xiaohongshu-search

Xiaohongshu viral note query

1. Introduction

Xiaohongshu popular note search tool, supports searching Xiaohongshu popular viral notes by keyword, and intelligently ranks and recommends based on a three-dimensional score of relevance, popularity, and timeliness. It also provides popular note recommendations and niche track guidance, helping creators, brands, and MCN agencies discover popular trends and gain creative inspiration. Note: This tool is executed only in the main Agent, not dispatched to sub-Agents.

2. Features

🔍 Intelligent keyword search — Supports exact keyword search, multi-keyword combinations (comma-separated), and site-wide popular queries (empty keyword)
📊 Three-dimensional score ranking — When a keyword is present, the total score is calculated as a weighted sum of relevance (max 10 points), popularity (max 3 points), and timeliness (max 2 points) (max 15 points); site-wide popular notes are sorted by interaction count
🧠 Fine-grained intent understanding — Prioritizes extracting niche direction words from the user's description, identifies generic words, and automatically recommends 10 niche directions
⏱️ Flexible time range — Defaults to querying the last 7 days; when data is insufficient, automatically expands the time range (1 day→3 days→7 days→30 days); updated daily at 7 AM
🔥 Popular note recommendations — When results are few, automatically displays recent popular recommended notes and popular topic hashtags
📈 Niche track guidance — After each query, proactively recommends 10 related niche directions to help users explore further
🏷️ Keyword expansion recommendations — The script returns the relatedSearches field, automatically displaying related search suggestions
📩 Scheduled subscription push — Supports creating calendar subscription tasks, automatically pushing the latest popular notes at the set time
📄 HTML report generation — Automatically generates {keyword}_热门数据.html visualization files
🛡️ Strong data explanation — The inclusion standard for popular notes is an interaction count of 1000+; the data explanation and sorting basis are displayed at the top

3. One-click installation

Authentication

Get API Key

Please go to RedFox Hub to get the API KEY

Configure API Key

Option 1: Using OpenClaw as an example, add REDFOX_API_KEY to ~/.openclaw/openclaw.json:

{ "env": { "REDFOX_API_KEY": "ak_xxxx..." } }

Option 2: Terminal configuration

export REDFOX_API_KEY="ak_xxxx..."

Dependency installation

This Skill uses the Python 3 standard library and requires no additional third-party dependencies. Just ensure Python 3.x is installed on the system.

Environment variable configuration

Environment variable	Description	Required	How to obtain
`REDFOX_API_KEY`	RedFox Data API Key	Yes	RedFox Hub

4. Usage guide

⚠️ Core execution rules (must be followed)

Generic words must be asked about before querying: When a generic word is identified,directly calling the script is strictly prohibited, you must first output niche word recommendations and wait for the user's selection before executing the query
Correct execution order: Keyword extraction → determine whether it is a generalized term → if it is a generalized term, ask the user → after the user replies, call the script
Mandatory wait rule: After outputting the niche term recommendations, execution must stop and wait for the user's next-turn reply of "expand" or "do not expand",and no script call may continue to be executed in the same conversation

Common generalized terms: Generalized term: a summary word with a high level of abstraction and broad coverage, without specific scenario/attribute modifiers, such as industry categories, and may contain multiple subcategories. Characteristics: ① Semantically a superordinate concept (e.g., "beauty" includes "foundation/lipstick"; "sports" includes "running/yoga"; such as AI); ② In context, it is often paired with summary words such as "field" and "type" (e.g., "beauty field", "sports type").

Common specific terms: Specific term: an instantiated word with a low level of abstraction and a clear referent, containing specific scenario/attribute modifiers, and belonging to a direct subcategory of a generalized term. Characteristics: ① Semantically a subordinate concept (e.g., "foundation" is a subcategory of "beauty products"; "keto diet" is a subcategory of "dietary methods"); ② The word structure often contains modifying components (e.g., "spring" → "spring outfits"; "keto" → "keto diet").

