Video Toolkit for Openclaw

An automated AI video editing suite that converts raw clips into polished 1080p MP4 files using natural language commands and cloud-based GPU rendering.

whitejohnk-26
v1.0.0
Apr 12, 2026
0
357
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install video-toolkit

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install video-toolkit 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 Video Toolkit?

The Video Toolkit is a specialized suite within the ecosystem of Openclaw Skills designed for creators who need professional-grade video edits without the complexity of traditional software. By leveraging remote GPU nodes, this skill allows users to perform intensive tasks like compositing layers, generating captions, and performing automated cuts entirely in the cloud.

This skill bridges the gap between raw footage and social-ready content by interpreting natural language intent. Whether you are looking to trim the silent pauses, add captions, or perform a batch export of high-definition assets, the toolkit handles the underlying API orchestration and rendering pipeline automatically.

Video Toolkit Use Cases

  • Automatically removing silent gaps from screen recordings or talking-head videos.
  • Generating and overlaying text captions for social media accessibility.
  • Converting multiple raw formats like MOV, WebM, or AVI into standardized 1080p MP4 files.
  • Rapidly prototyping video edits through iterative natural language feedback loops.

How Video Toolkit Works

  1. Authentication: The skill initializes a connection using the NEMO_TOKEN or generates an anonymous session token.
  2. Asset Upload: Source files up to 500MB are uploaded to remote processing servers.
  3. Intent Processing: Natural language instructions are sent via Server-Sent Events (SSE) to the AI editing engine.
  4. State Management: The skill tracks the project timeline, including video tracks, audio layers, and text segments.
  5. Rendering: A cloud GPU render job is triggered to composite the final video according to the draft state.
  6. Export: The system polls the render status and provides a final download URL for the processed MP4.

Video Toolkit Setup

To begin using this skill, ensure you have your environment configured. If you do not have a paid token, the skill will automatically provision an anonymous one with 100 credits.

# Set your API token as an environment variable
export NEMO_TOKEN="your_nemo_token_here"

# Configuration files are managed in the following directory
# ~/.config/nemovideo/

Video Toolkit Data Schema & Taxonomy

The skill organizes video projects using a structured draft schema to manage the timeline and assets:

Key Definition Details
t Tracks A collection of all media layers (video, audio, text)
tt Track Type 0 = Video, 1 = Audio, 7 = Text
sg Segments Individual clips or segments within a specific track
d Duration The length of the segment in milliseconds
m Metadata Technical properties and file info for the uploaded media

Video Toolkit Advanced Features

  • Real-time SSE Stream Handling: Processes long-running AI operations with live feedback and heartbeat monitoring.
  • Automated Silence Removal: Identifies and removes low-volume segments to create punchy, fast-paced edits.
  • Cloud GPU Render Pipeline: Offloads heavy H.264 compression and compositing to remote nodes, preserving local resources.
  • Session-Based Persistence: Maintains the state of your video draft across multiple prompts within the same Openclaw Skills session.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Github Stars: 0
forks: 0

Featured*