A high-performance workflow for automating video URL processing, metadata extraction, and organized archival across multiple platforms.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-archive-workflow
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 video-archive-workflow 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 Archive Workflow?
The Video Archive Workflow is a specialized skill designed for Openclaw Skills users to manage digital video assets with precision and scale. It automates the entire lifecycle of a video archive task, from parsing URLs on platforms like YouTube, Bilibili, and X/Twitter to extracting clean, deterministic metadata using tools like yt-dlp. The skill ensures that every record is normalized, deduplicated by video ID, and filed into a structured directory system based on uploader names.
By focusing on data integrity, this skill removes the manual labor of tagging, cleaning descriptions, and formatting spreadsheet entries, making it an essential tool for digital librarians and content researchers. It prioritizes lossless archival, converting mp4 sources to mkv containers while preserving original quality and embedding available subtitles automatically.
Video Archive Workflow Use Cases
- Researching and archiving social media trends from platforms like Xiaohongshu and Bilibili.
- Building a private, searchable video library with consistent metadata and folder structures.
- Automating the deduplication of video assets across multiple source URLs to save storage.
- Generating clean, tag-stripped spreadsheet records for content analysis and reporting.
- Managing large-scale video downloads with automated subtitle embedding and format conversion.
How Video Archive Workflow Works
- Parse the input URL to identify the platform, video ID, and content type.
- Perform a deduplication check against existing records using the unique video identifier to prevent redundant tasks.
- Extract raw metadata using yt-dlp JSON dumps to ensure the highest source of truth.
- Clean and normalize the title, description, and tags while stripping unnecessary characters and formatting.
- Resolve the uploader identity to determine the correct folder structure and archive destination.
- Execute download and archival tasks, including lossless container conversion and subtitle embedding where applicable.
- Write the finalized data into a structured sheet following a strict field schema for archival tracking.
Video Archive Workflow Setup
To integrate this skill into your environment, ensure you have the necessary dependencies installed for media processing. This workflow relies on Openclaw Skills architecture and requires yt-dlp and FFmpeg.
# Ensure yt-dlp is installed and updated
pip install -U yt-dlp
# Install FFmpeg for lossless conversion
# On macOS:
brew install ffmpeg
# Configure your archive root directory in your agent settings
export ARCHIVE_ROOT="/path/to/your/video/archive"
Video Archive Workflow Data Schema & Taxonomy
The skill organizes data into a consistent tabular format and filesystem structure. It adheres to a strict field mapping to ensure compatibility with Openclaw Skills data analysis tools.
| Field | Format/Rule | Description |
|---|---|---|
| video_id | Platform Native | The unique identifier used for deduplication. |
| upload_date | YYYY-MM-DD | Implicitly uses Beijing time without labels. |
| tags | Space-separated | Cleaned tags stripped from title and description. |
| resolution | yt-dlp format | Resolution string including units like fps and kbps. |
| folder_name | Sanitized String | Derived from the resolved uploader display name. |
Video Archive Workflow Advanced Features
- Deterministic deduplication logic that prevents redundant downloads based solely on video_id.
- Lossless mkv conversion for mp4 sources to preserve source quality during long-term archival.
- Automated subtitle detection and embedding for multi-lingual content support without manual intervention.
- Platform-specific tag parsing logic, including Bilibili tag-link extraction and X/Twitter tweet text analysis.
- Multi-uploader support with comma-separated metadata and intelligent primary uploader folder routing.
- Intelligent stop-rules that pause the workflow for human intervention during uploader ambiguity or filename conflicts.
SKILL.md
Loading
Related Openclaw Skills
Background Download Skill
A non-blocking file download utility featuring automatic retries, status tracking via Ontology, and channel-specific notifications.
MetaComp VisionX KYT
A comprehensive Web3 security skill for real-time risk assessment of crypto wallets and transactions using multi-vendor cross-verification.
Chill Beijing
A real-time Beijing activity recommender that scrapes top entertainment platforms to suggest after-work and weekend relaxation options.
Context Cache Manager
A sophisticated context management tool for Openclaw Skills that ensures fork-safe state inheritance and prevents token explosion through intelligent compression.
SEO Content Engine
An end-to-end SEO content creation workflow that handles everything from keyword research to fully optimized drafts.
Automation Workflows
A comprehensive framework for solopreneurs to identify, design, and deploy time-saving no-code automation workflows.
Featured*