Basic usage (complete the query in 3 steps)

Step 1 — Extract keywords: Extract search keywords from the user's natural language description. Prioritize extracting niche direction terms (with specific scenario/attribute modifiers) rather than generalized broad category terms.

Step 2 — Call the script：

python scripts/fetch_xhs_hot_articles.py --keyword <关键词> --start-date <日期>

With track keywords:python scripts/fetch_xhs_hot_articles.py --keyword <关键词> --start-date <日期>
Without track keywords (query site-wide trending):python scripts/fetch_xhs_hot_articles.py --keyword "" --start-date <日期>
Separate multiple keywords with commas:python scripts/fetch_xhs_hot_articles.py --keyword "减脂餐,职场穿搭,健身" --start-date <日期>
Pagination parameter:--page-num 1 --page-size 50

Step 3 — View results: The script returns structured JSON, and the results are output according to the display strategy specified in this guide.

Advanced usage

Understanding user intent (before querying the script)

⚠️ Core rule: semantic understanding should be used, prioritizing extraction of niche direction terms from the user's description rather than generalized broad category terms

1. Determine whether the user mentions track keywords：

No track keywords(e.g., "what are the recent trending notes", "what popular content is there recently", "take a look at the trending data") → directly call the script, passing an empty string as the keyword "", to query site-wide trending
Has track keywords → continue extraction and judgment

2. Extract precise search keywords(executed only when the user mentions a track):

Analyze the user's description: Extract clear niche field terms from the user's self-introduction or requirement description
Example analysis:
- User input: "I am an arts-and-culture self-media Xiaohongshu blogger with 10k followers. I usually post content related to niche film aesthetic accumulation, book reviews, music reviews, Hong Kong and Taiwan culture, etc. Help me find trending topics in the film field"
- Analysis result: niche directions mentioned by the user = niche films, book reviews, music reviews, Hong Kong and Taiwan culture
- Relate the preceding scenario to "film" to obtain niche terms = niche films, Hong Kong and Taiwan films, film music reviews
- Search keywords: niche films, Hong Kong and Taiwan films, film music reviews
- ❌ Wrong approach: extracting only the generalized term "film" for the search

3. Keyword type judgment(executed only when keywords are extracted):

Niche terms/vertical tracks(Words containing specific scenario/attribute modifiers, such as "workplace outfit", "fat-loss meal", "petite outfit") → search directly, no need to ask about expansion
Generalized words/categories(Pure broad category words, such as "outfit", "food", "beauty", with no modifiers at all) → execute the expansion strategy
Judgment principle: has modifiers (scenario/audience/style/intent) = specific term, search directly; no modifiers = generalized term, expansion needed

Generalized term expansion strategy

Generalized term handling process (⚠️ must wait for the user's explicit reply before calling the script!)：

Step 1: Generate specific terms(Calling the script to search data is prohibited)

Expansion term generation principles:
- Moderate word granularity: do not add combinations to words, avoid being too specific (e.g., "middle-class outfit" is too specific, no data can be found)
- Must cover different scenarios: 2-3 each of trend terms, audience terms, scenario terms, and intent terms
Output example:
```
我识别到「中产」是较大的分类，已查询近期热门趋势，推荐以下细分方向：
老钱、轻奢、品质生活、松弛感、高级感穿搭、体面、法式穿搭、律师、医生、品质家居
回复「拓展」将同时搜索这10个词，回复「不拓展」将继续搜索「中产」
```
Step 2: Wait for the user's reply
- ❌ Prohibited: calling the script when the user has not replied
- ✅ Correct: only wait for the user's explicit reply of "expand" or "do not expand" before executing
Step 3: Execute according to the user's explicit reply
- User replies "expand" → call the script to search 10 specific terms
- User replies "do not expand" or "continue" → call the script to search the original keyword
- User does not reply or replies with other content → identify the corresponding intent

