Bilibili Render Pdf

Takes a Bilibili video URL and generates a complete LaTeX course note with a compiled PDF. The workflow handles Chinese lecture content end to end: it falls back to Whisper when CC subtitles are missing, prompts you for cookie auth when HD frames are login-gated, detects multi-part videos and asks which segments to process, and extracts key frames at the highest available resolution. The output includes the original video cover on the front page, proper section structure, formulas and diagrams as figures, and a final synthesis chapter. It's explicitly designed to rewrite subtitle dumps into actual teaching flow rather than chronological transcription, which makes the difference between a decent reference and something you'd actually want to read.

skills.sh installs: 375
GitHub stars: 827
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add wdkns/wdkns-skills --skill bilibili-render-pdf --agent claude-code

Installs into .claude/skills of the current project.

Files

Bilibili Render PDF

Use this skill to turn a Bilibili video into a complete, compileable .tex note and a rendered PDF.

This skill extends the youtube-render-pdf workflow with Bilibili-specific adaptations for subtitle scarcity, login-gated high resolution, multi-part (分P) videos, and platform-specific non-teaching content.

Bilibili vs YouTube: Key Differences

Aspect	Handling
Subtitle scarcity	Try CC subtitles first → fall back to Whisper speech-to-text → visual-only mode
Login-gated HD	1080P+ requires cookies; prompt the user to use `yt-dlp --cookies-from-browser chrome`
Multi-part videos	Detect 分P videos and ask the user which parts to process
URL formats	Support `bilibili.com/video/BVxxxxxxx` and `b23.tv` short links
Danmaku	Do not use danmaku as a teaching content source (too noisy); use only CC subtitles or Whisper output