google-gemini-media
CommunityDeliver multimodal media workflows with Gemini
AuthorShenWang96
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Managing and orchestrating Gemini's image, video, and audio capabilities across generation and understanding is complex; this Skill consolidates them into reusable workflows and templates for end-to-end media production and analysis.
Core Features & Use Cases
- Image generation (Nano Banana) to produce high-fidelity visuals from prompts.
- Image understanding (captioning, VQA, classification, multi-image prompts) to extract insights and metadata.
- Video generation (Veo 3.1) to create short-form content with optional audio.
- Video understanding (analyze YouTube/direct uploads) to summarize and extract timestamps.
- Speech generation (TTS) for controllable narration.
- Audio understanding (transcription, description, token counting) for media insights.
Quick Start
Provide a Gemini-based prompt and use the included templates to generate media assets and corresponding understanding outputs.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: google-gemini-media Download link: https://github.com/ShenWang96/clawdbot_workspace_backup/archive/main.zip#google-gemini-media Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.