Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
larksuite avatar

Lark Sheets

larksuite/cli

  • 387k installs
  • 15.9k repo stars
  • Updated July 28, 2026
  • larksuite/cli

lark-sheets is a CLI skill for creating and operating Feishu spreadsheets.

About

lark-sheets enables agents to create and operate Feishu spreadsheets via CLI. It supports creating workbooks, managing sheets and row/column structure, reading and writing cells with formulas and styles, and building visualizations like charts and pivot tables.

  • Create and manage Feishu spreadsheets with full row/column operations
  • Read and write cells with values, formulas, styles, and comments
  • Build charts, pivot tables, filters, and conditional formatting

Lark Sheets by the numbers

  • 386,895 all-time installs (skills.sh)
  • +13,292 installs in the week ending Jul 28, 2026 (Skillselion tracking)
  • Ranked #3 of 923 Databases skills by installs in the Skillselion catalog
  • Security screen: HIGH risk (skills.sh audit)
  • Data as of Jul 28, 2026 (Skillselion catalog sync)
At a glance

lark-sheets capabilities & compatibility

Use cases
data analysis
Runs
Remote server
Pricing
Bring your own API key
npx skills add https://github.com/larksuite/cli --skill lark-sheets

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs387k
repo stars★ 15.9k
Security audit2 / 3 scanners passed
Last updatedJuly 28, 2026
Repositorylarksuite/cli ↗

How do you read and write Lark spreadsheets from CLI?

Create, read, and edit Feishu spreadsheets with formulas, styles, charts, and pivot tables.

Who is it for?

Agents and automation needing to create, read, or edit data in Feishu spreadsheets with formulas and visualizations.

Skip if: Developers searching cloud space by filename or keyword should use lark-doc docs +search instead of lark-sheets object commands.

When should I use this skill?

User asks to create, update, export, or batch-read Feishu/Lark spreadsheet cells via lark-cli or mentions 电子表格 operations.

What you get

Updated worksheets, appended row data, exported spreadsheet files, and structured cell reads from known spreadsheet tokens.

  • updated worksheets
  • exported spreadsheet files
  • cell and row read results

By the numbers

  • Supports import of xlsx, xls, csv files as Feishu spreadsheets

Files

SKILL.mdMarkdownGitHub ↗

sheets (v3)

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

快速决策

  • 按标题或关键词找云空间里的表格文件，先用 lark-cli docs +search。
  • docs +search 会直接返回 SHEET 结果，不要把它误解成只能搜文档 / Wiki。
  • 已知 spreadsheet URL / token 后，再进入 sheets +info、sheets +read、sheets +find 等对象内部操作。

核心概念

文档类型与 Token

飞书开放平台中，不同类型的文档有不同的 URL 格式和 Token 处理方式。在进行文档操作（如添加评论、下载文件等）时，必须先获取正确的 file_token。

文档 URL 格式与 Token 处理

URL 格式示例Token 类型处理方式
/docx/https://example.larksuite.com/docx/doxcnxxxxxxxxxfile_tokenURL 路径中的 token 直接作为 file_token 使用
/doc/https://example.larksuite.com/doc/doccnxxxxxxxxxfile_tokenURL 路径中的 token 直接作为 file_token 使用
/wiki/https://example.larksuite.com/wiki/wikcnxxxxxxxxxwiki_token⚠️ 不能直接使用，需要先查询获取真实的 obj_token
/sheets/https://example.larksuite.com/sheets/shtcnxxxxxxxxxfile_tokenURL 路径中的 token 直接作为 file_token 使用
/drive/folder/https://example.larksuite.com/drive/folder/fldcnxxxxfolder_tokenURL 路径中的 token 作为文件夹 token 使用

Wiki 链接特殊处理（关键！）

知识库链接（/wiki/TOKEN）背后可能是云文档、电子表格、多维表格等不同类型的文档。不能直接假设 URL 中的 token 就是 file_token，必须先查询实际类型和真实 token。

处理流程

1. 使用 `wiki.spaces.get_node` 查询节点信息

   lark-cli wiki spaces get_node --params '{"token":"wiki_token"}'

