Get Biji logo

Get Biji

Community
suyuan2022
get-biji

Get 笔记(biji.com):把账号里的笔记同步成本地 Markdown 并检索;用 Get 的转写额度把视频、播客、本地音视频转成逐字稿。 触发:用户要同步或查 Get 笔记里的录音和笔记;给了抖音、小红书、B 站、小宇宙链接或本地音视频,要逐字稿。

Overview

Publishersuyuan2022
Repositorysuyuan-skill
Skill nameget-biji
Stars
415
Forks
40
Bundled files
10
LicenseMIT
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.

  • 10 bundled files

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

  • Open source

    Published by suyuan2022 on GitHub. Read the source before you install it.

Installation

Install the Get Biji 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/suyuan2022/suyuan-skill/tree/main/get-biji
  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/suyuan2022/suyuan-skill.git /tmp/suyuan-skill
mkdir -p .claude/skills
cp -r /tmp/suyuan-skill/get-biji .claude/skills/get-biji
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Get Biji 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 Get Biji 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 Get Biji 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.

Get 笔记

两件事,共用一个 biji.com 登录态:

  • 同步:账号里的笔记(录音、链接、文字)存成 <笔记目录> 下按日期分的 Markdown,增量更新
  • 转逐字稿:链接或本地音视频交给 Get 转写,取回文字后删掉 Get 里的临时笔记

下文 <skill-dir> 是本文件所在的目录;<状态目录> 是环境变量 GET_BIJI_HOME 的值,没设就是 ~/.config/get-biji/。登录态、同步记录和 <笔记目录> 的位置都记在 <状态目录>,重装 skill 不受影响。

首次准备

需要 Node.js 18 及以上。

bash
cd <skill-dir> && npm install && npx playwright install chromium

chromium 约 250MB,只用来登录。装好的标志:node -e "require('playwright')" 不报错。按需再装:ffmpeg(含 ffprobe,转本地音视频时用),yt-dlp(下载其他网站的音视频时用)。

登录

没有登录态或登录态过期(约 90 天一次)时,任何脚本都会打开一个 Chrome 窗口,等用户登录 biji.com,最多等 10 分钟:

  1. 先告诉用户:电脑上会弹出浏览器,请在里面登录 Get 账号,登录后窗口会自己关
  2. 命令放后台跑,盯着输出:出现 Login successful 就是登录好了,脚本接着干原来的活
  3. 报 Cannot open a browser 是机器没有图形界面(远程服务器、云端环境):请用户在自己电脑上装好这个 skill 先跑一次,再把那台电脑的 <状态目录> 拷过来

同步

第一次同步先问用户笔记放哪,要绝对路径。录音转写是隐私,提醒他别放进会推到公开仓库的目录。

bash
cd <skill-dir> && OUTPUT_DIR="<笔记目录>" node scripts/sync.js

之后不用再带 OUTPUT_DIR,脚本用记下的目录;想知道是哪个,看 <状态目录>/config.json 的 outputDir。带上新的 OUTPUT_DIR 就是换目录,会把全部笔记重新同步到新目录。

  • TEST_LIMIT=3:只同步最新的 3 条,第一次可以先试,看看格式
  • SINCE_DATE=YYYY-MM-DD:只同步这天及以后的,默认全部

第一次全量同步每条 1 到 2 秒,笔记多就放后台跑。退出码 0、结尾是 Sync Completed,就是全部同步好了。退出码 1 时结尾会列出失败的笔记,直接重跑,只补没拉下来的。

查笔记

先读 references/检索.md:笔记文件长什么样,怎么由粗到细地搜。

搜之前先把新进 Get 的笔记补上,看 <状态目录>/sync-state.json 分两种:

