lark-sheets

Create, read, write, search, and export Lark spreadsheets via lark-cli commands.

Updated Apr 30, 2026
One-click install
npx skills add https://github.com/yuezhen-huang/my-bytedance-skillhub --skill lark-sheets-yuezhen-huang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lark-sheets
Source: https://github.com/yuezhen-huang/my-bytedance-skillhub/tree/main/lark-sheets
Command: npx skills add https://github.com/yuezhen-huang/my-bytedance-skillhub --skill lark-sheets-yuezhen-huang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires lark-cli, and includes references (resource) components.

What problem does it solve? Working with Lark (Feishu) spreadsheets programmatically requires knowing the correct API resources, token types, and permission scopes. This Skill gives an AI agent precise instructions to create spreadsheets, read and write cell data, append rows, find cell content, and export files through lark-cli without guessing API parameters. ## Core Features & Use Cases - Spreadsheet CRUD Operations: Create spreadsheets with headers and initial data, read ranges, overwrite cells, and append rows using high-level shortcuts like sheets +create, +read, +write, and +append. - In-Sheet Search and Export: Find cells by text or regex within a known spreadsheet, and export to xlsx or csv with async task polling and optional local download. - Token and Wiki Handling: Correctly resolves wiki URLs to real spreadsheet tokens via wiki spaces get_node, avoiding common token misuse errors. - Use Case: A user asks to build a monthly revenue report. The agent creates a new spreadsheet with headers, appends data rows, then exports it as an xlsx file saved locally. ## Quick Start Ask the agent to create a new Lark spreadsheet titled with your report name, write the header row and data rows into it, and export the result as an xlsx file.

Frequently Asked Questions about lark-sheets

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a Lark spreadsheet and write data into it?

Use the lark-cli sheets +create shortcut with a --title, optionally passing --headers as a JSON array and --data as a 2D JSON array. The command returns the spreadsheet_token and URL, and writes the header and data starting at cell A1.

How to read and write cells in a Feishu spreadsheet from the command line?

Use lark-cli sheets +read with a --range like sheetId!A1:D10 to read values, and sheets +write with --values as a 2D JSON array to overwrite a range. Both accept either a spreadsheet URL or a spreadsheet token.

Can I use a wiki URL to access a Lark spreadsheet?

Not directly. A wiki URL token must first be resolved with lark-cli wiki spaces get_node to obtain the real obj_token and confirm obj_type is sheet. The sheets shortcuts also accept wiki URLs and handle this resolution internally.

How do I search for text inside a Lark spreadsheet?

Use lark-cli sheets +find with --sheet-id and --find to locate matching cells, optionally with --ignore-case or --search-by-regex. Note this only searches within one known spreadsheet; to find spreadsheet files by name, use lark-cli docs +search first.

Why does creating a sheet filter fail with Wrong Filter Value?

This error means a filter already exists on the sheet. Delete the existing filter with spreadsheet.sheet.filters delete first, then create the new filter with a range covering all columns you want to filter.

What are the limits when writing or appending rows to a Lark sheet?

The +write and +append shortcuts validate input size before sending: a maximum of 5000 rows and 100 columns per row. Values must be provided as a 2D JSON array, and --dry-run can preview the request without executing it.