Xiaohongshu Publishing Skill

This skill document contains the detailed publishing process, DOM selectors, and operation steps for the Xiaohongshu Creator Platform.

Platform Overview

Platform: Xiaohongshu Creator Platform Domain:

creator.xiaohongshu.com

Publishing Format Selection

Choose different publishing entries based on content length:

Content Length	Publishing Format	Entry URL
< 140 characters	Text with Images	`https://creator.xiaohongshu.com/publish/publish?target=image`
≥ 140 characters	Graphic Notes	`https://creator.xiaohongshu.com/publish/publish?target=article`

I. Text with Images Process (< 140 characters)

Process Overview

1. Navigate to the Text with Images entry
2. Click the "Text with Images" button
3. Enter content for the first image (title)
4. Add a second image and enter body text
5. Generate all images at once
6. Select a template style and click Next
7. Fill in publishing information (title, body text, hashtags)
8. Publish after user confirmation

[!IMPORTANT] Core Process: Enter all content (title + body text) first, then generate all images at once. Do not generate each image separately!

Step 1: Navigate to the Text with Images Entry

URL:

https://creator.xiaohongshu.com/publish/publish?target=image

After the page loads, it will display the "Upload Graphics and Text" option, including two buttons:

"Upload Images" (red button)
"Text with Images" (gray button with icon)

Step 2: Click the "Text with Images" Button

Finding Method:

javascript

find: "文字配图 button"

Element Features:

Type:
```
button
```
Text: "文字配图"
Function: Enter the text-to-image editor

Operations:

javascript

find("文字配图 button")
click()
wait(2)

Step 3: Enter Content for the First Image (Title)

Input Box:

javascript

find("真诚分享经验或资讯 textbox")

Operations:

javascript

find("真诚分享经验或资讯 textbox")
click()
type(title)
wait(1)

Step 4: Add a Second Image and Enter Body Text

Add Second Image:

javascript

find("再写一张")
click()
wait(1)

Body Text Input Box:

javascript

find("在这里输入正文 textbox")

Operations:

javascript

find("在这里输入正文 textbox")
click()
type(content)
wait(1)

[!NOTE] All content (title + body text) has been entered at this point, ready to generate all images at once.

Step 5: Generate All Images at Once

Generate Images Button:

javascript

find("生成图片 button")

Operations:

javascript

find("生成图片 button")
click()
wait(5)  // 等待所有图片生成，时间稍长

[!NOTE] Clicking "Generate Images" will generate both the title and body text images simultaneously. No need to click generate separately for each image.

Step 6: Select Template Style and Click Next

Page Features:

Title: "Preview Images"
Large preview area on the left displays generated images
Multiple template options on the right (Basic, Border, Memo, Doodle, Handwritten, Light & Shadow, Minimalist, Sticky Note, Print, Tech, etc.)
"Next" button at the bottom

Template Selection:

"Border" template is selected by default (highlighted with blue border)
Can click other templates to switch styles
It is recommended to use the default selected template for automated processes

Operations:

javascript

// Use the default selected template
find("下一步 button")
click()
wait(2)

Step 7: Fill in Publishing Information

Page Title: "Publish Graphics and Text"

7.1 Image Editing Area

Features:

Displays "Image Editing (2/18)" - indicates 2 images have been added, maximum 18
"Add" button on the left to continue adding images
Displays thumbnails of generated images

7.2 Fill in Title

Title Input Box:

javascript

find("填写标题会有更多赞哦 input")

Operations:

javascript

find("填写标题会有更多赞哦 input")
form_input(title)

7.3 Fill in Complete Body Text and Hashtags

Body Text Box:

javascript

find(包含标题的 textbox)  // 正文文本框

Important Notes:

The body text box will automatically fill with the content of the first image (title)
Must replace it with the complete body text (not a summary or partial content)
Body text includes: complete body content + two line breaks + hashtags

Operations:

javascript

find(包含标题的 textbox)  // 正文文本框
click()
key("cmd+a")  // Select all existing content
type(content + "\n\n" + tags)  // Fill in complete body text + two line breaks + hashtags

[!WARNING] Hashtag Format Requirement: There must be two line breaks (
\n\n
) between the body text and hashtags, otherwise the hashtags will be displayed closely to the body text and look unappealing.

