← Back to Skills Marketplace
rwonly

URL to Markdown

by Rex Wang · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
34
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install url2md
Description
Convert HTML web pages from HTTP/HTTPS URLs to clean, readable Markdown files with optional batch processing and formatting features.
README (SKILL.md)

Url2md

Convert web pages to clean, readable Markdown.

Quick Start

Single URL

python3 scripts/url2md.py https://example.com/article

Output to a file:

python3 scripts/url2md.py https://example.com/article -o article.md

Batch Conversion

Create a file with URLs (one per line):

https://example.com/article-1
https://example.com/article-2
https://example.com/article-3

Convert all and save to a directory:

python3 scripts/url2md.py -f urls.txt -d ./markdown_files/

Features

  • No dependencies: Uses only Python standard library (urllib, html.parser)
  • Title extraction: Automatically adds page title as H1
  • Link resolution: Converts relative URLs to absolute
  • Basic formatting: Headings, paragraphs, lists, links, images, code blocks, tables
  • Noise removal: Strips scripts, styles, navigation, footers, and other boilerplate

Script Reference

scripts/url2md.py

Usage:

url2md.py [url] [options]

Options:

Option Description
url Single URL to convert
-o, --output Output file (default: stdout)
-f, --file File containing URLs to convert
-d, --dir Output directory for batch conversion
--no-title Skip adding page title as H1
--timeout Request timeout in seconds (default: 30)
-v, --version Show version

Examples:

# Single URL to stdout
python3 scripts/url2md.py https://docs.python.org/3

# Save to file
python3 scripts/url2md.py https://docs.python.org/3 -o python-docs.md

# Batch with custom timeout
python3 scripts/url2md.py -f urls.txt -d ./output/ --timeout 60

# Skip title
python3 scripts/url2md.py https://example.com --no-title

When to Use

  • Converting documentation pages to Markdown for local reference
  • Archiving web articles as text files
  • Building static content from dynamic sources
  • Extracting readable content when browser tools are unavailable
  • Batch processing a list of URLs

Limitations

  • Converts static HTML only; does not execute JavaScript
  • Complex layouts (multi-column, heavy CSS) may lose structural fidelity
  • Login-required or paywalled content requires authentication tokens
  • Rate-limited sites may block repeated requests
Usage Guidance
This skill is reasonable to use for URL-to-Markdown conversion. Before installing or invoking it, review the included script, run it only on intended URLs, avoid embedding secrets in URLs, choose output paths carefully, and treat generated Markdown from websites as untrusted content.
Capability Analysis
Type: OpenClaw Skill Name: url2md Version: 1.0.0 The url2md skill is a straightforward utility for converting web pages to Markdown format using only Python's standard library. The core logic in `scripts/url2md.py` uses `urllib.request` to fetch HTML and `html.parser` to process it, with no external dependencies, obfuscation, or evidence of malicious intent such as data exfiltration or unauthorized command execution.
Capability Assessment
Purpose & Capability
The SKILL.md, README, and visible Python code consistently describe and implement converting web pages to Markdown, including single-URL and batch modes.
Instruction Scope
The skill tells the agent/user to run a local Python script on supplied URLs; this is purpose-aligned, but use should remain tied to explicit URL conversion tasks.
Install Mechanism
There is no installer or dependency download, and the visible code uses Python standard-library modules. Provenance is limited because the source is unknown/homepage none, and the provided script artifact is marked truncated, so confidence is medium rather than high.
Credentials
Network access and local file reads/writes are proportionate for URL fetching, batch URL lists, and Markdown output, but users should choose URLs and output paths deliberately.
Persistence & Privilege
The script can persist fetched web content as Markdown files, but there is no evidence of background persistence, privilege escalation, credential storage, or autonomous behavior outside the conversion task.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install url2md
  3. After installation, invoke the skill by name or use /url2md
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of url2md: convert any web page to clean, readable Markdown. - Supports single URLs and batch processing from URL lists. - Outputs can be directed to file or directory; title extraction as H1 included by default. - Handles standard Markdown formatting (headings, lists, links, images, code blocks, tables). - Strips boilerplate content including scripts, styles, navigation, and footers. - Requires no third-party dependencies; uses only Python standard library.
Metadata
Slug url2md
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is URL to Markdown?

Convert HTML web pages from HTTP/HTTPS URLs to clean, readable Markdown files with optional batch processing and formatting features. It is an AI Agent Skill for Claude Code / OpenClaw, with 34 downloads so far.

How do I install URL to Markdown?

Run "/install url2md" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is URL to Markdown free?

Yes, URL to Markdown is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does URL to Markdown support?

URL to Markdown is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created URL to Markdown?

It is built and maintained by Rex Wang (@rwonly); the current version is v1.0.0.

💬 Comments