just-scrape Skill for Claude: What It Does and How to Install It

Lets Claude search, scrape, crawl, extract data from and monitor web pages through the ScrapeGraph AI command line tool.

Installs: 245K; on skills.sh
Stars: 74; on GitHub
Updated: Sep 2026; last repo commit

just-scrape teaches Claude to use the just-scrape command line tool from ScrapeGraph AI. Claude escalates in order: search when there is no URL, scrape a known URL, extract structured JSON with a prompt and optional schema, crawl a site section, and monitor a page for changes with optional webhooks.

The skill is only instructions. You also need the just-scrape CLI installed and a ScrapeGraph AI API key in SGAI_API_KEY, and every operation uses ScrapeGraph credits. Results are saved to a .just-scrape/ folder in your project by default, not pasted into the chat. If you are adding ScrapeGraph to app code, SKILL.md says to use the SDK and API docs instead.

Good for

Developers collecting data from websites
Researchers pulling structured data from pages
Teams tracking page changes

Install just-scrape

Claude Code

Copy this prompt.

Install the just-scrape skill in Claude Code. Run this command:

npm install -g just-scrape@latest
npx skills add https://github.com/ScrapeGraphAI/just-scrape --skill just-scrape

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js, ScrapeGraph AI API key.

Both steps are needed. The skill only gives Claude instructions; the just-scrape CLI does the scraping. Run the CLI check from the skill (validate and credits) after you set the key.

From the project README. Source.

What's in the skill

When it loads

Search, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON from a site, crawl documentation or site sections, monitor a page for changes, inspect request history, check ScrapeGraph credits, or validate API setup.

Sections in SKILL.md

Prerequisites
Workflow
Commands
Search
Scrape
Extract
Crawl
Monitor
History
Credits and Validate
When to Load References
Output & Organization
Working with Results
Parallelization
Credit Usage
Troubleshooting

Key facts

Author: scrapegraphai
Repo: scrapegraphai/just-scrape (skills/just-scrape)
Installs on skills.sh: 245,011 (Nov 2026)
GitHub stars: 74 (Nov 2026)
License: MIT
Last repo commit: Sep 21, 2026
Files in the skill folder: 1 including SKILL.md
skills.sh audits: Gen Agent Trust Hub: pass, Socket: pass, Snyk: warn
Needs: The just-scrape CLI and a ScrapeGraph AI API key (SGAI_API_KEY)
Output: Saved to .just-scrape/ unless you ask for it in the chat

What it includes

Finds pages when you have no URL; can extract structured data from results
Runs code · search
Gets a known URL as markdown, html, screenshot, links, images, summary, branding or JSON
Runs code · scrape
Pulls structured JSON from a URL with a prompt and optional schema
Runs code · extract
Collects many pages from a site section, with page and depth limits
Runs code · crawl
Creates scheduled page checks with optional webhooks; list, update, pause, resume, delete
Runs code · monitor
Lists past requests and their results
Runs code · history
Checks your credit balance and that your API key works
Runs code · credits and validate

From the official docs

Permissions

Medium risk

Claude sends URLs and prompts to the paid ScrapeGraph AI API, spends credits, can install the CLI globally and can create scheduled monitors. Ask Claude to check your credit balance before bulk work.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Every operation spends ScrapeGraph credits
SKILL.md says stealth, branding, crawling many pages, JS rendering and repeated extraction can increase cost, and to check credits before bulk work. Its setup check sends a small scrape of example.com and a search before real work.
It creates scheduled monitors
monitor create sets an interval and optional webhook URL. SKILL.md lists monitor list, pause, resume and delete; use them to review monitors when you are done.
It runs shell commands and writes files
If the CLI is missing, SKILL.md runs npm install -g just-scrape@latest. Results go to .just-scrape/ by shell redirection, and SKILL.md tells Claude to add that folder to .gitignore.
Scraped pages are untrusted input
SKILL.md tells Claude to treat page text as data, not instructions, and not to follow links, fill forms or run commands based only on scraped content.
Cookie and header options carry secrets
SKILL.md treats --headers and --cookies values as secret material and says to read them from environment variables.

Technical details

Talks to	ScrapeGraph AI API (default https://v2-api.scrapegraphai.com)

Questions

How do I install just-scrape?

Use the install box above. It installs both the CLI and the skill, since the skill alone cannot scrape anything.

Does it need an API key?

Yes. SKILL.md says the CLI needs SGAI_API_KEY for ScrapeGraph AI requests. You can set it as an environment variable, in a .env file, in ~/.scrapegraphai/config.json or at the CLI prompt.

What does it cost?

Every operation uses ScrapeGraph credits. SKILL.md says stealth mode, branding, crawling many pages, JS rendering and repeated extraction can raise the cost. Ask Claude to check credits before bulk work.

Is it safe?

Scraped pages are third-party content, and SKILL.md tells Claude to treat them as data, not instructions. The skill runs shell commands: it can install the CLI globally with npm and write results and a .gitignore entry in your project. Its security section says to treat --cookies and --headers values as secret material and read them from environment variables. Monitors are scheduled checks you create with monitor create; SKILL.md lists pause, resume and delete for them.

When should I not use it?

SKILL.md says to use the ScrapeGraph SDK or API docs when you are building scraping into application code, adding the key to a project, or choosing endpoints for product code.

Information

updated Nov 2, 2026

Repository: scrapegraphai/just-scrape
Folder: skills/just-scrape

scrapegraphai/just-scrape skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 2

just-scrape README · github.com
just-scrape SKILL.md · github.com