A comprehensive automation skill for CapCut that enables AI agents to create, edit, and render video drafts via a local or cloud-based API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install capcut-mate-skill
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 capcut-mate-skill 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 CapCut Mate Automation?
CapCut Mate is a powerful, open-source automation assistant designed to integrate seamlessly with the CapCut (Jianying) ecosystem. By leveraging the Openclaw Skills framework, it allows Large Language Models to perform programmatic video editing tasks, bridge the gap between creative prompts and professional video output.
The skill provides a robust API bridge to the CapCut desktop or server environment, enabling the automated creation of drafts, batch importing of media assets, and sophisticated timeline management. It effectively turns CapCut into a headless video engine that can be controlled by AI agents for high-volume content production.
CapCut Mate Automation Use Cases
- Automated short-video generation from AI-written scripts.
- Batch processing of social media content with consistent branding and styles.
- AI-driven video subtitle and caption generation with keyword highlighting.
- Programmatic application of visual effects, stickers, and transitions to raw footage.
- Remote video rendering pipelines using the CapCut Mate server.
How CapCut Mate Automation Works
- The user or AI agent initiates a request through the Openclaw Skills interface to create a new project.
- CapCut Mate creates a local draft file (.draft) with specified canvas dimensions and settings.
- Media assets (videos, images, audios) are imported via URL or local paths and arranged on the timeline based on calculated durations.
- The agent applies sophisticated layers like text styles, keyframe animations, and masks through specific API endpoints.
- Once the draft is complete, the skill triggers the rendering process to generate the final video file or saves the draft for manual refinement.
CapCut Mate Automation Setup
Server Deployment
Ensure you have Python 3.11+ and the uv package manager installed.
# Clone the repository
git clone https://github.com/Hommy-master/capcut-mate.git
cd capcut-mate
# Install dependencies
uv sync
# For Windows users: uv pip install -e .[windows]
# Start the API service
uv run main.py
Openclaw Configuration
Add the following endpoint to your TOOLS.md or environment variables:
- CAPCUT_MATE_URL: http://localhost:30000/openapi/capcut-mate/v1
CapCut Mate Automation Data Schema & Taxonomy
The skill manages video projects through a structured JSON-based draft system. Key data components include:
| Data Type | Description |
|---|---|
| Draft Metadata | Includes project ID, canvas size (16:9, 9:16), and frame rate. |
| Material Tracks | Organized by type (video, audio, text, sticker) with precise start/end timestamps. |
| Timeline Config | Generated via timelines and audio_timelines to ensure synchronization. |
| Asset Schemas | Detailed objects for video_infos, caption_infos, and effect_infos mapping URLs to timeline positions. |
CapCut Mate Automation Advanced Features
- Multi-agent support via Coze plugin integration for collaborative video editing.
- Keyframe animation engine for programmatic control of position, scale, and rotation.
- Batch captioning with rich text styling and automatic keyword highlighting.
- Headless server mode using Docker for cloud-based rendering pipelines.
- Desktop GUI client available via Electron for visual monitoring of automated tasks.
SKILL.md
Loading
Related Openclaw Skills
Agent Content Analyzer
A professional tool for analyzing AI Agent news data to extract trending topics, evaluate market heat, and generate actionable content creation inspiration.
Smart-Speak Multilingual TTS
A sophisticated text-to-speech engine that intelligently handles mixed Vietnamese, Chinese, and English text with automatic Pinyin-to-Hanzi conversion.
Gemini Smart Search
A specialized search skill for Openclaw agents that leverages Gemini with Google Search grounding and intelligent model fallback routing.
TRON Account Profiling
A comprehensive analytical tool for profiling TRON addresses, covering assets, resources, staking, and on-chain behavior.
TRON Token Scanner
A comprehensive analysis tool for auditing TRC-20 and TRC-10 tokens on the TRON network, covering supply, holders, and contract safety.
ImageFlare
A command-line interface for generating and transforming images using the Cloudflare Workers AI global network.
Featured*