Hashtag Format:

Start with
```
#
```
Separate multiple hashtags with spaces
It is recommended to use no more than 3 hashtags
Must have two line breaks separating hashtags from the body text

7.4 Other Publishing Options

Topic Button:

javascript

find: "话题"

User Button:

javascript

find: "用户"

Emoji Button:

javascript

find: "表情"

Activity Topics:

The page will display current platform activity topics
Format: "# 第五人格五周年春"
Can choose to participate

Add Location:

javascript

find: "添加地点"

Add Collection:

javascript

find: "添加合集"

Associate Group Chat:

javascript

find: "选择群聊"

Step 8: Publish

Publish Button:

javascript

find: "发布 button"
element_type: button
color: Red (primary action button)

Save Draft Button:

javascript

find: "暂存草稿 button"
element_type: button
color: Gray (secondary action button)

Auto-Save:

The page will automatically save drafts
Displays "Auto-saved at HH:MM" at the bottom

⚠️ Important Reminder: According to security policies, automated scripts should:

Stop after filling in all content
Display a message prompting the user to review
Do not automatically click the "Publish" button
Let the user manually click "Publish" in the browser

II. Graphic Notes Process (≥ 140 characters)

Process Overview

1. Navigate to the Graphic Notes entry
2. Click the "New Creation" button
3. Fill in the title
4. Fill in the body text
5. Click "One-Click Formatting" to select a template
6. Fill in body text excerpt and hashtags
7. Fill in other publishing information
8. Publish after user confirmation

Step 1: Navigate to the Graphic Notes Entry

URL:

https://creator.xiaohongshu.com/publish/publish?target=article

After the page loads, it will display the "Write Long Article" page with the following features:

Main Title: "Supports 1000-character long articles, full-screen reading experience"
Two buttons: "New Creation" (red) and "Import Link"
"Long Article Collections" section at the bottom

Step 2: Click the "New Creation" Button

Finding Method:

javascript

find: "新的创作 button"

Element Features:

Type:
```
button
```
Text: "新的创作"
Color: Red (primary action button)

Step 3: Fill in the Title

After clicking "New Creation", enter the long article editor.

Page Features:

Top Title: "New Creation"
Toolbar: Formatting tools like H₁, H₂, Lists, Quotes, Images, Emojis, etc.
Two input areas: Title area and body text area

Title Input Box:

javascript

find: "输入标题"
element_type: textbox

Input Method:

javascript

click(ref_51)  // 点击标题输入框
type("小红书自动发布工具使用指南")  // 输入标题

Step 4: Fill in the Body Text

Body Text Editor:

javascript

// 正文编辑器是一个 generic 元素（ref_55）
// 不是标准的 textarea

Input Method:

javascript

click(ref_55)  // 点击正文编辑区域
type("正文内容...")  // 输入正文

Body Text Features:

Supports rich text editing
Word count displayed at the bottom: "Word count: 194"
Auto-save feature: "Auto-saved at HH:MM"
Maximum support for 10,000 characters

Step 5: Click "One-Click Formatting" to Select a Template

One-Click Formatting Button:

javascript

find: "一键排版 button"

After clicking, enter the formatting preview page.

Formatting Preview Page Features:

Left: Content preview (in article card format)
Right: Multiple template options
- "Minimalist Basic" (selected by default ✓)
- "Fresh and Bright"
- "Black and White Minimalist"
Bottom: "Drag slider to quickly locate" control

Next Button:

javascript

find: "下一步 button"

Click "Next" to enter the final publishing page.

