skills.rest
beatai-org
beatai-orgOFFICIAL
Explore all skills by this author →
GitHub

x-fetch

Converts X posts and long-form articles to Markdown with local image assets.

4.7k|260|Updated Dec 29, 2021
Search Tags:#web scraping#x-twitter#markdown extraction#chrome automation#image localization#tweet fetching#thread stitching
One-click install
npx skills add https://github.com/beatai-org/beatai --skill x-fetch
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: x-fetch
Source: https://github.com/beatai-org/beatai/tree/main/.claude/skills/x-fetch
Command: npx skills add https://github.com/beatai-org/beatai --skill x-fetch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, yaml, and includes scripts (resource) components.

What problem does it solve?

This Skill eliminates the manual effort of saving X (Twitter) posts and threads by URL, turning a hard-to-archive webpage into structured Markdown and locally bundled assets.

Core Features & Use Cases

  • Tweet / thread downloader: Fetches the OP author’s continuation thread starting from a status URL, with each tweet separated into sections.
  • X Article (long-form) parser: Detects long-form article rendering and converts Draft.js rich text into Markdown while preserving headings, bold/italic, links, lists, and blockquotes.
  • Asset localization: Downloads images from pbs.twimg.com and rewrites them to local relative paths so the result works offline.
  • Safety/contract behavior: Preserves the original language verbatim and leaves translation, summarization, and destination decisions to the orchestrator.

Quick Start

Set RAW_DIR to an absolute output directory and run x-fetch to fetch a tweet URL into Markdown plus an assets folder for offline viewing.

Frequently Asked Questions about x-fetch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I download X Twitter threads and convert them to Markdown?▼

To download an X Twitter thread as Markdown, you provide a status URL and the tool uses real Chrome automation to fetch the thread. It separates each tweet into distinct Markdown sections for structured, offline-ready reading.

Can I parse X long-form articles into clean Markdown?▼

Yes, you can parse X long-form articles into clean Markdown by detecting the article rendering mode. The tool converts Draft.js rich text into Markdown while preserving headings, bold and italic text, links, lists, and blockquotes.

Does web scraping tweets with Chrome automation localize images for offline viewing?▼

Yes, web scraping tweets with Chrome automation localizes images for offline viewing. It downloads images from pbs.twimg.com and rewrites the image sources to local relative paths within your output assets folder.

Do I need to set an absolute output directory path for tweet fetching?▼

Yes, you must set an absolute output directory path for tweet fetching. You need to define RAW_DIR as an absolute path with no default value to ensure the extracted Markdown and localized image assets are correctly saved.

Why does my tweet scraping output preserve the original language without translation?▼

Tweet scraping output preserves the original language without translation due to built-in safety behavior. It leaves translation, summarization, and destination routing decisions entirely to the downstream orchestrator pipeline.

Related Skills

Explore More Content & Communication Skills→
krishna-cyberkrishna-cyber

dev-browser

Connect to a persistent Chrome instance for fallback browser automation.

Community
Advanced
escapevelocitylabsescapevelocitylabs

research-restaurants-local-cuisine

Cross-reference local food research with live web data to validate restaurants serving signature dishes.

Official
Advanced
CrumbgrabberCrumbgrabber
3

webapp-testing

Automate local web application testing with Python Playwright scripts.

Community
Intermediate
aehyokaehyok
100

post-to-x

Post text, images, and Markdown articles to X via Chrome CDP.

Community
Advanced