read
Fetches any URL or PDF as clean Markdown for reading, quoting, citation, or downstream work. Handles paywalls, JS-heavy pages, X/Twitter, and Chinese platforms via proxy cascade. Not for local text files already in the repo.
Security Assessment
Detected risks:
About read
The 'read' skill is designed to fetch content from any URL or PDF and convert it into clean Markdown format, making it easier for users to read, quote, and cite information. This skill addresses the common challenges associated with accessing online content, particularly from paywalled sites or JavaScript-heavy pages, by utilizing a proxy cascade to bypass these barriers. It ensures that users can obtain the information they need without the hassle of navigating through complex web pages or dealing with formatting issues.
FAQ
How do I use the 'read' skill?
You can invoke the skill by providing any URL or PDF link, and it will fetch the content in Markdown format.
What types of content can be fetched?
The skill can fetch content from URLs, PDFs, and specific platforms like Twitter and WeChat.
Are there any limitations on the content I can fetch?
Yes, the skill does not support local text files already in the repository and may encounter issues with paywalled content.
Can I save the fetched content?
Yes, you can save the content as a Markdown file under certain conditions, such as explicitly asking to save or if called from within a specific context.
What happens if the content is behind a paywall?
The skill will inspect the content for paywall signals and will not save the login page if it encounters one.
Install read
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
tw93/waza