Lark Markdown logo

Lark Markdown

OrganizationPopular
larksuite
lark-markdown

飞书 Markdown:查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件,或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档,也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。

Overview

Publisherlarksuite
Repositorycli
Skill namelark-markdown
Stars
17.3K
Forks
1.4K
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

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

Installation

Install the Lark Markdown 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.
  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/larksuite/cli.git /tmp/cli
mkdir -p .claude/skills
cp -r /tmp/cli/skills/lark-markdown .claude/skills/lark-markdown
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lark Markdown 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 Lark Markdown 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 Lark Markdown 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.

markdown (v1)

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md,其中包含认证、权限处理

快速决策

  • 身份:Markdown 文件通常属于用户云空间资源,优先使用 --as user。如为自动化场景,或应用已创建并持有目标文件权限,可按场景使用 --as bot。首次以 user 身份访问前执行 lark-cli auth login

  • markdown +create / +overwrite 失败时,先判断是不是身份和权限问题:bot 更常见的是 app scope 或目标目录 ACL,user 更常见的是用户授权或用户 ACL;不要不加判断地来回切身份重试。

  • 用户要上传、创建一个原生 .md 文件,使用 lark-cli markdown +create

  • 用户要比较原生 .md 文件的历史版本差异,或比较远端 Markdown 与本地草稿,使用 lark-cli markdown +diff

  • 用户要读取 Drive 里某个 .md 文件内容,使用 lark-cli markdown +fetch

  • 用户要对 Markdown 文件做局部文本替换 / 正则替换,优先使用 lark-cli markdown +patch

  • 用户要覆盖更新 Drive 里某个 .md 文件内容,使用 lark-cli markdown +overwrite

  • 用户要先拿 Markdown 文件的历史版本号,再做比较/下载/回滚,先用 lark-drivelark-cli drive +version-history

  • 用户要把本地 Markdown 导入成在线新版文档(docx),不要用本 skill,改用 lark-drivelark-cli drive +import --type docx

  • 用户要对 Markdown 文件做rename / move / delete / 搜索 / 权限 / 评论等云空间(云盘/云存储)操作,不要留在本 skill,切到 lark-drive

  • markdown +create / +overwrite 命中 missing scopepermission deniednot foundquota_exceededversion limit 时,默认停止重试并按报错 hint 处理;只有 rate_limitserver_error 或临时网络错误才做有限退避重试。

  • markdown +create 的目标参数不要猜:Drive 文件夹用 --folder-token,Wiki 节点用 --wiki-token。如果用户给的是 URL,可以直接传完整 URL;CLI 会归一成 token。不要把 doc/sheet/wiki URL 放进 --folder-token 试错。

核心边界

  • 本 skill 处理的是 Drive 中作为普通文件存储的 Markdown,不是 docx 文档
  • --name 和本地 --file 文件名都必须显式带 .md 后缀;不满足时 shortcut 会直接报错
  • --content 支持:
    • 直接传字符串
    • @file 从本地文件读取内容
    • - 从 stdin 读取内容
  • markdown +patch 的内部语义是:先完整下载 Markdown,再本地替换,再整文件覆盖上传
  • markdown +patch 不是服务端原子 patch;它是 CLI 侧编排出来的局部更新能力
  • markdown +patch 当前只支持单组 --pattern / --content
  • markdown +patch 替换后的最终内容不能为空;CLI 会拒绝上传空文件,因为 Drive 不支持零字节 Markdown,且空文件通常是误操作
  • --file 只接受本地 .md 文件路径

正则替换时要特别注意 --pattern 的转义:

bash
# BAD: 未转义正则特殊字符,可能匹配到错误位置
lark-cli markdown +patch --file-token boxcnxxxx --regex --pattern "version (1.0)" --content "version (2.0)"

# GOOD: 显式转义括号和点号
lark-cli markdown +patch --file-token boxcnxxxx --regex --pattern "version \\(1\\.0\\)" --content "version (2.0)"

Shortcuts(推荐优先使用)

Shortcut 是对常用操作的高级封装(lark-cli markdown +<verb> [flags])。有 Shortcut 的操作优先使用。

Shortcut说明
+createCreate a Markdown file in Drive
+diffCompare two remote Markdown versions, or compare remote Markdown against a local file
+fetchFetch a Markdown file from Drive
+patchPatch a Markdown file in Drive via fetch-local-replace-overwrite
+overwriteOverwrite an existing Markdown file in Drive

参考

  • lark-shared — 认证和全局参数
  • lark-drive — Drive 文件管理、导入 docx、move/delete/search 等

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 Lark Markdown AI skill do?

飞书 Markdown:查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件,或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档,也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。

Why use Lark Markdown on TypingMind?

Because you install it once and use it with any model. Lark Markdown 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 Lark Markdown in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/larksuite/cli/tree/main/skills/lark-markdown. 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 Lark Markdown?

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 Lark Markdown?

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

Is the Lark Markdown AI skill free?

Yes. It is published on GitHub by larksuite 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 👇