feishu-doc

Read, write, and manage Feishu documents including blocks, tables, and images.

1|Updated Jun 9, 2026
One-click install
npx skills add https://github.com/JEROME-PRAKASH-L/openclaw --skill feishu-doc-jerome-prakash-l
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: feishu-doc
Source: https://github.com/JEROME-PRAKASH-L/openclaw/tree/main/extensions/feishu/skills/feishu-doc
Command: npx skills add https://github.com/JEROME-PRAKASH-L/openclaw --skill feishu-doc-jerome-prakash-l

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Working with Feishu (Lark) cloud documents programmatically requires handling many separate API operations for reading, writing, block editing, tables, and media uploads. This Skill consolidates all Feishu document operations into a single tool with a unified action parameter, so you can manage docx content without learning the underlying API surface. ## Core Features & Use Cases - Full Document Operations: Read, create, overwrite, and append markdown content to Feishu docx documents, with automatic image upload from URLs embedded in markdown. - Block-Level Editing: List, inspect, update, and delete individual blocks (headings, paragraphs, code, todos) using the block types reference for precise edits. - Tables and Media: Create native Docx table blocks with values in one step, and upload images or file attachments from URLs or local paths with position control. - Use Case: A user shares a Feishu docx link and asks for a summary table of its contents. Extract the doc_token from the URL, read the document, then create a table block with the summarized rows directly in the document. ## Quick Start Read the Feishu document at this link and append a short summary section at the end.

Frequently Asked Questions about feishu-doc

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

FAQPage Schema
How do I read a Feishu document from a URL?

Extract the doc_token from the URL path after /docx/ (e.g., ABC123def from https://xxx.feishu.cn/docx/ABC123def), then call the feishu_doc tool with action "read" and that token. It returns the title, plain text, and block statistics.

How do I create a table in a Feishu docx document?

Use the create_table_with_values action with row_size, column_size, column_width, and a 2D values array. Markdown tables are not supported by the write action because the Feishu API rejects table creation via documentBlockChildren.create.

Can I write markdown content to a Feishu document?

Yes, the write action replaces the entire document with markdown content, and append adds markdown to the end. Headings, lists, code blocks, quotes, links, and images are supported, but markdown tables are skipped.

Why can't others see the Feishu document I created?

Documents created without owner_open_id are only accessible to the bot app. Always pass the requesting user's open_id (from sender_id metadata) as owner_open_id so they receive full_access permission automatically.

How do I edit a specific paragraph in a Feishu doc?

First call list_blocks to find the target block_id, then use update_block with the new text content. Text-based blocks like paragraphs, headings, and list items are editable; images and tables have restrictions.

What permissions does the Feishu doc tool require?

The Feishu app needs docx:document, docx:document:readonly, docx:document.block:convert, and drive:drive scopes. The feishu_wiki tool also depends on this tool for reading and writing wiki page content.