Bilibili

A collection of agent skills. Mostly vibe coded.

Install

npx -y skills add whtsky/skills --skill bilibili

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Extract and transcribe Bilibili (B站) video content via subtitles or Groq Whisper audio transcription for summarization and analysis.

SKILL.md

1.9 KB, 531 tokens by cl100k_base, as published. Nobody here has run it

Bilibili 视频内容获取

获取B站视频的文字内容，用于理解和总结视频。

使用方法

# 获取视频内容（先尝试字幕，失败则音频转写）
bash scripts/bilibili.sh "https://www.bilibili.com/video/BV1xx..."

# 只获取视频信息（标题、UP主、时长等）
bash scripts/bilibili.sh "BV1xx..." --info-only

# 只尝试字幕（不fallback到音频转写）
bash scripts/bilibili.sh "BV1xx..." --subtitle-only

支持的输入格式：

完整链接：https://www.bilibili.com/video/BVxxx
BV号：BV1xx411c7mD
短链接：https://b23.tv/xxx

工作流程

通过 API 获取视频信息（标题、UP主、时长）
尝试获取 CC 字幕或 AI 字幕（优先 CC）
如果字幕不可用，用 yt-dlp 下载音频 + groq-whisper 转写

配置

Set the following environment variables:

export BILIBILI_SESSDATA="your-bilibili-sessdata"
export GROQ_API_KEY="your-groq-api-key"  
export GROQ_WHISPER_SCRIPT="/path/to/groq-whisper/transcribe.sh"

BILIBILI_SESSDATA: B站会话cookie，用于访问字幕和下载音频
GROQ_API_KEY: Groq API密钥，用于音频转写（音频fallback需要）
GROQ_WHISPER_SCRIPT: groq-whisper转写脚本的绝对路径

输出格式

# 视频标题
UP主: xxx | 时长: x分x秒
---

（字幕文本或转写文本）

限制

没有 BILIBILI_SESSDATA 时：字幕大概率获取不到，音频下载也会被拒绝
Cookie 有效期约几个月，过期需要更新
番剧可能有地域限制

What ships with it: 1 file

5.9 KB alongside SKILL.md, 1 of them executable

scripts/

bilibili.shruns5.9 KB

Gives 0 of the 12 instructions most video audio skills give in 531 tokens

Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07

Read individual rule files for detailed explanationsin 21 of 622, across 10 files
Render final videoin 13 of 622, across 6 files
Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
Use this skill when dealing with Remotion codein 11 of 622, across 4 files
Save generated audio to a WAV filein 11 of 622, across 4 files
Handle conversion errors gracefullyin 10 of 622, across 6 files
Add captions to videos alwaysin 10 of 622, across 4 files
Generate music from text descriptions using MusicGenin 9 of 622, across 2 files
Do not skip pipeline layersin 9 of 622, across 3 files
Do not make one tool do everythingin 9 of 622, across 3 files
Use Azure Document Intelligence for complex PDFsin 9 of 622, across 4 files
Never ask the user to paste their full API keyin 9 of 622, across 3 files

Said here and by no other author read

run the bilibili script with the video url
attempt subtitle retrieval before audio transcription
prefer cc subtitles over ai subtitles
download audio with yt-dlp if subtitles fail
transcribe audio with groq whisper if subtitles fail
set bilibili_sessdata environment variable

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.