Time range and data query

Time range：

The database only contains data from yesterday to 30 days ago
Default definition of "recent": the last 7 days (startDate = today - 7 days)
Date calculation(Convert the user's expression into startDate):
- Today: directly use yesterday's date, startDate = yesterday
- Recent/last 7 days: startDate = today - 7 days
- Last N days: startDate = today - N days
- Example: user says "last 15 days" → startDate = today - 15 days

Automatic adjustment when data is insufficient (⚠️ prioritize extending time, changing words is prohibited!)：

Handling principle: when data is insufficient, only the time range can be extended; keywords cannot be replaced or expanded
Adjustment order: automatically extend the time range in the following order
1. Last 1 day → last 3 days
2. Last 3 days → last 7 days
3. Last 7 days → last 30 days
Inform the user: when automatically adjusting, inform the user: "This keyword has relatively little data in the last X days, and the time range has been automatically extended to the last Y days"
Prohibited actions: ❌ Do not replace keywords, recommend other words, or trigger the generalized term expansion process just because data is insufficient

Apology explanation for being out of range or data not updated：

When the user says "today": reply "We are very sorry, today's data has not been updated yet, and we have shown you the most recently available data"
When the time requested by the user exceeds 30 days: reply "We are very sorry, currently only data from the last 30 days is supported, and we have shown you the closest data"

Output file：

Filtered recommended data:{keyword}_热门数据.html

Preliminary notes (must be communicated to the user before displaying data)

Data description: The hot notes range covers articles with 1000+ interactions; yesterday's data is updated every day at 7:00 AM. The interaction data for articles is as of the time of ingestion, not real-time data; after ingestion, interaction data may continue to grow.
Sorting description(when there is a keyword search): weighted calculation based on the three dimensions of relevance (out of 10), popularity (out of 3), and recency (out of 2), for a total score of 15
Sorting description(site-wide hot / no keyword): sorted by interaction count, no score field

Data display strategy (core)

⚠️ Mandatory output rules：

✅ Must strictly follow the format specified in this step for output
❌ Do not add any analysis or interpretation before the output
❌ Do not take the liberty of giving suggestions or solutions
❌ Do not ask the user about their true purpose or needs
✅ Directly read the JSON data returned by the script and output it according to the corresponding strategy

Data field description：

articles: normal note data (main display content)
latestHotArticles: recommended hot notes (auxiliary content, 10 items displayed by default, table does not include the score field)
hotTopics: hot topics (returned by the API, for reference only, not displayed in the conversation)

A. Number of articles ≥ 10

Display content:

Time range description: must inform the user of the queried time range, e.g. "📅 Query time range: May 8 - May 19"
Normal note data (when there is a keyword, sorted by totalScore descending; when site-wide hot, sorted by interaction count)
Related search recommendations (relatedSearches)

Markdown table format：

⚠️ The table field order must strictly follow the order below：

Note: the total score field needs to be displayed in bold (using**分数**format)

Example (with keyword): 📅 Query time range: May 8 - May 19

Note title	Author	Interactions	Publish time	Relevance	Popularity	Recency	Total score
Must-read for workplace newcomers: 5 tips to help you quickly integrate into the team	Workplace Growth Community	10.0w	2026-05-15	9.8	3.0	2.0	14.8

Example (site-wide hot): 📅 Query time range: May 8 - May 19

Note title	Author	Interactions	Publish time
Hot note title	Author name	10.0w	2026-05-15

🔤 Related search recommendations: workplace communication, workplace promotion, workers

B. Number of articles < 10 but > 0

Display content:

Time range description: must inform the user of the queried time range, e.g. "📅 Query time range: May 8 - May 19"
Prompt information: "💡In the current time period for the current keyword, only X results were found. You can try expanding the keywords or the time range. We have also recommended recent popular notes for you."
Normal note data
Keyword expansion recommendations (relatedSearches)
Recommended popular notes (latestHotArticles, with a "Recommended Popular Notes" title section, displaying 10 items by default)
Recommended popular topics

Markdown format example：

📅 The inclusion principle for viral notes is articles with more than 1,000 interactions. Query time range: May 8 - May 19