  • 有 fullSyncAt(本地是全的):不带 SINCE_DATE 跑一次同步。它只拉还没拉过的笔记,录音卡隔几天才传上来的录音也补得到,平时几十秒就完。按日期窗口同步会漏掉窗口外晚到的录音,所以这种情况一律完整同步
  • 没有 fullSyncAt(本地只同步过一部分,比如用户只试跑过):完整同步会把所有没拉过的都拉下来,可能要很久,先别跑。问最近的事,用 SINCE_DATE=<一个月前的日期> 补一段再搜;不管问什么,回答时都说明本地不全、搜不到不等于没有,问用户要不要全量同步

每次同步都要把 Get 的笔记列表从头翻一遍,笔记多的账号光这一步就要几十秒到一两分钟。

转逐字稿

bash
cd <skill-dir> && node scripts/link-transcript.js "<链接>" --json
cd <skill-dir> && node scripts/link-transcript.js --file "<本地路径或媒体直链>" --json

链接和路径都加引号,分享链接里的 ?、& 会被 shell 吃掉。

按来源选路,免费的先走:

来源走法额度
抖音、小红书、B 站(认 ?p=N 分 P)、小宇宙链接链接解析不扣
链接解析报错,或其他网站的音视频先下载到本地(比如用 yt-dlp),再 --file按时长扣
本地音视频--file按时长扣
YouTube用别的工具拿字幕:Get 会抓到错误语言的字幕轨—

--file 按音频时长扣每月的转写额度,四舍五入到分钟,同一个文件重复传也照扣;单个文件最长 3 小时、最大 1GB。上传前先看时长:ffprobe -v error -show_entries format=duration -of csv=p=0 "<文件>"(单位秒),告诉用户大约扣几分钟,超过 30 分钟的等他确认。

stdout 只有一行 JSON:

  • title、url:标题和规范化后的链接
  • text:给用户的正文
  • source:get-corrected 是 Get 按提示词出的纠错稿,直接交付;get-raw(链接解析)和 get-upload-raw(--file)是原始识别,专有名词和同音字常错,先纠错再交付。出不出纠错稿由 Get 决定,同一个平台也会变,以这个字段为准
  • raw:原始识别全文;corrected:来源是纠错稿时就是 text,来源是原始识别时是 Get 的智能总结
  • minutes:--file 实际扣的分钟数

逐字稿太长、不适合直接贴在对话里时,问用户存到哪个文件。

纠错原始识别

按段切成约 3000 字的块,每块只改错别字、同音字和品牌型号等专有名词,补全标点;时间戳、分段、说法和内容一律原样保留。corrected 里的智能总结专有名词基本是对的,拿来当参照。一块纠完长度变了 15% 以上,说明被删改了,这块退回原文。逐字稿长的,分块交给更便宜的模型并发去纠。

出问题时

  • 反复要求登录、或者登录相关报错:删掉 <状态目录> 里的 token-cache.json 和 auth-state.json,重新运行登录
  • 同步记录丢了(换了电脑、删了 <状态目录>),但笔记目录还在:带上 OUTPUT_DIR 跑 node scripts/rebuild-state.js,按硬盘上已有的文件重建记录,缺的下次同步补上
  • 同一条笔记出现多个总结文件:node scripts/dedupe.js 按 note_id 去重,留最大的那份,连同它配对的原文文件一起删
  • 转逐字稿时加 --keep,Get 里的临时笔记会留着不删,排查用

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 Get Biji AI skill do?

Get 笔记(biji.com):把账号里的笔记同步成本地 Markdown 并检索;用 Get 的转写额度把视频、播客、本地音视频转成逐字稿。 触发:用户要同步或查 Get 笔记里的录音和笔记;给了抖音、小红书、B 站、小宇宙链接或本地音视频,要逐字稿。

Why use Get Biji on TypingMind?

Because you install it once and use it with any model. Get Biji 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 Get Biji in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/suyuan2022/suyuan-skill/tree/main/get-biji. 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 Get Biji?

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 Get Biji?

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

Is the Get Biji AI skill free?

Yes. It is published on GitHub by suyuan2022 under the MIT license. 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 👇