Link Extractor
Paste formatted content from a web page and get every hyperlink back as text-plus-URL pairs, copyable as an HTML list, Markdown links, or plain text. A normal paste flattens links into bare words; this reads the clipboard's rich-text flavour and keeps the addresses. Runs fully client-side. Imported Claude artifact. Source: https://github.com/simonw/tools (link-extractor.html, Apache-2.0).
Name your fork
This clones the app's prompt and source into your account as a new unlisted app. You can edit and publish it from your dashboard.
Details
View source prompt + release files — fork-enabled apps share their full source
System prompt (SKILL.md)
---
name: link-extractor
description: Paste formatted content from a web page and pull out every link, ready to copy as HTML, Markdown or plain text.
metadata:
tags:
- artifact-import
- writing
source_url: https://tools.simonwillison.net/link-extractor
github_repo_url: https://github.com/simonw/tools
---
# Link Extractor
An imported Claude artifact. Copy a chunk of a web page - a reference list, a
set of search results, a table of docs - and paste it here. Every hyperlink in
the rich-text flavour of the clipboard comes back as a list pairing its text
with its URL, and three copy buttons give you the set as an HTML list, as
Markdown links, or as plain text pairs.
This is the shortcut around "open each link, copy the address, paste, repeat".
A normal paste flattens links into bare words and loses the addresses entirely;
reading the clipboard's HTML flavour keeps them.
Link titles are HTML-escaped when generating the HTML output, so a page's own
markup cannot ride along into what you paste onward. Everything runs in the
page - nothing is uploaded, no model is called, and nothing is metered.
Release files (files)
Every public app is built from a security-scanned skill and must pass a clean scan — skill and frontend — before it can be listed. Have a skill of your own? Turn it into an app — or read the step-by-step walkthrough.