In the current time period for the current keyword, only 3 results were found:

When there are keywords:

Note title	Author	Interactions	Publish time	Relevance	Popularity	Timeliness	Total score
Note 1	Author 1	10.0w	2026-05-15	9.8	3.0	2.0	14.8

When popular site-wide (no scoring field):

Note title	Author	Interactions	Publish time
Note 1	Author 1	10.0w	2026-05-15

🔤 Keyword expansion recommendations: workplace communication, workplace promotion, office workers

💡We have recommended recent popular notes for your reference, which may be helpful to you：

⚠️ The recommended popular notes table does not require a scoring field, and the format is:

Note title	Author	Interactions	Publish time
Popular note 1	Author A	8.5w	2026-05-14
Popular note 2	Author B	6.2w	2026-05-13

📈 You can also try searching the following popular tracks:：

Fashion, food, makeup, film and television, workplace, cute pets, home, travel, transportation, interests, technology, internet, healthcare, astrology and relationships, weddings, photography, education, parenting, personal care, trendy shoes and bags, lifestyle, scientific exploration, news and information, sports

C. Number of articles = 0

⚠️ You must strictly output in the following format. Do not add suggestions or analysis on your own initiative.

Display content:

**🔍抱歉，爆款笔记收录原则为互动数1000以上的文章,该搜索词在查询时间范围（5月8日 - 5月19日）内太小众，未找到与"XXX"直接相关的内容，你可以尝试用更短/宽泛的关键词重试。**

**推荐搜索词**：从脚本返回的relatedSearches字段中提取推荐词，以加粗形式展示；

💡我们为您推荐了近期的热门笔记供参考，或许对您有帮助：

⚠️ 推荐热门笔记表格不需要评分字段，格式为：
| 笔记标题 | 作者 | 互动数 | 发布时间 |
|---------|------|--------|----------|
| [热门笔记1](url) | [作者A](https://www.xiaohongshu.com/user/profile/xxx) | 8.5w | 2026-05-14 |
| [热门笔记2](url) | [作者B](https://www.xiaohongshu.com/user/profile/xxx) | 6.2w | 2026-05-13 |

📈 您还可以尝试搜索以下热门赛道：
穿搭、美食、彩妆、影视、职场、萌宠、家居、旅行、交通、兴趣、科技、互联网、医疗保健、星座情感、婚庆婚礼、拍摄、教育、亲子育儿、个人护理、潮流鞋包、生活、科学探索、新闻资讯、运动

Output rules：

✅ You must directly output the above format content
❌ Do not add extra analysis or suggestions
❌ Do not explain why no data was found
❌ Do not proactively provide other search options
❌ Do not ask about the user's true purpose

Display logic (pagination)

When the number of articles > 10：

By default, only the first 10 items of data are initially displayed
You must prompt the user:

💡 当前共找到 X 条相关笔记（X为实际返回条数），已展示前10条。是否需要查看全部？

Wait for the user to reply:

User replies "yes"/"view all"/"all" → display all data
User replies "no"/"not needed"/"no need" → do not display more

Format when displaying all data：

📊 全部结果（共X条，X为实际返回条数）：

有关键词时：
| 笔记标题 | 作者 | 互动数 | 发布时间 | 相关性 | 热度 | 时效 | **总分** |

全站热门时：
| 笔记标题 | 作者 | 互动数 | 发布时间 |

| ...（全部数据）...

