An AI-powered tool for downloading, transcribing, and generating detailed summaries from Bilibili videos using Google Gemini and Whisper.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install bili-summary
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 bili-summary 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 bili-summary?
The bili-summary skill is a sophisticated automation tool designed to bridge the gap between Bilibili video content and actionable text-based insights. By integrating yt-dlp for media fetching and faster-whisper for speech-to-text processing, it offers a complete pipeline for analyzing B站 content. This is a vital addition to any workflow utilizing Openclaw Skills for research or content consumption.
The skill excels at handling diverse video types, providing a smart fallback mechanism that automatically transcribes audio if official subtitles are unavailable. Once the text is extracted, it utilizes the Google Gemini 2.5 Flash model to produce structured summaries, including chapter breakdowns and key insights, making it easier than ever to digest long-form video content within the Openclaw Skills ecosystem.
bili-summary Use Cases
- Summarizing long Bilibili lectures or tutorials into concise notes.
- Extracting subtitles from B站 videos for translation or archival purposes.
- Transcribing audio from Bilibili videos that lack official closed captions.
- Downloading high-quality audio or video files for offline reference using Openclaw Skills.
How bili-summary Works
- The skill first fetches video metadata including title, duration, and uploader information via yt-dlp.
- It attempts to download official CC subtitles directly from the Bilibili platform.
- If no subtitles are found, the skill downloads the audio stream and utilizes the faster-whisper tiny model to generate a local transcription.
- The resulting text is sent to the Gemini 2.5 Flash API, which returns a comprehensive summary organized by chapters and key takeaways.
bili-summary Setup
To get started with this skill in your Openclaw Skills environment, follow these installation steps:
- Install the necessary Python packages:
pip install yt-dlp faster-whisper
- Secure a Google Gemini API Key from the Google AI Studio.
- Set your environment variable to authorize the AI summarization:
export GEMINI_API_KEY="your-api-key-here"
- Execute a full summary workflow using the following syntax:
uv run scripts/bili-summary.py "VIDEO_URL" --action summary
bili-summary Data Schema & Taxonomy
The skill organizes its output in the workspace temp directory. The following table describes the file structure used by these Openclaw Skills:
| File Name | Purpose |
|---|---|
audio.m4a |
The extracted audio track used for transcription (temporary). |
subtitle.txt |
The raw text transcript or retrieved subtitles. |
summary.txt |
The final structured AI summary content. |
bili-summary Advanced Features
- Intelligent Fallback: Automatically invokes Whisper AI transcription when Bilibili CC subtitles are unavailable.
- Action Granularity: Supports specific operations such as info-only retrieval, subtitle extraction, or full video downloads.
- Gemini 2.5 Flash Integration: Optimized for speed and accuracy, delivering complex summaries in under 10 seconds.
- Flexible Directory Support: Custom output paths can be specified to manage data within your Openclaw Skills workspace.
SKILL.md
Loading
Related Openclaw Skills
Python Agentmail Send & Receive
An AI-friendly Python skill for sending, receiving, and threading emails via the agentmail.to API using structured JSON data.
OpenClaw Shield
A comprehensive security audit engine designed to identify vulnerabilities, secret leaks, and misconfigurations in your OpenClaw setup.
Daily AI News Briefing
An automated news aggregator that scans top tech publications and research papers to deliver a structured daily briefing on the AI industry.
Fathom
A powerful integration for retrieving meeting intelligence, including transcripts and action items, directly from Fathom AI.
IELTS Test Data Extraction Skill
A specialized skill designed to programmatically extract IELTS reading articles and question sets from Cambridge PDF materials into structured JSON format.
peaq-robotics
A core ROS 2 integration for managing decentralized identity, storage, and access control on the peaq network.
Featured*
