A comprehensive multimedia toolkit for processing, analyzing, and generating audio and video files within an AI-driven environment.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install av
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 av 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 AV Skill?
The AV skill is a robust extension designed for the Openclaw Skills ecosystem, enabling AI agents to manage complex multimedia tasks with ease. It serves as a bridge between raw media files and professional output, providing a full suite of tools for format conversion, metadata extraction, and automated content generation.
By integrating this skill, developers can empower their agents to handle diverse media formats, apply specialized audio effects, and even generate visual content from text. It is designed to maintain high output quality while ensuring efficient resource usage during intensive processing tasks.
AV Skill Use Cases
- Converting legacy audio files to modern formats like MP3 or FLAC for better compatibility.
- Trimming and cutting video segments to create highlights or short-form content.
- Extracting audio streams from video files for separate processing or transcription workflows.
- Analyzing media properties such as bitrate and resolution to optimize files for web delivery.
- Generating automated slideshows from image sets or creating video previews from text descriptions.
How AV Skill Works
- The skill identifies the media task based on user intent, whether it involves a local file or a remote URL.
- It analyzes the source file's technical properties using built-in codecs and algorithms.
- The requested operation—such as merging files, adjusting resolution, or applying filters—is executed in a secure environment.
- Progress updates are provided for long-running operations to ensure transparent workflow management.
- The final processed file or detailed metadata report is returned as the output.
AV Skill Setup
To get started with this skill within the Openclaw Skills framework, you need to ensure basic media codecs are installed on your host system. Install the skill via the CLI:
openclaw install av
Ensure you have sufficient storage for temporary processing files and an active internet connection if you plan to use Text-to-Speech (TTS) or cloud-based generation features.
AV Skill Data Schema & Taxonomy
The skill organizes processed data and technical metadata into clear, structured formats for further use in Openclaw Skills workflows:
| Component | Data Type | Description |
|---|---|---|
| Media Output | File Stream | The processed audio or video file in the target format |
| Metadata Report | JSON | Technical details including bitrate, codec, duration, and frame rate |
| Scene Analysis | Array | Timestamps and keyframe data for video segments |
| Generation Logs | Text | Status updates for TTS and video generation tasks |
AV Skill Advanced Features
- Advanced scene and keyframe detection for automated video editing.
- Integrated Text-to-Speech (TTS) engine for rapid audio narration generation.
- Support for a wide array of professional codecs and file containers including MKV, MOV, and AAC.
- High-efficiency batch processing for merging multiple files into a single output.
- Seamless integration with other AI agents for multi-step multimedia automation pipelines.
SKILL.md
Loading
Related Openclaw Skills
Xiaohongshu Auto-Interaction Skill
A sophisticated automation tool for Xiaohongshu that intelligently handles content discovery, likes, and favorites while maintaining historical records to avoid duplication.
GTM Strategy Planner
A comprehensive strategic framework for planning product launches, market entries, and repositioning efforts.
Travel Planner CN
An expert AI travel consultant that generates detailed day-by-day itineraries, budget estimates, and essential packing lists tailored for Chinese travelers.
Xiaohongshu (RED) Viral Post Writer
An AI-powered content creation tool for generating high-engagement Xiaohongshu posts with optimized titles, emojis, and hashtags.
tvfetch
A comprehensive market data assistant for fetching historical prices, live streams, and technical analysis from TradingView without requiring an API key.
Xiaohongshu All-in-One Assistant
A comprehensive automation toolkit for Xiaohongshu that manages the entire content lifecycle from AI copywriting to automated image generation and platform publishing.
Featured*
