Bilibili Video Notes logo

Bilibili Video Notes

Community
asdhabdua
bilibili-video-notes

从 B 站教育/讲课视频生成带截图的 DOCX 学习笔记。下载视频+字幕→全覆盖抽帧→OCR去重→AI视觉打分→提取图中内容→融合生成DOCX。

Overview

Publisherasdhabdua
Repositorybilibili-video-notes-skill
Skill namebilibili-video-notes
Stars
52
Forks
7
Bundled files
15
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 15 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by asdhabdua on GitHub. Read the source before you install it.

Installation

Install the Bilibili Video Notes AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/asdhabdua/bilibili-video-notes-skill/tree/main
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/asdhabdua/bilibili-video-notes-skill.git \
  .claude/skills/bilibili-video-notes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bilibili Video Notes in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bilibili Video Notes on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bilibili Video Notes is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bilibili Video Notes

从 B 站教育/讲课视频生成带截图的 DOCX 学习笔记。

工作流程

  1. 下载视频 + AI 字幕
  2. 每 10 秒全覆盖抽帧
  3. OCR + 感知哈希去重
  4. AI 并发视觉打分,人工选出最终 7-12 帧
  5. AI 并发提取最终帧中的文字/公式/表格/概念
  6. 融合字幕 + 图中内容生成 DOCX
  7. 验证 + 清理临时文件

安装

bash
pip install -r scripts/requirements.txt

需要系统安装 ffmpeg。

配置 API:

bash
cp templates/env.example .env
# 填写 VISION_API_KEY / VISION_BASE_URL / VISION_MODEL

配置 B 站 Cookie:

bash
cp bilibili_cookies.txt.example bilibili_cookies.txt
# 填写 SESSDATA

使用方法

当用户提供 B 站视频链接并要求做笔记时,按以下步骤执行:

bash
# 1. 抽帧
python scripts/extract_frames.py <BV号> \
  --page <N> \
  --mode cover \
  --subtitle \
  --workspace ./workspace \
  --frames ./frames/pXX

# 2. 去重
python scripts/smart_select.py ./frames/pXX/fixed \
  --output-dir ./frames/pXX/selected \
  --skip-clustering

# 3. 并发打分
python scripts/score_frames_concurrent.py \
  --frames ./frames/pXX/selected \
  --output ./workspace/vision_scores_pXX.json \
  --workers 16

# 4. 人工选最终帧,复制到 final/
mkdir -p ./frames/pXX/final
cp ./frames/pXX/selected/frame_XXXX.jpg ./frames/pXX/final/

# 5. 提取图中内容
python scripts/score_frames_concurrent.py \\
  --frames ./frames/pXX/final \\
  --output ./workspace/vision_extract_pXX.json \\
  --mode extract \\
  --workers 16

# 6. 生成 DOCX 前,先提取字幕关键因果句
python scripts/extract_key_sentences.py \\
  ./workspace/<BV>_p<N>_subtitles.txt

# 7. 生成 DOCX
cp templates/docx_note_v2.py ./workspace/gen_pXX_v1.py
# 编辑 TITLE/SOURCE/FRAMES/SECTIONS,参考 <BV>_p<N>_subtitles.key.json 覆盖因果句
python ./workspace/gen_pXX_v1.py

# 8. 验证(含字幕关键句覆盖检查)
python scripts/verify_docx.py ./workspace/<output>.docx --subtitle ./workspace/<BV>_p<N>_subtitles.txt

# 9. 清理
rm -f ./workspace/<BV>_p<N>.mp4
rm -f ./workspace/<BV>_p<N>_subtitles.json
rm -f ./workspace/gen_pXX_v1.py


## 笔记写作标准

- 以顶级学者身份,融会贯通字幕和截图
- 追求知识完整性,宁可多写不可遗漏
- 保留所有重要细节、公式、定义、例题、做题技巧
- 解释 WHY,不只是 WHAT
- 不带时间戳
- 截图只补充字幕没讲的考点,不抄非考点内容

## 关键规则

- **抽帧用 `--mode cover`**,不用 scene(讲课视频会漏内容)
- **每个视频必须有独立的 `frames/pXX/` 目录**,禁止多视频共用
- **最终帧放入独立的 `final/` 目录**
- **不要用 Hermes 的 `vision_analyze` 串行调用**,所有视觉分析走 `score_frames_concurrent.py`
- **帧目录必须是纯英文路径**
- **不要用 `**xxx**` 或 `<font color=red>` 等 markdown 语法写 DOCX**,要用 `run.bold` 和 `run.font.color`

## 依赖

```bash
pip install yt-dlp imagehash rapidocr-onnxruntime python-docx Pillow requests python-dotenv

需要 ffmpeg。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bilibili Video Notes AI skill do?

从 B 站教育/讲课视频生成带截图的 DOCX 学习笔记。下载视频+字幕→全覆盖抽帧→OCR去重→AI视觉打分→提取图中内容→融合生成DOCX。

Why use Bilibili Video Notes on TypingMind?

Because you install it once and use it with any model. Bilibili Video Notes is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bilibili Video Notes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/asdhabdua/bilibili-video-notes-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bilibili Video Notes?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bilibili Video Notes?

As many as you like. As long as a model supports skills, you can use Bilibili Video Notes with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bilibili Video Notes AI skill free?

It is published on GitHub by asdhabdua. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