---
title: "feishu-doc by m1heng · skilld"
canonical_url: "https://skilld.dev/gh/m1heng/clawdbot-feishu"
meta:
description: "Reads, writes, and appends Feishu document content via token-based API; also manages document and block-level comments. Targets the Feishu cloud docs platform and… From m1heng/clawdbot-feishu."
"og:description": "Reads, writes, and appends Feishu document content via token-based API; also manages document and block-level comments. Targets the Feishu cloud docs platform and… From m1heng/clawdbot-feishu."
"og:title": "feishu-doc by m1heng"
"twitter:description": "Reads, writes, and appends Feishu document content via token-based API; also manages document and block-level comments. Targets the Feishu cloud docs platform and… From m1heng/clawdbot-feishu."
"twitter:title": "feishu-doc by m1heng"
---
`
[All skills](https://skilld.dev/skills)
[](https://skilld.dev/gh/m1heng)
# **/feishu-doc**
[@5f4418c](https://github.com/m1heng/clawdbot-feishu/commit/5f4418ce8f28f89d2d796a538ba104a943f0bbf2 "Your agent reads SKILL.md at commit 5f4418c")
by [m1heng](https://skilld.dev/gh/m1heng)· [m1heng](https://skilld.dev/gh/m1heng)/ [clawdbot-feishu](https://skilld.dev/gh/m1heng/clawdbot-feishu)·4.2k stars
438
Feishu document read/write operations + comment management. Activate when user mentions Feishu docs, cloud docs, docx links, or document comments.
- 2 files
- 7.5 KB
- Updated 7 months ago
- [GitHub](https://github.com/m1heng/clawdbot-feishu/blob/5f4418ce8f28f89d2d796a538ba104a943f0bbf2/skills/feishu-doc/SKILL.md "View SKILL.md on GitHub")
- [1 warning](#third-party-checks "Third-party checks: 1 warning · 5 checks · Risk SAFE")
## SKILL.md
4 KB
**≈40** tokens always: the name and description. **≈985** when used: this file. **≈898** more on demand in 1 file.
## Feishu Document Tool
Single tool `feishu_doc` with action parameter for all document operations including comment management.
### Token Extraction
From URL `https://xxx.feishu.cn/docx/ABC123def` → `doc_token` = `ABC123def` From URL `https://xxx.feishu.cn/docs/doccn123c` → `doc_token` = `doccn123c`
### Actions
#### Read Document
```
{ "action": "read", "doc_token": "ABC123def" }
```
Returns: title, plain text content, block statistics. Check `hint` field - if present, structured content (tables, images) exists that requires `list_blocks`.
#### Write Document (Replace All)
```
{ "action": "write", "doc_token": "ABC123def", "content": "# Title\n\nMarkdown content..." }
```
Replaces entire document with markdown content. Supports: headings, lists, code blocks, quotes, links, images (`` auto-uploaded), bold/italic/strikethrough.
**Limitation:** Markdown tables are NOT supported.
#### Create + Write (Atomic, Recommended)
```
{
"action": "create_and_write",
"title": "New Document",
"content": "# Title\n\nMarkdown content..."
}
```
With folder:
```
{
"action": "create_and_write",
"title": "New Document",
"content": "# Title\n\nMarkdown content...",
"folder_token": "fldcnXXX"
}
```
Creates the document and writes content in one call. Prefer this over separate `create` + `write`.
#### Append Content
```
{ "action": "append", "doc_token": "ABC123def", "content": "Additional content" }
```
Appends markdown to end of document.
#### Create Document
```
{ "action": "create", "title": "New Document" }
```
With folder:
```
{ "action": "create", "title": "New Document", "folder_token": "fldcnXXX" }
```
Creates an empty document (title only).
#### List Blocks
```
{ "action": "list_blocks", "doc_token": "ABC123def" }
```
Returns full block data including tables, images. Use this to read structured content.
