Why it is worth attention

It offers a zero‑cost, dependency‑light way to query WeChat public‑account content, which is otherwise locked behind official APIs or paywalls, and it integrates easily into AI agent pipelines.

Who it is for

Developers building AI assistants or agents that need to reference WeChat articles
Researchers and journalists performing topic discovery on WeChat public accounts
Content curators aggregating articles from multiple WeChat sources

Use cases

Automatically fetch the latest articles for a given keyword during agentic research
Build a local archive of WeChat articles for offline analysis
Supplement fact‑checking or background research with Chinese social‑media content

Strengths

No API key, authentication, or platform coupling – works with any runtime that can run Node.js
Structured output (title, URL, summary, timestamps, source account) for easy parsing
Optional real‑URL resolution converts Sogou redirects to direct mp.weixin.qq.com links
Minimal dependencies – only requires cheerio beyond Node.js 18+

Considerations

Subject to Sogou’s anti‑bot rate limiting; intermittent empty results or blocked requests
URL resolution via -r flag is inconsistent under anti‑spider policies
Not intended for large‑scale commercial crawling – excessive use may result in IP blocks

README quick start

[!IMPORTANT] This repository is a generated compatibility mirror. The editable source, Issues, and contributions live in zjp1997720/zhijian-skills.

WeChat Article Search

Search WeChat public-account articles by keyword and return structured evidence without an API key.

简体中文 · Canonical source · Standalone mirror

Use it for topic discovery when you know the keyword but not which WeChat public account published the useful article.

Agent Install

npx skills add zjp1997720/wechat-article-search -g -a codex --skill wechat-article-search -y

Requirements

Node.js 18+ (tested on Node 20)
One npm dependency: cheerio. Run npm install inside the skill folder after install.

What It Does

Keyword search across WeChat public accounts via Sogou WeChat Search — returns 1–50 articles per query.
Structured output: title, URL, summary, publish datetime, date text, relative time, source account name.
Optional real-URL resolution (-r): converts Sogou redirect links into mp.weixin.qq.com direct links when reachable.
Optional file output (-o): writes JSON to disk for archival.

How It Works

The skill drives a single self-contained Node.js script (scripts/search_wechat.js) that queries Sogou WeChat Search (weixin.sogou.com), parses the result HTML with cheerio, and emits structured JSON to stdout. No API keys, no MCP tools, no platform coupling — it works in any agent runtime that can run node.

Example Requests

Search WeChat articles about "Loop Engineering", give me 10.

搜一下"AI培训"相关的公众号文章，要 5 条，保存到 result.json。

CLI Usage

node scripts/search_wechat.js "" [-n ] [-o ] [-r]

Flag	Default	Description
`query`	required	Search keyword
`-n, --num`	10	Number of results (max 50)
`-o, --output`	stdout	Write JSON to a file
`-r, --resolve-url`	off	Resolve real `mp.weixin.qq.com` URLs (slower, may fail under anti-bot)

First run: npm install in the skill folder to pull cheerio.

Safety & Limits

Uses public Sogou WeChat Search as the data source. Anti-bot rate limiting can intermittently return empty results or block URL resolution — retry with a different keyword or wait.
-r URL resolution succeeds

Description

Search WeChat public account articles by keyword via Sogou WeChat Search. Returns structured JSON — no API key required.

Related repositories

Similar projects matched by category, topics, and programming language.

7-e1even

Featured

learn-agent

A collection of notes on building coding agents, derived from the production development of the desktop agent Reina, with each mechanism simplified into a zero-dependency, single-file Node.js demo.

AI & Machine LearningLarge Language Models

218

S40911120

Featured

recensa

Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.

AI & Machine LearningLarge Language Models

bjan

Featured

claudemux

Claudemux is a lightweight, dependency-minimal message bus that lets multiple Claude Code sessions communicate in real-time over tmux, enabling one session to ask another a question and receive the answer without manual intervention.

AI & Machine LearningAI Agents