2. 从返回结果中提取关键信息

  • node.obj_type：文档类型（docx/doc/sheet/bitable/slides/file/mindnote）
  • node.obj_token：真实的文档 token（用于后续操作）
  • node.title：文档标题

3. 根据 `obj_type` 使用对应的 API

obj_type说明使用的 API
docx新版云文档drive file.comments.*、docx.*
doc旧版云文档drive file.comments.*
sheet电子表格sheets.*
bitable多维表格bitable.*
slides幻灯片drive.*
file文件drive.*
mindnote思维导图drive.*
查询示例
# 查询 wiki 节点
lark-cli wiki spaces get_node --params '{"token":"wiki_token"}'

返回结果示例：

{
   "node": {
      "obj_type": "docx",
      "obj_token": "xxxx",
      "title": "标题",
      "node_type": "origin",
      "space_id": "12345678910"
   }
}

资源关系

Wiki Space (知识空间)
└── Wiki Node (知识库节点)
    ├── obj_type: docx (新版文档)
    │   └── obj_token (真实文档 token)
    ├── obj_type: doc (旧版文档)
    │   └── obj_token (真实文档 token)
    ├── obj_type: sheet (电子表格)
    │   └── obj_token (真实文档 token)
    ├── obj_type: bitable (多维表格)
    │   └── obj_token (真实文档 token)
    └── obj_type: file/slides/mindnote
        └── obj_token (真实文档 token)

Drive Folder (云空间文件夹)
└── File (文件/文档)
    └── file_token (直接使用)

操作流程（重要）：

1. create — 创建筛选

  • 用于首次创建筛选
  • ⚠️ range 必须覆盖所有需要筛选的列（如 B1:E200）
  • 如果已有筛选存在，再用 create 会覆盖整个筛选

2. update — 更新筛选

  • 用于在已有筛选上添加/更新指定列的条件
  • 只需指定 col 和 condition，不需要 range

3. delete — 删除筛选

4. get — 获取筛选状态

多列筛选示例：

创建媒体名称(B列)和情感分析(E列)的双重筛选：

# 1. 删除现有筛选（如有）
lark-cli sheets spreadsheet.sheet.filters delete \
  --params '{"spreadsheet_token":"<spreadsheet_token>","sheet_id":"<sheet_id>"}'

# 2. 创建第一个筛选，range 覆盖所有要筛选的列
lark-cli sheets spreadsheet.sheet.filters create \
  --params '{"spreadsheet_token":"<spreadsheet_token>","sheet_id":"<sheet_id>"}' \
  --data '{"col":"B","condition":{"expected":["xx"],"filter_type":"multiValue"},"range":"<sheet_id>!B1:E200"}'

# 3. 添加第二个筛选条件
lark-cli sheets spreadsheet.sheet.filters update \
  --params '{"spreadsheet_token":"<spreadsheet_token>","sheet_id":"<sheet_id>"}' \
  --data '{"col":"E","condition":{"expected":["xx"],"filter_type":"multiValue"}}'

常见错误：

  • Wrong Filter Value：筛选已存在，需要先 delete 再 create
  • Excess Limit：update 时重复添加同一列条件

单元格数据类型

接受二维数组的 shortcut（+write/+append 的 --values、+create 的 --data）中，每个单元格值支持以下类型。公式、带文本链接、@人、@文档、下拉列表必须使用对象格式，直接传字符串会被当作纯文本存储。

类型写入格式示例
字符串"文本""hello"
数字数字123、3.14
日期数字（自 1899-12-30 起的天数，需先设单元格日期格式）42101
链接（纯 URL）"URL 字符串""https://example.com"
链接（带文本）{"type":"url","text":"显示文本","link":"URL"}{"type":"url","text":"飞书","link":"https://www.feishu.cn"}
邮箱"邮箱字符串""user@example.com"
公式{"type":"formula","text":"=公式"}{"type":"formula","text":"=SUM(A1:A10)"}
@人`{"type":"mention","text":"标识","textType":"email\openId\
@文档{"type":"mention","textType":"fileToken","text":"token","objType":"类型"}{"type":"mention","textType":"fileToken","text":"shtXXX","objType":"sheet"}
下拉列表{"type":"multipleValue","values":[值1,值2]}{"type":"multipleValue","values":["选项A","选项B"]}