#### Get Single Block
```
{ "action": "get_block", "doc_token": "ABC123def", "block_id": "doxcnXXX" }
```
#### Update Block Text
```
{ "action": "update_block", "doc_token": "ABC123def", "block_id": "doxcnXXX", "content": "New text" }
```
#### Delete Block
```
{ "action": "delete_block", "doc_token": "ABC123def", "block_id": "doxcnXXX" }
```
#### List Comments
```
{ "action": "list_comments", "doc_token": "ABC123def", "page_size": 50 }
```
Returns all comments for the document. Use `page_token` for pagination. Comments include `is_whole` field to distinguish between whole-document comments (true) and block-level comments (false).
#### Get Single Comment
```
{ "action": "get_comment", "doc_token": "ABC123def", "comment_id": "comment_xxx" }
```
#### Create Comment
```
{ "action": "create_comment", "doc_token": "ABC123def", "content": "Comment text" }
```
#### List Comment Replies
```
{ "action": "list_comment_replies", "doc_token": "ABC123def", "comment_id": "comment_xxx", "page_size": 50 }
```
`page_size` should be a positive integer. If omitted, tool defaults to `50`.
#### Comment Write Scope
Current tool provides documented comment write action `create_comment` (global comment creation). For replies, use `list_comment_replies` for retrieval; the reply creation endpoint is not exposed in current SDK surface.
### Reading Workflow
1. Start with `action: "read"` - get plain text + statistics
2. Check `block_types` in response for Table, Image, Code, etc.
3. If structured content exists, use `action: "list_blocks"` for full data
### Configuration
```
channels:
feishu:
tools:
doc: true # default: true
```
**Note:** `feishu_wiki` depends on this tool - wiki page content is read/written via `feishu_doc`.
### Permissions
Required: `docx:document`, `docx:document:readonly`, `docx:document.block:convert`, `drive:drive`
For comment operations:
- Read comments: `docx:document.comment:read`
- Write comments: `docx:document.comment` (optional, for create\_comment)
Source: [SKILL.md on GitHub](https://github.com/m1heng/clawdbot-feishu/blob/5f4418ce8f28f89d2d796a538ba104a943f0bbf2/skills/feishu-doc/SKILL.md)
## Third-party checks
1 warning16d5 checks · Risk SAFE
- Gen Agent Trust Hub16d
The skill is generally safe, but it interacts with external document content from Feishu/Lark which could potentially contain instructions that mislead the AI agent (indirect prompt injection).
- Socket16d
No alerts
- Snyk16d
Risk: MEDIUM · 1 issue
- Runlayer7mo
2 files scanned · No issues
- ZeroLeaks5mo
Score: 93/100 · 2 sections analyzed
## Provenance
[Signed by skilld at 5f4418c.](https://github.com/m1heng/clawdbot-feishu/commit/5f4418ce8f28f89d2d796a538ba104a943f0bbf2 "5f4418ce8f28f89d2d796a538ba104a943f0bbf2") This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub 2 months ago.
Dormantupdated 7 months ago
## Topics
- [API](https://skilld.dev/skills/tag/api "REST/GraphQL/RPC design, client generation")
- feishu
- document
- markdown
- comments
- blocks
- read-write
- lark
## README badge
## What it does
Reads, writes, and appends Feishu document content via token-based API; also manages document and block-level comments. Targets the Feishu cloud docs platform and handles markdown conversion, block operations, and comment threads with pagination support.
Generated from the current SKILL.md.
## Frequently asked
Can I read and write tables in Feishu documents?
You can read tables using the list\_blocks action, which returns full structured data. However, markdown table syntax is not supported when writing — use list\_blocks to inspect table structure and update individual blocks instead.
What's the difference between create and create_and_write?
create\_and\_write is atomic and recommended — it creates the document and writes content in a single call. Use create only if you need an empty document first.
How do I handle images in document content?
Images in markdown format (!\[](url)) are automatically uploaded to Feishu when you write or append content.
Can I reply to comments?
You can list replies to a comment using list\_comment\_replies, but the skill does not expose a reply creation endpoint — only global comment creation is supported.
How do I extract the document token from a Feishu URL?
Take the alphanumeric string after /docx/ or /docs/ in the URL — for example, from https://xxx.feishu.cn/docx/ABC123def, the token is ABC123def.
Generated from the current SKILL.md. These answers refresh after source changes.
## Related skills
-
-
-
-
-
-