ClawHub

X Article Extractor

v1.0.0

AI-ready skill to extract long-form X (Twitter) articles and convert them into clean Markdown files using headless browser technology.

⭐ 0· 98·0 current·0 all-time
byLei@caol64

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for caol64/x-article-to-markdown.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "X Article Extractor" (caol64/x-article-to-markdown) from ClawHub.
Skill page: https://clawhub.ai/caol64/x-article-to-markdown
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install x-article-to-markdown

ClawHub CLI

Package manager switcher

npx clawhub@latest install x-article-to-markdown
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
The skill claims to extract long-form X articles using a headless browser; the SKILL.md directs the agent to install a package that provides a CLI (mdcli) and explains that Playwright/Chromium will be lazy-downloaded. These requirements are coherent with the stated purpose.
ℹ
Instruction Scope
The instructions tell the agent to run shell commands (pip install, mdcli) and to allow Playwright to download Chromium on first run. The instructions do not request unrelated files, credentials, or access to system config, but they do require outbound network access and will write binaries to disk during installation/runtime.
ℹ
Install Mechanism
There is no registry-level install spec (the skill is instruction-only) but SKILL.md asks the agent to pip install 'omni-article-markdown' and to rely on Playwright's automatic Chromium download. Pip/Playwright downloads are normal for this use case, but installing an external PyPI package and downloading a browser binary are operations with non-trivial risk if the package or mirrors are untrusted.
✓
Credentials
No environment variables, credentials, or special config paths are requested. The lack of secrets is proportionate to the stated task.
✓
Persistence & Privilege
The skill does not request permanent/global privileges (always:false) and does not modify other skills or system-wide settings. Autonomous invocation is allowed (platform default) but not excessive in itself.
Assessment
This skill appears to do what it says: it needs you to pip install a third‑party package and will download Playwright/Chromium at first run. Before installing or running it, verify the package/repo (https://github.com/caol64/omni-article-markdown is referenced), review the package source if possible, and prefer running in an isolated environment (container or VM) because pip packages can execute arbitrary code during install and headless browsers perform large downloads. Ensure the runtime environment allows outbound network access to x.com and Playwright mirrors, and avoid running this on systems with sensitive credentials or private data you wouldn't want exposed to a third‑party package.

Like a lobster shell, security has layers — review code before you run it.

latestvk978tak7hh8wxgndf4cfg75ed1844vfk
98downloads
0stars
1versions
Updated 3w ago
v1.0.0
MIT-0
Lei@caol64
latest
Download

X Article Extractor (Omni-Article)

A specialized skill designed for AI Agents to capture long-form "Articles" from X (formerly Twitter). It utilizes a headless browser to bypass basic access restrictions and produces structured Markdown.

Capabilities

  • Zero-Config Extraction: No Cookies, Tokens, or API Keys required.
  • On-Demand Browser Setup: Automatic lazy-loading of Playwright and Chromium core.
  • Asset Preservation: Maintains original image URLs within the Markdown.
  • Reference Handling: Automatically converts quoted posts into standard Markdown links.
  • Clean Output: Strips UI clutter, focusing solely on the article body.

Prerequisites & Installation

The tool manages its own browser dependencies. Simply install the package:

pip install omni-article-markdown

Important (First Run Only): The Playwright engine and Chromium core are lazy-loaded. They will be automatically downloaded and configured during the first execution. Expect a significant delay (1-3 minutes depending on bandwidth) during the initial run. Subsequent runs will be near-instant.

AI Agent Instructions

When to use this skill

Call this skill when a user provides an X (Twitter) URL and asks to "save," "read," "extract," or "convert" the long-form content.

Parameters

  • url (Required): The full X post/article URL.
  • --output-dir (Optional): Target directory for the .md file.

First-Run Strategy

If the environment is fresh, the Agent should inform the user: "I'm setting up the browser environment for the first time, this might take a minute..." to prevent the user from thinking the process has hung.

Usage Examples

Standard Extraction

# Basic command
mdcli https://x.com/elonmusk/status/1234567890

Save to Specific Directory

mdcli https://x.com/username/status/xxxx -s ./downloads/articles/

Troubleshooting for Agents

  • Extended Latency: If the command takes >60s on the first run, do not kill the process; it is likely downloading the Chromium core.
  • Network Error: Ensure the environment has internet access to both x.com and the Playwright binary mirrors.

GitHub Repository

caol64/omni-article-markdown

License

MIT

Comments

Loading comments...