An automated end-to-end workflow that transforms raw video files into structured, AI-summarized Markdown study notes with email notifications.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-note-maker
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-note-maker 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-note-maker?
video-note-maker is a robust automation tool designed to streamline the academic or professional task of transcribing video content. By leveraging industry-standard tools like ffmpeg and OpenAI's Whisper model, it handles the heavy lifting of audio extraction and speech-to-text conversion. The skill is optimized for Openclaw Skills users who need a seamless transition from raw media to polished documentation without manual intervention.
Beyond simple transcription, this skill integrates advanced AI organization logic. It segments long-form videos into manageable chunks, processes them through high-performance LLMs for summarization, and generates two versions of notes: a comprehensive detailed version and a condensed study guide. This makes it an essential tool for students, researchers, and developers looking to archive technical lectures or meetings efficiently.
video-note-maker Use Cases
- Transcribing long technical lectures (e.g., HCIP/OSPF network training) into readable documentation.
- Converting recorded team meetings or webinars into searchable Markdown notes.
- Automating the creation of study guides from video-based online courses.
- Generating structured summaries for high-volume video archives using Openclaw Skills.
How video-note-maker Works
- The user provides a video file path to the script.
- The system extracts the audio stream and converts it to a compact AAC (.m4a) format.
- Long audio files are segmented into 15-minute chunks to ensure transcription stability.
- The Whisper 'small' model transcribes each segment into text files.
- AI logic (Qwen-3.5-Plus) processes the transcripts to generate a detailed Markdown file and a refined summary version.
- The tool sends a completion notification and the final files via QQ Mail or Feishu Webhook.
video-note-maker Setup
Ensure you have ffmpeg installed and the necessary Python environment variables set for email notifications.
# Install dependencies (Whisper and ffmpeg required)
pip install openai-whisper
# Set up environment variables for email notifications
export QQMAIL_USER="[email protected]"
export QQMAIL_AUTH_CODE="your_auth_code"
export FEISHU_WEBHOOK="your_webhook_url"
# Run the skill
python video_note_maker.py "/path/to/video.mp4"
video-note-maker Data Schema & Taxonomy
The skill maintains a strict directory hierarchy to manage intermediate and final assets:
| Directory | File Type | Description |
|---|---|---|
tmp/ |
.m4a, .txt |
Contains extracted audio, segments, and raw transcript snippets. |
done/ |
.md |
Stores the final Detailed Note and the Study Guide version. |
input/ |
.mp4, .mkv |
Original video source files provided by the user. |
video-note-maker Advanced Features
- Auto-Mode: Use the
--autoflag to bypass user confirmation prompts for head-less automation within Openclaw Skills. - Custom Segmentation: Configure
--segment-durationto adjust audio slicing for better context retention. - Multi-Channel Notification: Supports simultaneous alerts via SMTP (QQ Mail) and Feishu Webhooks.
- Detailed Mode: Toggle between raw transcriptions and AI-enhanced summarized versions.
SKILL.md
Loading
Related Openclaw Skills
Dopost API Skill
A powerful integration for automating social media publishing, scheduling, and media management across multiple platforms via the Dopost REST API.
RSSHub Route Generator
A powerful developer tool that analyzes website structures to automatically generate RSSHub-compliant TypeScript route files.
Choice Brand Encyclopedia
A comprehensive research skill for gathering detailed brand intelligence, product matrix data, and global market insights for the Choice brand.
Cabify Knowledge Card
The Cabify Knowledge Card is an intelligence-gathering skill that provides instant technical and business snapshots of the global ride-sharing platform.
WeShop AI 3D Rendering CLI Skill
A powerful CLI skill that transforms static images into realistic 3D modeling environment screenshots mimicking the Blender viewport.
2D to 3D Image Converter OpenAPI Skill
A high-performance AI tool designed to transform flat 2D graphics into realistic 3D rendered versions via the WeShop OpenAPI.
Featured*
