skills.rest
chhpt
chhptCOMMUNITY
Explore all skills by this author →
GitHub

feishu-doc-reader

Extract content and block structure from Feishu documents via the Feishu Open API.

Updated Aug 23, 2026
Search Tags:#api integration#blocks#feishu#lark#document extraction#content parsing
One-click install
npx skills add https://github.com/chhpt/skills --skill feishu-doc-reader-chhpt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: feishu-doc-reader
Source: https://github.com/chhpt/skills/tree/main/skills/feishu-doc-reader
Command: npx skills add https://github.com/chhpt/skills --skill feishu-doc-reader-chhpt

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Reading Feishu (Lark) documents programmatically requires handling authentication tokens, document types, and complex block structures. This Skill wraps the official Feishu Open API so you can pull document content, metadata, and full block hierarchies with simple commands instead of writing API integration code yourself. ## Core Features & Use Cases - Document Content Extraction: Read Docx, legacy Doc, Sheet, and Slide documents using their document tokens, with structured JSON output. - Full Block Access: Retrieve complete block hierarchies including text, headings, tables, images, code blocks, and lists with parent-child relationships. - Robust Error Handling: Built-in token validation, permission checks, retry logic, and clear diagnostics for common Feishu API error codes. - Use Case: You need to migrate a knowledge base of Feishu docs into another system. Run the blocks script against each document token to export the full structured content as JSON for downstream transformation. ## Quick Start Set up your Feishu app credentials in the config file, then ask the assistant to read a Feishu document by providing its document token from the URL.

Frequently Asked Questions about feishu-doc-reader

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

FAQPage Schema
How do I read a Feishu document programmatically?▼

Use the Feishu Open API with a tenant access token obtained from your app credentials. This Skill's read_doc.sh script handles authentication and content retrieval when you pass the document token found in the document URL.

How to extract document blocks from Feishu docs?▼

Call the Feishu blocks API endpoint with the document token to get the full block hierarchy. The get_blocks.sh script returns all blocks including text, tables, images, and headings, with an option to include child blocks.

What Feishu API permissions are needed to read documents?▼

You need docx:document:readonly for new documents, doc:document:readonly for legacy docs, and sheets:spreadsheet:readonly for spreadsheets. The app must also be published and the document shared with or accessible to the app.

Why does Feishu API return 403 Forbidden when reading a document?▼

A 403 error means the app lacks permission to access the document. Verify the app has the required read scopes, is published, and that the document is shared with the app or in an accessible space.

Can I extract content from Feishu slides and legacy docs?▼

Legacy Doc documents support basic metadata and limited content extraction. Slides return basic metadata only, as full content extraction requires additional permissions beyond the standard read scopes.

Related Skills

Explore More Software Engineering Skills→
wulaosijiwulaosiji
28

feishu-pdf-downloader

Download files from Feishu cloud drive using a file token.

Community
Intermediate
papachongpapachong
2

brave-search

Search Brave Search headlessly and extract page content as markdown.

Community
Intermediate
chiragborse1chiragborse1

feishu-wiki

Extract Feishu wiki tokens and manage node metadata.

Community
Intermediate
CalWadeCalWade

feishu-doc-create-and-grant

Create Feishu cloud documents, write content blocks, and grant permissions via Open IDs.

Community
Advanced