Skip to main content
View on GitHub → Clean web page extraction. Turn one or more public URLs into readable text with Tavily Extract through AIsa.

​
Install

Start a new agent session after installing so the skill loads.

​
What can agents do with it?

Article extraction

Pull readable article text from a public URL.

Document review

Extract source text before analysis.

Citation prep

Keep source content attached to summaries.

Research cleanup

Remove page chrome and keep useful content.

​
Setup

This skill requires the AISA_API_KEY environment variable. When installed as a Claude plugin, the key is configured via the plugin’s userConfig.

​
Usage

Run the search client with the extract subcommand:

​
Arguments

​
Examples

​
Output

For each URL, the script prints:
  • URL — The source URL
  • Content — Clean extracted text (up to 3000 characters per page)

​
When to Use

Use this skill when the user provides a URL and wants to read or analyze its content, or when you need to fetch the full text of an article found via search. This is the best tool for “read this page” or “summarize this URL” requests.

​
Get started

  1. Sign up at aisa.one and create an API key in the console.
  2. Set it in your shell: export AISA_API_KEY="your-key".
  3. Install the skill with one of the commands under Install, then start a new agent session.

Tavily Search

Search the web before extracting sources.

AIsa Tavily Search

Combined search and extraction workflow.

Tavily Extract API

Endpoint reference for extraction.