WeChat Article Parser for Openclaw

A high-performance utility designed to parse WeChat Official Account articles and extract structured summaries without losing critical context or data.

oldjie
v1.0.0
May 1, 2026
2
659
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install wechat-article-parser-oldjie

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install wechat-article-parser-oldjie using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is WeChat Article Parser?

The WeChat Article Parser is a specialized tool within the Openclaw Skills ecosystem tailored for developers and researchers who need to digest content from the WeChat ecosystem. It bypasses the complexity of manual reading by programmatically fetching article content, preserving essential nuances such as timelines, pricing, and logical arguments while filtering out fluff.

This skill is particularly adept at handling various content types, from technical briefings and product launches to historical narratives. By leveraging automated browser tech, it ensures that even dynamic or restricted content is captured accurately, providing a clean Markdown-ready summary for further AI analysis or archival.

WeChat Article Parser Use Cases

  • Rapidly summarizing lengthy WeChat Official Account posts for research.
  • Extracting key technical specifications or pricing from product launch articles.
  • Tracking policy changes and event backgrounds from official news updates.
  • Archiving WeChat content into local knowledge bases with structured metadata.
  • Automating information gathering for competitive analysis or industry monitoring.

How WeChat Article Parser Works

  1. The user provides a valid WeChat Official Account article URL to the AI agent.
  2. The skill triggers a Node.js script located in the local skill directory.
  3. A headless browser (Playwright) loads the URL to ensure all dynamic elements are rendered.
  4. Cheerio parses the HTML structure to extract the primary text, links, and media references.
  5. The AI agent processes the raw text according to specific output principles, categorizing the content (e.g., event, product launch, or story) to ensure the most relevant details are highlighted.
  6. A structured Markdown summary is returned, including core points, references, and critical data like dates or prices.

WeChat Article Parser Setup

To integrate this parser into your Openclaw Skills environment, ensure you have Node.js installed and follow these steps:

# Navigate to the skill directory
cd ./.claude/skills/wechat-article-parser/scripts

# Install required dependencies
npm install playwright cheerio

# Execute the parser with a target URL
node fetch-wechat.js <WECHAT_ARTICLE_URL>

WeChat Article Parser Data Schema & Taxonomy

The skill processes data into a structured format to maintain logical consistency:

Feature Description
Core Points High-level summary of the article's main message.
Contextual Data Specific dates, names, percentages, and amounts extracted from the text.
Reference Links A dedicated section for official service links or cited URLs.
Classification Content is tagged as News, Product, Logical Argument, or Story to dictate summary style.
Metadata Includes original author, publication date (if available), and price information.

WeChat Article Parser Advanced Features

  • Adaptive Summarization: Automatically switches output logic based on detected article genre (e.g., keeping humor in reviews while remaining clinical for tech specs).
  • Preservation of Causality: Specifically designed to map "Before vs. After" scenarios in policy or event-based articles.
  • Link Verification: Extracts and labels official service links specifically mentioned in the text for high-utility output.
  • No-Hallucination Policy: Strict internal guidelines prevent the generation of data not explicitly found in the source HTML.
  • Multi-Agent Compatibility: Can be used as a pre-processing step for Openclaw Skills workflows involving translation or deep-dive research agents.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*