写入公式示例：

# ✅ 正确：使用对象格式
lark-cli sheets +write --url "URL" --sheet-id "sheetId" --range "C6" \
  --values '[[{"type":"formula","text":"=SUM(C2:C5)"}]]'

# ❌ 错误：直接传字符串，会被存为纯文本
lark-cli sheets +write --url "URL" --sheet-id "sheetId" --range "C6" \
  --values '[["=SUM(C2:C5)"]]'
公式语法参考：涉及 ARRAYFORMULA、原生数组函数、MAP/LAMBDA、日期差、Excel 公式改写等飞书特有规则时，先阅读 `references/lark-sheets-formula.md`。

限制：

  • 公式支持 IMPORTRANGE 跨表引用（最多 5 层嵌套、每个工作表最多 100 个引用）
  • @人仅支持同租户用户，单次最多 50 人
  • 下拉列表需先配置下拉选项，否则 multipleValue 写入会变成纯文本。配置方法见 `references/lark-sheets-dropdown.md#set-dropdown`。值中的字符串不能包含逗号

Shortcuts（推荐优先使用）

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

Spreadsheet Management

对应参考文档：spreadsheet-management

Shortcut说明
`+create`Create a spreadsheet (optional header row and initial data)
`+info`View spreadsheet and sheet information
`+export`Export a spreadsheet (async task polling + optional download)

Sheet Management

对应参考文档：sheet-management

Shortcut说明
`+create-sheet`Create a sheet in an existing spreadsheet
`+copy-sheet`Copy a sheet within a spreadsheet
`+delete-sheet`Delete a sheet from a spreadsheet
`+update-sheet`Update sheet title, position, visibility, freeze, or protection

Cell Data

对应参考文档：cell-data

Shortcut说明
`+read`Read spreadsheet cell values
`+write`Write to spreadsheet cells (overwrite mode)
`+append`Append rows to a spreadsheet
`+find`Find cells in a spreadsheet
`+replace`Find and replace cell values

Cell Style And Merge

对应参考文档：cell-style-and-merge

Shortcut说明
`+set-style`Set cell style for a range
`+batch-set-style`Batch set cell styles for multiple ranges
`+merge-cells`Merge cells in a spreadsheet
`+unmerge-cells`Unmerge (split) cells in a spreadsheet

Cell Images

对应参考文档：cell-images

Shortcut说明
`+write-image`Write an image into a spreadsheet cell

Row Column Management

对应参考文档：row-column-management

Shortcut说明
`+add-dimension`Add rows or columns at the end of a sheet
`+insert-dimension`Insert rows or columns at a specified position
`+update-dimension`Update row or column properties (visibility, size)
`+move-dimension`Move rows or columns to a new position
`+delete-dimension`Delete rows or columns

Filter Views

对应参考文档：filter-views

Shortcut说明
`+create-filter-view`Create a filter view
`+update-filter-view`Update a filter view
`+list-filter-views`List all filter views in a sheet
`+get-filter-view`Get a filter view by ID
`+delete-filter-view`Delete a filter view
`+create-filter-view-condition`Create a filter condition on a filter view
`+update-filter-view-condition`Update a filter condition
`+list-filter-view-conditions`List all filter conditions of a filter view
`+get-filter-view-condition`Get a filter condition by column
`+delete-filter-view-condition`Delete a filter condition

Dropdown

对应参考文档：dropdown

Shortcut说明
`+set-dropdown`设置下拉列表（multipleValue 写入的前置步骤）
`+update-dropdown`更新下拉列表选项
`+get-dropdown`查询下拉列表配置
`+delete-dropdown`删除下拉列表

Float Images

对应参考文档：float-images

Shortcut说明
`+media-upload`上传本地图片素材，返回 file_token（供 +create-float-image 使用；>20MB 自动分片）
`+create-float-image`创建浮动图片
`+update-float-image`更新浮动图片属性
`+get-float-image`获取浮动图片
`+list-float-images`查询所有浮动图片
`+delete-float-image`删除浮动图片

Formula

对应参考文档：formula

浮动图片相关的读接口只返回元数据（含 float_image_token），不包含图片字节。要读取图片内容，用 token 调 lark-cli docs +media-preview --token "<float_image_token>" --output ./image.png。