Subscription service inquiry (must be executed)

When the number of articles > 0, you must ask after the result output is completed：

📬 订阅服务
1️⃣ 是否需要订阅当前搜索条件笔记，订阅后将定时推送给您？
2️⃣ 暂不需要

Handle user replies：

User selects 1️⃣ → use calendar_create Tool creates a schedule and subscribes to the current search criteria
User selects 2️⃣ → End the current conversation

Subscription implementation steps：

Inform the data update time and ask about the push time：

📅 数据更新时间：每日早上7点更新昨日数据

请告诉我您希望推送的具体时间~

After the user selects, call the calendar_create tool：
- title：小红书热门笔记订阅：{关键词}
- description: Record the current search parameters (keywords, time range)
- start_time: Set according to the time selected by the user
- remind_type: Set as a recurring reminder
- Other parameters use the current query parameters
Prompt after successful subscription：

✅ 订阅创建成功！

📌 订阅信息：

- 关键词：{关键词}
- 时间范围：{当前时间范围}
- 推送时间：{用户选择的时间}
- 数据更新：每日早上7点更新昨日数据

到达设定时间后，将自动为您推送最新的小红书热门笔记。

⚠️ Mandatory rules：

✅ Must ask immediately after the result output is completed
✅ When the user chooses to subscribe, must use the calendar_create tool
✅ Parameters must use the current query parameters (keywords, time range, etc.)
❌ Do not skip this step
❌ Do not ask before displaying the results

Recommended niche tracks (⚠️ Must be executed after displaying the data)

Core rules: After displaying the popular data,must proactively ask the user whether they need to query more specific niche tracks

Recommended niche term generation：

Based on the keywords of the current query, generate 10 related niche direction terms
Generation principles：
- Moderate term scope: Avoid being too narrow (no data found) or too broad (scope too large)
- Cover different dimensions: 2-3 each of scenario terms, audience terms, style terms, and intent terms
- Reference data performance: Prioritize recommending directions with higher recent popularity

Output format：

以上是「{当前关键词}」的热门数据。

如需深入了解某个细分方向，可以从以下赛道中选择：
{细分词1}、{细分词2}、{细分词3}、{细分词4}、{细分词5}、 {细分词6}、{细分词7}、{细分词8}、{细分词9}、{细分词10}

回复具体关键词，我将为您查询该赛道的热门笔记。

Example output：

以上是「减脂餐」的热门数据。

如需深入了解某个细分方向，可以从以下赛道中选择：
早餐减脂、减脂便当、低卡晚餐、减脂零食、学生党减脂、一周食谱、减脂沙拉、减脂主食、控糖减脂、懒人减脂餐

回复具体关键词，我将为您查询该赛道的热门笔记。

Special case handling：

If the user queries a very niche term (such as "one-week fat-loss meal plan"), more specific directions may no longer be recommended; terms that have already been expanded do not need to be asked about again for expansion

If the user queries an empty keyword (site-wide popular),directly use the popular track listrecommend, in the following format:

以上是全站热门数据。

如需深入了解某个细分赛道，可以从以下热门赛道中选择：
穿搭、美食、彩妆、影视、职场、萌宠、家居、旅行、交通、兴趣、科技、互联网、医疗保健、星座情感、婚庆婚礼、拍摄、教育、亲子育儿、个人护理、潮流鞋包、生活、科学探索、新闻资讯、运动

回复具体关键词，我将为您查询该赛道的热门笔记。

Self-check before output [must be executed]

Before output, check item by item whether every field of the output format is complete:

[] Intent recognition: Is the user's search intent accurately identified?
[] Note data: Are all filtered results returned by the script displayed truthfully (display 10 items when max_items=10), with each item containing the sequence number (bold), note title, work link, author name, author link, publish time, interaction count, and recommendation reason (bold)?
[] HTML card: Does it include an html card?
[] Recommended niche terms: Are 10 niche terms listed?

If any field is missing or incomplete, it must be completed before output.

