An AI-powered video editing skill for removing unwanted objects and exporting clean 1080p MP4 files via cloud GPU rendering.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install remover-from-video
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 remover-from-video 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 Remover from Video?
The Remover from Video skill is a sophisticated tool designed for developers and content creators who need to automate video post-production. By leveraging high-performance cloud GPUs, this skill allows users to erase logos, watermarks, or unwanted background objects from video clips using natural language commands. As part of the wider ecosystem of Openclaw Skills, it bridges the gap between raw video footage and polished, professional content.
The skill supports a wide range of formats including MP4, MOV, and WebM, processing files up to 500MB. It operates through a cloud-based pipeline that handles complex compositing and inpainting tasks, ensuring that even users without specialized video editing software can produce high-quality 1080p results in just a few minutes.
Remover from Video Use Cases
- Removing distracting background objects or people from cinematic footage.
- Erasing watermarks and brand logos for cleaner marketing presentations.
- Batch processing multiple clips within a single session to maintain visual consistency.
- Automating the cleanup of stock video assets for YouTube and social media creators.
How Remover from Video Works
- The skill initiates by checking for a NEMO_TOKEN or generating an anonymous session token via the cloud API.
- Users upload their video files which are then queued in a cloud rendering pipeline.
- Natural language instructions are sent via a Server-Sent Events (SSE) stream to define the removal area or editing intent.
- A cloud GPU node processes the video layers, applying platform-specific compression and AI object removal.
- The system monitors the rendering status through polling and provides a secure download URL for the final 1080p MP4 file.
Remover from Video Setup
To get started with this skill, ensure you have your environment configured properly. This skill requires a connection to a cloud backend.
# Set your environment variable
export NEMO_TOKEN="your_token_here"
# If no token is provided, the skill will auto-generate an anonymous token
# via POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token
Once the token is set, the skill will automatically manage session creation and file uploads within the Openclaw Skills framework.
Remover from Video Data Schema & Taxonomy
The skill manages video data through a structured JSON draft system and session-based state management. Below are the primary data structures used:
| Key | Definition | Description |
|---|---|---|
| t | Tracks | Array of media tracks (video, audio, text) |
| tt | Track Type | 0: Video, 1: Audio, 7: Text |
| sg | Segments | Specific time segments within a track |
| d | Duration | Duration of the segment in milliseconds |
| m | Metadata | Extra data for rendering parameters |
Supported file formats include: mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, and aac.
Remover from Video Advanced Features
- Iterative Editing: The session-based architecture allows users to keep their timeline state for multiple rounds of refinement without re-uploading.
- Real-time SSE Feedback: Provides live status updates and heartbeats during intensive GPU processing tasks.
- Multi-Layer Compositing: Supports complex timelines with video, background music (BGM), and text overlays simultaneously.
- Automated Credit Management: Built-in handling for anonymous token credits and easy registration hooks for power users within the Openclaw Skills ecosystem.
SKILL.md
Loading
Related Openclaw Skills
Trimmer In Between
A high-performance AI video editing tool designed to trim unwanted segments and merge clips with cloud GPU acceleration.
Pilot Service Agents Books
A dedicated skill for searching Project Gutenberg and Open Library records via the Pilot protocol.
Museum & Cultural Collection Agents
A specialized set of AI agents providing structured access to world-renowned cultural archives and museum artwork metadata.
Academic Service Agents
A specialized suite of agents for querying global scholarly literature databases and bibliographic metadata through the pilot protocol.
Kre Video
A high-performance AI video creation tool for Openclaw Skills that transforms raw footage into polished 1080p clips via simple text commands.
Video CLI
A command-line video editor that uses cloud GPU rendering to edit, trim, and export 1080p videos via natural language or CLI commands.
Featured*
