An AI-driven video editing skill that leverages Google Gemini for smart scene analysis, caption generation, and automated editing workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-video-editor
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install gemini-video-editor using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Gemini Video Editor?
The gemini-video-editor is a sophisticated tool within the Openclaw Skills ecosystem designed to transform raw footage into polished, professional content. By utilizing Google Gemini's multimodal intelligence, it goes beyond simple metadata to understand the visual and audio context of your footage. This allows for intelligent suggestions, automated scene detection, and precise narrative structuring that traditional editing tools cannot match.
This skill is essential for creators who need to compress hours of manual work—like scrubbing timelines or drafting scripts—into minutes. As part of your Openclaw Skills library, it bridges the gap between raw media files and publish-ready assets by handling the cognitive heavy lifting of video analysis while leaving the final creative decisions in your hands.
Gemini Video Editor Use Cases
- Automating scene breakdowns and chapter generation for tutorials and educational content.
- Creating social media highlights and intelligent cut suggestions from long-form video files.
- Generating accurate captions and subtitles in various styles, from verbatim to cleaned-up edits.
- Drafting AI-powered voiceover scripts that perfectly align with the visual pacing of your demo.
- Repurposing existing video content for different platforms and audiences using Openclaw Skills.
How Gemini Video Editor Works
- The user provides a video file via multipart upload or a public URL (YouTube, Vimeo, etc.).
- The skill authenticates using a NEMO_TOKEN and initializes a cloud-based project session for the video.
- Google Gemini multimodal engine analyzes the footage to identify key moments, speech patterns, and visual elements.
- Users interact with the agent using natural language to request specific edits, transcriptions, or summaries.
- The skill processes requests through an SSE pipeline, updating the project timeline and draft state in real-time.
- Once editing is complete, the final project is rendered via a cloud proxy and provided as a high-quality download link.
Gemini Video Editor Setup
To get started with this addition to your Openclaw Skills, follow these installation and configuration steps:
- Ensure the NEMO_TOKEN environment variable is set. If not found, the skill will attempt to generate an anonymous token with 100 free credits.
- Configure the local environment at
~/.config/nemovideo/for persistent session management. - Initialize a session using the following logic:
# POST to session creation endpoint
curl -X POST "https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent" \
-H "Authorization: Bearer $NEMO_TOKEN" \
-H "Content-Type: application/json" \
-d '{"task_name":"project"}'
- Use the returned session_id for all subsequent upload and edit operations.
Gemini Video Editor Data Schema & Taxonomy
The skill manages video data through a structured metadata taxonomy mapped to a project draft. The following schema defines how Openclaw Skills organize your video timeline:
| Key | Definition | Description |
|---|---|---|
t |
Tracks | Array of media tracks including video, audio, and text. |
tt |
Track Type | 0 for Video, 1 for Audio, 7 for Text (Captions). |
sg |
Segments | The specific clips or text blocks within a track. |
d |
Duration | The length of a segment in milliseconds. |
m |
Metadata | Scene descriptions, AI-generated tags, and caption text. |
All state transitions are tracked via the session_id and can be retrieved through the latest state API endpoint.
Gemini Video Editor Advanced Features
- Server-Sent Events (SSE) handling for asynchronous, long-running multimodal analysis tasks.
- Multilingual support for caption generation and scene description in various languages.
- Automated GUI-to-API translation allowing natural language commands to trigger complex timeline edits.
- Robust error recovery for session expiration and token management within the Openclaw Skills framework.
- Intelligent credit management and balance tracking for high-volume video processing workflows.
SKILL.md
Loading
Related Openclaw Skills
Personal Development System (PD)
A unified productivity operating system that integrates energy management, habit building, and systems thinking into a local AI-managed framework.
Memory Auto Update
An intelligent context retention engine that automatically identifies, summarizes, and saves critical conversation data to persistent memory files.
Tech News Daily Generator
An automated tool to aggregate tech news from major platforms and generate beautiful, iOS-inspired glassmorphism HTML reports.
Walmart Advertising Strategy
An expert AI skill for mastering Walmart Connect advertising, including campaign setup, bidding strategies, and ROAS optimization.
PingHarbor
A comprehensive monitoring skill for tracking website uptime, cron job heartbeats, and incident reports.
Investment Analysis Framework
A comprehensive three-dimensional investment analysis framework designed to evaluate stocks through macro, industry, and company-level perspectives.
Featured*