Common command quick reference table

Scenario	Command
Keyword search (default last 7 days)	`python scripts/fetch_xhs_hot_articles.py --keyword "关键词" --start-date <日期>`
Site-wide popular	`python scripts/fetch_xhs_hot_articles.py --keyword "" --start-date <日期>`
Multi-keyword search	`python scripts/fetch_xhs_hot_articles.py --keyword "词1,词2,词3" --start-date <日期>`
Paginated query	`python scripts/fetch_xhs_hot_articles.py --keyword "关键词" --start-date <日期> --page-num 1 --page-size 50`
Generate HTML report	Script automatically generates `{keyword}_热门数据.html`
Subscription creation	After replying 1️⃣, use the `calendar_create` tool to create a scheduled task

5. Use Cases

Use Case 1: Xiaohongshu Blogger Seeking Topic Inspiration

Role: Xiaohongshu Content Creator
Need: Wants to learn which popular notes exist recently in the "fat-loss meals" niche, to find topic directions for the next note
How to Use: Enter the niche keyword "fat-loss meals"; the system returns a list of high-scoring popular notes, and after displaying them automatically recommends 10 niche directions (such as "breakfast fat-loss" and "fat-loss bento")
Expected Benefits: Quickly lock onto high-value topics through three-dimensional scoring and sorting, while gaining inspiration for niche tracks, improving content output quality

Use Case 2: Brand Market Research

Role: Brand Marketing Staff
Need: Understand the overall popular trends in the "outfit" track, but is unsure of specific niche directions
How to Use: After entering the broad term "outfit", the system recommends 10 niche directions (such as "petite outfit", "French outfit", "workplace outfit", etc.); reply "expand" to batch search all directions
Expected Benefits: Cover multiple niche areas at once, fully grasp the popularity distribution of the track, and provide data support for the brand's content marketing strategy

Use Case 3: MCN Agency Creator Content Planning

Role: MCN Agency Content Director
Need: Needs to view popular notes across multiple areas (fat-loss meals, fitness, workplace outfit) at once, to plan the content schedule for the agency's creator matrix
How to Use: Use commas to separate multiple keywords --keyword "减脂餐,健身,职场穿搭" for cross-domain queries
Expected Benefits: One command covers multiple categories, efficiently obtaining cross-domain popular trends and improving content planning efficiency

Use Case 4: Scheduled Daily Push of Popular Notes

Role: Xiaohongshu Operations Staff
Need: Hopes to automatically receive a list of popular notes in a specific track every morning, to continuously track trends
How to Use: After searching keywords, select "1️⃣ Subscribe", set the push time, and create a calendar scheduled task
Expected Benefits: No need to manually repeat searches; obtain the latest popular notes on a daily schedule, continuously track track dynamics, and maintain creative sensitivity

6. Project Architecture

Directory Structure

xiaohongshu-search/
├── SKILL.md                               # Skill 定义与使用文档（本文件）
├── scripts/
│   └── fetch_xhs_hot_articles.py          # 核心搜索脚本，调用红狐 API 获取小红书热门笔记
└── references/
    └── xhs_hot_article_format.md          # 数据字段格式参考文档

Tech Stack

Component	Technology	Description
Runtime Environment	Python 3.x	Standard library, no third-party dependencies
Data Interface	Redfox API (Redfox)	Authenticated via REDFOX_API_KEY
Output Format	JSON (stdout) + HTML (file)	JSON is output via stdout for AI parsing; HTML is a visual report file
Display Format	Markdown Table	The AI agent renders JSON as a table for display
Execution Restriction	Main Agent only	Not executed in sub-agents

Core Module Description

Module	Path	Features
Search Script	`scripts/fetch_xhs_hot_articles.py`	Call the Red Fox API to get Xiaohongshu trending notes, support --keyword, --start-date, --page-num, --page-size parameters, and automatically generate an HTML report
Data Format Reference	`references/xhs_hot_article_format.md`	Detailed explanation of the data field format returned by the interface and the output specification
SKILL Definition	`SKILL.md`	Define Skill metadata, intent understanding rules, generalization word expansion strategy, display strategy, subscription logic, and self-check checklist

Resource Index

Core Script：scripts/fetch_xhs_hot_articles.py — Call the Red Fox API to get Xiaohongshu trending note data and generate an HTML report
Reference Document：references/xhs_hot_article_format.md — When to read: when you need to understand the data field format and output specification

7. FAQ

Installation

Q: Which dependencies need to be installed? A: This tool uses the Python 3 standard library and requires no additional third-party dependencies. Just ensure that Python 3.x is installed on the system.