Step 6: Fill in Body Text and Hashtags

Page Title: "Publish Graphics and Text"

Important Notes:

Graphic Notes has a "Body Text Excerpt" input box. Although it's called "excerpt", must fill in the complete body text
Do not fill in a summary, but the full body content + hashtags

Body Text Input Box:

javascript

find: "输入正文摘录 textarea"
element_type: textbox

Input Method:

javascript

click(ref_194)  // 点击正文内容输入框
type(完整正文内容 + "\n\n" + 标签)  // 输入完整正文 + 标签

Content Format:

Fill in the complete body text (not a summary)
Add two line breaks after the body text
Then add hashtags (starting with
```
#
```
)
Separate multiple hashtags with spaces
It is recommended to use no more than 3 hashtags

Example:

在这个信息爆炸的时代，内容创作者面临着越来越多的平台和渠道选择。小红书作为一个重要的社交电商平台，已经成为许多创作者分享生活方式和产品推荐的首选平台。

为了提高发布效率，我们开发了这款自动化发布工具。它可以帮助你快速将内容发布到小红书平台，节省大量的重复性工作时间。

本文将详细介绍如何使用这个工具，让你的内容发布工作变得更加轻松高效。无论你是个人创作者还是团队运营，这个工具都能为你带来显著的效率提升。

#小红书发布 #自动化工具 #效率提升

Step 7: Fill in Other Publishing Information

Title Input Box (optional, usually auto-filled):

javascript

find: 包含标题文本的 textbox
max_length: 20 characters

Cover Image:

The system will automatically convert the long article content into a cover image
Displayed in the "Image Editing" area
"Add" button on the left to add more cover images

Other Options:

Add Location
Add Collection
Associate Group Chat
Activity Topics (same as Text with Images)

Step 8: Publish

Publish Button:

javascript

find: "发布 button"
element_type: button
color: Red

Save Draft Button:

javascript

find: "暂存草稿 button"

⚠️ Important Reminder: According to security policies, automated scripts should:

Stop after filling in all content
Display a message prompting the user to review
Do not automatically click the "Publish" button
Let the user manually click "Publish" in the browser

Comparison: Graphic Notes vs Text with Images

Feature	Text with Images (< 140 characters)	Graphic Notes (≥ 140 characters)
Entry URL	`target=image`	`target=article`
Editing Method	Text-to-image generation	Rich text editor
Title Input	Content of first image	Independent title input box
Body Text Input	Starts from second image	Body text editor
Cover Image	Manually generate multiple images	Automatically generate cover image
Body Text Area on Publish Page	Body text box	"Body Text Excerpt" input box
Body Text Filling Method	Complete body text + hashtags	Complete body text + hashtags
Formatting	None	Supports H1/H2/lists, etc.
Word Limit	Recommended < 140	140-10,000 characters

Key Reminder: Both modes require filling in complete body text instead of a summary or partial content on the publishing page.

III. Common Elements and Selectors

Login Status Detection

Method 1: Check User Avatar

javascript

find: "用户头像"

If the user avatar cannot be found or a "Login" button is displayed, it means the user is not logged in.

Method 2: Check URL Redirection If the URL redirects to the login page after navigating to the publishing page, it means the user is not logged in.

Error Handling

Common Error Prompts:

"Please log in first" - Requires manual login by the user
"Content cannot be empty" - Required fields are not filled in
"Title cannot exceed 20 characters" - Title is too long
"Insufficient number of images" - At least 1 image is required

IV. Best Practices

1. Content Preparation

Title: Concise and clear, no more than 20 characters
Body Text: Clearly segmented, use line breaks to enhance readability
Hashtags: Select highly relevant hashtags, 2-3 are recommended

2. Image Recommendations

Text with Images: At least 2 images (title + body text)
Content Distribution:
- First image: Core title or question
- Subsequent images: Detailed explanations, steps, summary

3. Hashtag Selection

Good Hashtag Examples:

```
#小红书发布
```
```
#自动化工具
```
```
#效率提升
```
```
#生活美学
```

Avoid:

Overly broad hashtags (e.g.,
```
#生活
```
)
Irrelevant hashtags
More than 5 hashtags

