lark-sheets

Create and edit Lark spreadsheets via CLI, covering cells, formulas, charts, pivot tables, and formatting.

Updated May 28, 2026
One-click install
npx skills add https://github.com/changfengpro/agent-skills --skill lark-sheets-changfengpro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lark-sheets
Source: https://github.com/changfengpro/agent-skills/tree/main/skills/lark-sheets
Command: npx skills add https://github.com/changfengpro/agent-skills --skill lark-sheets-changfengpro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Working with Lark (Feishu) spreadsheets programmatically is error-prone: agents guess wrong command names, write numbers as text, skip read-back verification, and mistranslate Excel formulas. This Skill provides a complete, verified command vocabulary and editing discipline for reliably creating and modifying online spreadsheets through the lark-cli tool. ## Core Features & Use Cases - Full spreadsheet lifecycle: Create workbooks, manage sheets (insert/delete/rename/copy), read and write cells with values, formulas, styles, comments, and embedded images, plus find-and-replace and batch updates. - Data objects and visualization: Build native charts, pivot tables, conditional formats, filters, filter views, sparklines, and floating images as real spreadsheet objects that stay linked to source data. - Formula correctness pipeline: Translate Excel formulas into Lark-executable semantics (ARRAYFORMULA, MAP/LAMBDA, native array functions) and verify zero-error results with the formula-verify self-check. - Use Case: A user asks to build a financial model in a Lark spreadsheet: create the workbook with typed data, write DCF formulas, add a pivot table for segment summary, generate a trend chart, apply conditional formatting, and confirm every formula computes without errors. ## Quick Start Ask the AI to create a new Lark spreadsheet with a sales table, add a pivot table summarizing revenue by region, and verify all formulas compute correctly.

Frequently Asked Questions about lark-sheets

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

FAQPage Schema
How do I create and edit a Lark spreadsheet from the command line?

Use lark-cli sheets shortcuts such as +workbook-create to create a spreadsheet with typed data, +cells-set or +table-put to write values and formulas, and +csv-get to read data back. Every write should be followed by a read-back check to confirm the change actually took effect.

How do I convert Excel formulas to Feishu (Lark) spreadsheet formulas?

Lark does not spill arrays like Excel 365, so range arithmetic needs ARRAYFORMULA, and implicit per-row evaluation needs MAP with LAMBDA. After writing translated formulas, run +formula-verify until it returns status success to confirm zero errors.

Can I create pivot tables and charts in Lark sheets programmatically?

Yes. Use +pivot-create for real pivot table objects and +chart-create for native charts, both of which stay linked to source data. Local scripts or matplotlib images are explicitly disallowed as substitutes because they do not update with the data.

Why did my numbers or dates turn into text when writing to a Lark sheet?

Writing values through +csv-put treats everything as plain text, so amounts, percentages, and dates lose their numeric type. Use +table-put or +workbook-create with dtypes and formats so quantities are stored as real numbers.

What happens when a Lark sheets command is marked high-risk-write?

High-risk commands like +batch-update, +cells-clear, and object deletions require explicit user approval. The workflow is to run with --dry-run first, show the user the planned changes, then re-run with --yes only after consent.