An AI-powered video editing skill for Feishu that automates silence removal, subtitle generation, and video trimming through simple chat commands.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install feishu-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 feishu-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 Feishu AI Video Editor?
The Feishu AI Video Editor is a robust automation tool designed to bridge the gap between cloud-based collaboration and local post-production. As a core part of the Openclaw Skills ecosystem, this tool allows developers and teams to perform complex video manipulations—such as Removing dead air or generating high-accuracy captions—directly from a chat interface. By integrating Whisper for speech recognition and FFmpeg for processing, it provides a high-performance alternative to manual editing workflows.
This skill is particularly valuable for teams that rely on Feishu for internal communications, enabling them to transform raw meeting recordings or training videos into polished, accessible content without leaving their primary workspace. By utilizing the local processing capabilities of Openclaw Skills, users maintain data privacy while benefiting from state-of-the-art AI analysis.
Feishu AI Video Editor Use Cases
- Automatically removing silent segments from lengthy meeting recordings to create concise highlights.
- Generating SRT subtitle files for internal training videos using AI-driven transcription.
- Trimming specific video segments based on precise timestamps provided in a chat command.
- Extracting high-quality audio tracks from video files for separate distribution or archival.
- Merging multiple video clips into a single presentation file for team reviews.
How Feishu AI Video Editor Works
- The user uploads a video to a Feishu cloud space and invokes the assistant with a specific command.
- The Openclaw Skills agent downloads the file to a secure local environment for processing.
- AI modules, including Whisper and Librosa, analyze the audio track to identify speech patterns and silence.
- A dynamic processing plan is formulated based on the user's intent (e.g., trim silence or generate subtitles).
- FFmpeg executes the technical editing tasks, ensuring high-quality output and correct encoding.
- The processed video, audio, or subtitle file is automatically uploaded back to Feishu and shared via a direct link.
Feishu AI Video Editor Setup
First, ensure that FFmpeg is installed on your host system as it is required for all video manipulation tasks:
# For macOS
brew install ffmpeg
# For Ubuntu/Debian
sudo apt update && sudo apt install -y ffmpeg
Next, install the skill using the Openclaw Skills manager:
claw skill install feishu-video-editor
Navigate to the skill directory to install the necessary Python environment:
cd ~/openclaw-skills/feishu-video-editor
pip install -r requirements.txt
Finally, update your config.json with your preferred AI model sizes and silence detection thresholds.
Feishu AI Video Editor Data Schema & Taxonomy
The skill manages video assets and metadata using a structured configuration. The primary data points include:
| Configuration Key | Purpose | Default |
|---|---|---|
| whisper_model | Specifies the Whisper model size (tiny, base, small, medium, large) | base |
| silent_threshold | The decibel level used to identify silence | -50 |
| auto_upload | Whether to sync the final file back to the Feishu cloud | true |
| output_dir | The local directory where processed assets are stored | ~/Videos/edited |
Feishu AI Video Editor Advanced Features
- Intelligent silence detection with granular control over decibel thresholds and minimum duration settings.
- Multi-agent compatibility, allowing the skill to be triggered by other automation scripts or workflows.
- Support for multiple Whisper models, enabling users to choose between rapid processing and maximum transcription accuracy.
- Automated cleanup routines that ensure local storage remains optimized after cloud synchronization is complete.
- Custom FFmpeg encoding presets to balance file size and visual quality based on team requirements.
SKILL.md
Loading
Related Openclaw Skills
Cex Analyzer
A specialized CLI skill designed to analyze Cex operations, evaluate protocol security, and manage on-chain conceptual data.
Feishu Messaging & Documents
An AI agent skill designed to automate Feishu messaging, group management, and document workflows via the Lark Open API.
Bug Data Generator
An intelligent workflow tool that transforms bug descriptions into verified synthetic training data for AI agents.
Security Audit (seguranca-auditoria)
A specialized security auditing utility designed to scan and verify Openclaw Skills for malicious code, prompt injections, and data exfiltration risks.
Z-Shijie Live Resolver
A smart channel resolution skill that maps Z-Shijie television requests and program aliases to live stream URLs and opens them automatically.
Survser
A powerful integration for managing surveys and collecting audience feedback directly through AI-driven workflows.
Featured*