4. Publishing Timing

Avoid frequent publishing (recommended interval of at least 1 hour)
Consider user active times (8 AM, 12 PM, 8 PM)

V. Troubleshooting

Issue 1: Text Input Failure

Cause: Xiaohongshu uses a custom DIV editor instead of a standard input/textarea

Solution:

Click the text box first to activate it
Use the
```
type
```
action to enter text
Do not use
```
form_input
```
(only applicable to standard form elements)

Issue 2: Generate Images Button is Unclickable

Cause: Text content is empty or too short

Solution:

Ensure sufficient text content has been entered
Wait for auto-save to complete (check the "Auto-saved at" prompt at the bottom)

Issue 3: Hashtags are Not Added Correctly

Cause: Incorrect hashtag format or not starting with

Solution:

Ensure hashtags start with
```
#
```
Separate multiple hashtags with spaces
There should be a space or line break after hashtags

Issue 4: Page Loading is Slow

Cause: Network delay or slow server response

Solution:

Increase
```
wait
```
time (2-3 seconds) after key operations
Use
```
screenshot
```
to verify page status
Check the page title to confirm successful navigation

VI. Word Limits and Specifications

Field	Minimum	Maximum	Notes
Title	1 character	20 characters	Required
Body Text	1 character	10,000 characters	Required
Hashtags	0	3 recommended	Optional
Number of Images	1	18	At least 1 image for Text with Images

VII. Automation Notes

Anti-Automation Detection

Xiaohongshu may have anti-automation mechanisms, it is recommended to:

Operation Intervals: Add 1-3 second delays between each step
Randomization: Randomize delay times appropriately
Frequency Limits: Avoid frequent publishing in a short period
Manual Review: Always let the user confirm the final publish

Security

Do Not Automatically Click Publish: Only fill in content, let the user manually publish
Content Review: It is recommended that the user preview the content
Sensitive Information: Avoid processing sensitive information during automation

VIII. Summary

This skill document provides the complete process and detailed DOM selector information for Xiaohongshu's Text with Images publishing. The Graphic Notes process requires further testing and improvement.

Core Principles:

Text with Images Process: Enter all content (title + body text) first, then generate all images at once
Use the correct entry URL
Execute each step in order
Use
```
wait
```
to ensure page loading
Verify status via
```
screenshot
```
Let the user confirm the final publish

xhs-publisher

NPX Install

Tags

SKILL.md Content (Chinese)

Xiaohongshu Publishing Skill

Platform Overview

Publishing Format Selection

I. Text with Images Process (< 140 characters)

Process Overview

Step 1: Navigate to the Text with Images Entry

Step 2: Click the "Text with Images" Button

Step 3: Enter Content for the First Image (Title)

Step 4: Add a Second Image and Enter Body Text

Step 5: Generate All Images at Once

Step 6: Select Template Style and Click Next

Step 7: Fill in Publishing Information

7.1 Image Editing Area

7.2 Fill in Title

7.3 Fill in Complete Body Text and Hashtags

7.4 Other Publishing Options

Step 8: Publish

II. Graphic Notes Process (≥ 140 characters)

Process Overview

Step 1: Navigate to the Graphic Notes Entry

Step 2: Click the "New Creation" Button

Step 3: Fill in the Title

Step 4: Fill in the Body Text

Step 5: Click "One-Click Formatting" to Select a Template

Step 6: Fill in Body Text and Hashtags

Step 7: Fill in Other Publishing Information

Step 8: Publish

Comparison: Graphic Notes vs Text with Images

III. Common Elements and Selectors

Login Status Detection

Error Handling

IV. Best Practices

1. Content Preparation

2. Image Recommendations

3. Hashtag Selection

4. Publishing Timing

V. Troubleshooting

Issue 1: Text Input Failure

Issue 2: Generate Images Button is Unclickable

Issue 3: Hashtags are Not Added Correctly

Issue 4: Page Loading is Slow

VI. Word Limits and Specifications

VII. Automation Notes

Anti-Automation Detection

Security

VIII. Summary