenhutchison
515

gemini-api-dev

Build applications with Gemini models across Python, JavaScript, Java, and Go SDKs.

Community
Advanced