Q: How do I get an API Key? A: Please visit Red Fox Hub to register and get an API Key, and configure the environment variables according to the "One-click Installation" section of this document.

Usage

Q: What is the difference between generalization words and细分词? A: Generalization words are broad summarizing terms with a high level of abstraction and wide coverage (such as "beauty" and "outfit"), without specific scene/attribute modifiers;细分词 contain specific modifying components (such as "liquid foundation" and "petite outfit"). Generalization words trigger the expansion strategy, while细分词 are searched directly.

Q: What is the time range of the data? A: The database only contains data from yesterday to 30 days ago. By default, it queries the most recent 7 days, and automatically expands the time when there is insufficient data (1 day→3 days→7 days→30 days). Yesterday's data is updated every morning at 7 AM.

Q: Why do some tables have a score field and some do not? A: When there is a keyword search, results are sorted by totalScore (relevance + popularity + timeliness), and the score field is displayed; site-wide trending is sorted by interaction count, with no score field. The recommended trending notes table also does not include scores.

Q: How can I view the complete results if there are more than 10? A: When the results exceed 10, the system will prompt "Do you need to view all?". Reply "yes", "view all", or "all" to display the complete data.

Q: Why does it recommend细分赛道 after every query? A: This is a designed feature — to help users further discover more precise细分 directions from the current query results and deeply mine the value of the data. If the query is already a细分词, the system will intelligently determine whether to skip the recommendation.

Troubleshooting

Q: What should I do if the search results are empty? A: The inclusion standard for trending notes is an interaction count of 1000+. If the keyword is too niche or the time range is too short, there may be no data. The system will automatically expand the time range, and you can also choose a search term recommended in relatedSearches and try again.

Q: It says "Today's data has not been updated yet"? A: The database updates yesterday's data every morning at 7 AM, and the current day's data has not yet been stored. The system will automatically display the most recently available data.

Q: Script execution error? A: Common causes: (1) REDFOX_API_KEY is not configured or has expired; (2) the Python version is lower than 3.x; (3) network connection issues. Please troubleshoot them one by one.

Security Permission

Q: How should the API Key be stored securely? A: It is recommended to use option 1 (configure it in the env field of openclaw.json) to avoid leaking it in terminal history. Do not hardcode the API Key in scripts or upload it to public repositories.

Q: Data source and copyright? A: The data comes from public Xiaohongshu notes indexed by the Honghu API. The copyright of the notes belongs to the original authors. This tool is intended only for learning and content creation reference.

Q: Why must it be executed in the main Agent? A: The Xiaohongshu search tool involves complete intent understanding, generalized term expansion, and data presentation strategy. The process is complex and depends on global context judgment, so it is executed only in the main Agent to ensure consistent behavior and complete rules.

About this skill

1. Introduction

2. Features

3. One-click installation

Authentication

Get API Key

Configure API Key

Dependency installation

Environment variable configuration

4. Usage guide

⚠️ Core execution rules (must be followed)

Basic usage (complete the query in 3 steps)

Advanced usage

Understanding user intent (before querying the script)

Generalized term expansion strategy

Time range and data query

Preliminary notes (must be communicated to the user before displaying data)

Data display strategy (core)

A. Number of articles ≥ 10

B. Number of articles < 10 but > 0

C. Number of articles = 0

Display logic (pagination)

Subscription service inquiry (must be executed)

Recommended niche tracks (⚠️ Must be executed after displaying the data)

Self-check before output [must be executed]

Common command quick reference table

5. Use Cases

Use Case 1: Xiaohongshu Blogger Seeking Topic Inspiration

Use Case 2: Brand Market Research

Use Case 3: MCN Agency Creator Content Planning

Use Case 4: Scheduled Daily Push of Popular Notes

6. Project Architecture

Directory Structure

Tech Stack

Core Module Description

Resource Index

7. FAQ

Installation

Usage

Troubleshooting

Security Permission