A powerful extraction tool for X/Twitter that captures standard tweets, long-form X Articles, and external content behind shortened URLs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install x-article-extract
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install x-article-extract 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 X Article Extract?
The X Article Extract skill is a specialized tool designed for the Openclaw Skills ecosystem to handle the complexities of retrieving data from X/Twitter. It goes beyond simple text scraping by providing three distinct extraction methods: direct tweet parsing via xreach, headless browser rendering for long-form X Articles using Playwright, and external web scraping for shared links via the Firecrawl API.
This skill ensures that developers and researchers can access high-fidelity data, including full text, author details, and real-time engagement metrics like likes, retweets, and bookmarks. By automating the bypass of shortened t.co links and handling session-based authentication, it transforms X into a structured data source for any AI agent or content workflow.
X Article Extract Use Cases
- Archiving long-form X Articles into personal knowledge bases like Obsidian.
- Monitoring social media engagement and viral metrics for specific accounts.
- Extracting content from external articles shared via Twitter without manual clicking.
- Building automated content pipelines that ingest X data into CMS or research tools.
- Resolving t.co shortened links to verify destination safety or relevance.
How X Article Extract Works
- The user provides an X/Twitter URL or a t.co link to the skill script.
- The system identifies the content type: standard tweet, long-form X Article, or an external link.
- For tweets, it utilizes xreach to fetch immediate metadata and media.
- For X Articles, it launches a headless Playwright browser to render and scrape the full text.
- For external links, it resolves the t.co redirect and uses Firecrawl to parse the destination page.
- The extracted data is structured into a JSON object containing title, author, engagement, and word count.
- Optionally, the data is ingested into a connected content factory or database.
X Article Extract Setup
To use this within your Openclaw Skills environment, ensure you have the required binaries and API keys configured.
# Install system dependencies
pip install playwright
python3 -m playwright install chromium
# Ensure xreach is authenticated
xreach auth extract --cookie-source chrome
# Set environment variables for external scraping
export FIRECRAWL_API_KEY='your_key_here'
export HTTPS_PROXY='your_proxy_url'
X Article Extract Data Schema & Taxonomy
The skill produces a structured JSON output with the following taxonomy:
| Field | Description | Example |
|---|---|---|
title |
The heading of the article or tweet snippet | "Breaking News..." |
author |
The X handle or display name of the creator | "@Openclaw" |
description |
The full text content extracted | "Full content body..." |
engagement |
Object containing views, likes, retweets, and bookmarks | {"likes": 120, ...} |
content_type |
Categorization: tweet, x_article, or external_page | "x_article" |
word_count |
Total count of words in the extracted text | 450 |
X Article Extract Advanced Features
- Multi-URL Support: Batch process multiple X links in a single execution command.
- Automatic Ingestion: Direct integration with ObsidianAdapter to save content to your local vault automatically.
- Fallback Mechanism: If Playwright fails for an X Article, the system automatically falls back to xreach thread analysis to recover context.
- Proxy Integration: Built-in support for HTTPS_PROXY to handle regional access restrictions smoothly.
- Engagement Scraping: Captures live interaction data alongside the static text content.
SKILL.md
Loading
Related Openclaw Skills
E-Commerce Advertising Planner
A professional-grade advertising architect that generates multi-channel campaign strategies, keyword research, and budget allocations for e-commerce brands.
AI News Generator
An automated workflow that scrapes 24-hour AI trends, performs deep analysis, and generates structured daily reports directly to your digital notes.
Yep Search
A zero-dependency Python tool for performing high-performance web searches using the independent Yep Search index.
Claw Browser Automation
A high-performance Rust-based headless browser automation CLI designed for AI agents to interact with web pages through structured commands.
docx-cn: Word Document Processing
A powerful toolkit for creating, reading, and editing Microsoft Word documents with precision using JavaScript and XML manipulation.
Agent Create Config
A comprehensive automation skill for creating, configuring, and deploying Openclaw employees and AI agents from scratch.
Featured*
