An automated workflow engine that downloads, transcribes, and analyzes Douyin videos and notes into structured knowledge.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install douyin-orchestrator
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 douyin-orchestrator 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 Douyin Orchestrator?
Douyin Orchestrator is a comprehensive workflow automation tool designed to bridge the gap between short-form video content and structured data. By integrating specialized modules within Openclaw Skills, it manages the entire lifecycle of content processing—from the initial fetch to the final analysis. It effectively coordinates douyin-fetcher for media acquisition, douyin-transcriber for speech-to-text conversion, and douyin-analyzer for semantic summarization, providing a seamless experience for power users and researchers.
This skill is built to be highly versatile, capable of handling standard video URLs, image-text notes, and even pre-existing local media files. It ensures that every piece of information is captured, transcribed accurately using Whisper ASR, and indexed properly within your local knowledge base. This orchestrator is an essential component for anyone looking to build a searchable archive of Douyin content using Openclaw Skills.
Douyin Orchestrator Use Cases
- Automatically transcribing viral Douyin videos for content analysis and archiving.
- Extracting text and insights from image-based Douyin notes via browser snapshots.
- Batch processing local video files to generate summaries and key learning points.
- Creating a searchable personal knowledge base from social media video resources.
- Streamlining the download-only process for high-quality video archiving without transcription.
How Douyin Orchestrator Works
- The orchestrator identifies the input type, such as a video link, a note URL, or a local file path.
- For links, it triggers douyin-fetcher to parse the URL and download the necessary media streams.
- The douyin-transcriber module extracts the audio and sends it to a Whisper ASR service for high-fidelity transcription.
- The douyin-analyzer processes the raw text to perform semantic segmentation, error correction, and key point extraction.
- The workflow concludes by saving the markdown transcript and media file while automatically updating the repository indexes.
Douyin Orchestrator Setup
To get started with this orchestrator in Openclaw Skills, ensure your environment meets the following requirements:
# Install FFmpeg for video processing
winget install Gyan.FFmpeg
# Ensure the Whisper ASR Docker container is running
docker start whisper-asr
# Verify system dependencies
curl --version
ffmpeg -version
docker ps --filter "name=whisper-asr"
Additionally, ensure your browser is configured with an active profile named openclaw to allow the fetcher to bypass automated detection during the scraping process.
Douyin Orchestrator Data Schema & Taxonomy
The skill organizes processed data into a structured directory for easy navigation:
| File Category | Path Location | Description |
|---|---|---|
| Transcripts | /knowledge/transcripts/ |
Markdown files containing titles, links, and full text. |
| Media Files | /videos/ |
The raw .mp4 video files downloaded from the source. |
| Transcript Index | /transcripts/data_structure.md |
A local index tracking all processed transcripts. |
| Master Index | /knowledge/data_structure.md |
The primary metadata repository for Openclaw Skills data. |
Douyin Orchestrator Advanced Features
- Intelligent input detection that adjusts the workflow based on whether the source is a video, note, or file.
- Support for DASH stream processing, allowing for faster transcription by targeting audio streams directly.
- Built-in error handling for common link resolution issues, such as 403 Forbidden errors or expired URLs.
- Seamless integration with Docker-based Whisper services for localized, private speech-to-text processing.
- Automated metadata indexing that keeps your Openclaw Skills library organized and searchable without manual intervention.
SKILL.md
Loading
Related Openclaw Skills
Ocr Pro
A high-performance OCR and document extraction tool utilizing Vision Language Models for complex layouts.
PDF Analysis
A powerful document intelligence skill for extracting structured content, tables, and formulas from PDFs using MinerU.
Paper Parser
An advanced academic document processor that converts research PDFs into structured Markdown with LaTeX formulas and preserved table layouts.
OpenClaw Bash Safety Validator Primer
A comprehensive security guide and technical primer designed to harden Openclaw Skills against autonomous shell execution risks and injection attacks.
Douyin Content Analyzer
An AI-driven content analysis module that transforms raw Whisper transcriptions into structured, professional reports with key point extraction.
HTML to Text
A powerful utility that converts complex HTML and web pages into clean, readable text or structured JSON using the MinerU engine.
Featured*