API Resources

lark-cli schema sheets.<resource>.<method>   # 调用 API 前必须先查看参数结构
lark-cli sheets <resource> <method> [flags] # 调用 API
重要：使用原生 API 时，必须先运行 schema 查看 --data / --params 参数结构，不要猜测字段格式。

spreadsheets

  • create — 创建电子表格
  • get — 获取电子表格信息
  • patch — 修改电子表格属性

spreadsheet.sheet.filters

  • create — 创建筛选
  • delete — 删除筛选
  • get — 获取筛选
  • update — 更新筛选

spreadsheet.sheets

  • find — 查找单元格

spreadsheet.sheet.float_images

  • create — 创建浮动图片
  • patch — 更新浮动图片
  • get — 获取浮动图片
  • query — 查询所有浮动图片
  • delete — 删除浮动图片

权限表

方法所需 scope
spreadsheets.createsheets:spreadsheet:create
spreadsheets.getsheets:spreadsheet.meta:read
spreadsheets.patchsheets:spreadsheet.meta:write_only
spreadsheet.sheet.filters.createsheets:spreadsheet:write_only
spreadsheet.sheet.filters.deletesheets:spreadsheet:write_only
spreadsheet.sheet.filters.getsheets:spreadsheet:read
spreadsheet.sheet.filters.updatesheets:spreadsheet:write_only
spreadsheet.sheets.findsheets:spreadsheet:read
spreadsheet.sheet.float_images.createsheets:spreadsheet:write_only
spreadsheet.sheet.float_images.patchsheets:spreadsheet:write_only
spreadsheet.sheet.float_images.getsheets:spreadsheet:read
spreadsheet.sheet.float_images.querysheets:spreadsheet:read
spreadsheet.sheet.float_images.deletesheets:spreadsheet:write_only

Related skills

microsoftAzure KustoRun fast KQL queries against Azure Data Explorer for log analytics, telemetry, and time-series data.467k1.3kopen.feishu.cnLark BaseLet their coding agents read from, write to, and query structured data stored in Lark Base (Feishu) spreadsheets and databases.452ksupabaseSupabase Postgres Best PracticesAutomatically apply Supabase Postgres performance rules during query writing, schema design, and database optimization.300k2.4kfirebaseFirebase Data ConnectGenerate complete, production-ready Firebase Data Connect GraphQL schemas and queries for complex relational data models.107k386firebaseFirebase FirestoreAdd Cloud Firestore read/write capabilities to an Android Kotlin app using the official Firebase SDK.72.1k386neondatabaseNeon PostgresGet accurate, up-to-date guidance on Neon Serverless Postgres setup, connection strings, branching, autoscaling, connection pooling, Neon Auth, and SDK usage.54.1k81

How it compares

Pick lark-sheets for spreadsheet cell CRUD and export; use lark-doc when the first step is locating files in cloud space.

FAQ

How does lark-sheets find a spreadsheet by name?

lark-sheets does not search cloud space by title. Use lark-cli docs +search first to locate SHEET resources, then pass the returned spreadsheet token to sheets +info, +read, or +export commands.

What does lark-sheets require before running commands?

lark-sheets requires the lark-cli binary installed and authentication configured per lark-shared SKILL.md. Agents should read lark-shared first for credential and permission handling before any sheets v3 operation.

Is Lark Sheets safe to install?

skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

Databasesdatabasesanalytics
Browse by category
AI & AgentsFrontend & DesignBackend & DataDev ToolsAutomationTesting & ReviewSecurityMonitoring & CloudDocs & Planning
Design & frontend
Design systemsAnimation & motionAccessibility (a11y)CSS & TailwindUI designUXDesign to codeshadcn/uiLanding pagesBest design skills
Most searched skills
find-skillscavemanfrontend-designbrainstormingsystematic-debuggingstop-slopemil-design-engui-ux-pro-maxkarpathy-guidelinesweb-design-guidelinesreact-best-practicesgrill-meimprovemicrosoft-foundryagent-browser
Browse all listings
All agent skillsAll MCP serversAll marketplacesAll plugins

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.