📝 Introduction
Enter a keyword to search for WeChat Official Account blogger accounts, with the account name, account ID, and account bio all visible at a glance.
✨ Features
| Feature Module | Capability Description | Core Value |
|---|---|---|
| Keyword Search | Enter a keyword to search for WeChat Official Account blogger accounts | Precisely discover WeChat Official Accounts in the target field |
| Data Display | Display account name, account ID, and account bio | Quickly understand account positioning and content direction |
| Page Browsing | Display multiple results per page, supports browsing through multiple pages | Never miss a single account |
🎯 Target Users
- 🔍 Content Creators — Find WeChat Official Accounts in the same field and study the content direction and operation approach of benchmark accounts.
- 📊 Operations / Data Analysis — Quickly figure out which top accounts a certain category has on WeChat Official Accounts and grasp the competitive landscape.
- 🏢 Brands / MCNs — Screen potential partner accounts, evaluate account value by field, and support partnership decisions.
- 📝 Copywriting Planners — Search WeChat Official Accounts in niche tracks to find topic inspiration and content references.
🔑 Authentication
Get API Key
Please go to RedFox Hub to get the API KEY
Configure API Key
Option 1: Taking 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..."
🔄 Workflow
Step 1: Understand user intent and extract keywords
⚠️ Core Rule: Semantic understanding takes priority; prioritize extracting niche direction words rather than generalized broad category words
1. Extract keywords
- Extract niche keywords of 2 to 6 characters from the user's description
- Filter out redundant modifiers: When the user says "xx blogger", "xx WeChat Official Account", "xx account", or "xx influencer", the search keyword should take only the core part xx, removing category modifiers such as "blogger", "WeChat Official Account", "account", and "influencer" at the end. For example, "finance blogger" → search "finance", "technology WeChat Official Account" → search "technology"
- If the user's intent is vague (such as "help me search for WeChat Official Accounts"), proactively ask: "Which direction or field of WeChat Official Accounts would you like to search for?"
- Do not make arbitrary guesses and call the script when the user has not provided a keyword
2. Identify the page number parameter(use the default value when the user does not specify one)
- Page number(
--page): Default1- When the user mentions "next page" or "page 2" → corresponding page number
- When the user mentions "previous page" → current page - 1
- When no page number is mentioned →
1(default)
Step 2: Call the search script
python3 ~/.agents/skills/wechat-account-search/scripts/search_gzh_account.py "<关键词>" [--page 页码]
Parameter description:
| Parameter | Optional values | Meaning |
|---|---|---|
| keyword | Any string | Search keyword |
--page |
Positive integer | Page number, starting from 1 (default 1) |
--cursor |
Integer | Pagination cursor, obtained from the cursor field in the JSON output |
The script outputs in JSON format:
| Field | Description |
|---|---|
accounts |
List of matched accounts (maintaining the original order of the API) |
page |
Current page number |
has_next |
Whether there is a next page (true/false) |
total |
Number of items returned on the current page |
cursor |
Pagination cursor value, for use in the next page query |
⚠️ Complete data reading rules: When the JSON data output by the script is large, the terminal may truncate the middle content and display // This is the omitted part. In this case, you must read the complete file path indicated in the Bash output (e.g., Full output saved to: /path/to/file), use the Read tool to obtain the complete JSON before generating the table, ensuring that all field data is completely visible and no records are omitted.
Fields for each account:
| Field | Description |
|---|---|
nickname |
Account name |
account_id |
Account ID |
introduction |
Account description |
profile_url |
Account redirect link (has a value when account_id is non-empty, already URL-encoded) |
Step 3: Determine the result and display it
Case A: accounts count > 0 (matching results found)
A1. Inform the user of the query scope
📊 Keyword "XXX" found Nofficial account accounts (page {page}), the detailed data is as follows:
A2. Render a Markdown table (display all)
| # | 账号名称 | 账号ID | 账号简介 |
| --- | ---------------- | --------------- | -------------------------------------------------- |
| 1 | [占豪](https://open.weixin.qq.com/qr/code?username=zhanhao668) | zhanhao668 | 国际局势·财经投资·国学哲学丨连续6年新媒体百大人物... |
Account name rules: Display in full, do not truncate
Account name link rules: When profile_url is non-empty, the account name includes a clickable redirect [昵称](profile_url); when profile_url is empty, the account name displays only plain text, and redirection is disabled
Account ID rules: Display the original value in full
Description rules: Display in full, do not truncate
A3. Pagination prompt (⚠️ immediately after the table, cannot be omitted, must be output every time)
- If
has_nextis true:
📄 Currently on page {page} . Reply "next page" to continue viewing.
- If
has_nextis false (already the last page):
📄 Currently on page {page} , there is no more data.
"Next page" invocation rules when paginating: If the user replies "next page", you must extract the cursor value from the previous round's JSON output, and call the script:
python3 ~/.agents/skills/wechat-account-search/scripts/search_gzh_account.py "<关键词>" --page {page+1} --cursor {上一轮返回的cursor值}
⚠️ A1~A3 are all indispensable and must be completed consecutively in the same round of output. If A3 is missing, it is considered an execution error and the output must be supplemented again.
Case B: accounts count = 0 (no matching results)
B1. Apology prompt
😔 Sorry, no official account accounts directly related to "XXX" were found.
⚠️ B1 must be completed in the same round of output and must not be interrupted.
Step 4: End output
After all content has been displayed, do not wait, end the output immediately.