Skip to content
mcp/skillhub

Agent Skill

Just Scrape skill

just-scrapeScrapeGraphAI/just-scrapeskills/just-scrape/SKILL.md

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.

72MIT

always on

80 tokname + description

once used

3,004 tokSKILL.md body

bundled files

0

installs

245kskills.sh

Install the Just Scrape skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/ScrapeGraphAI/just-scrape --skill just-scrape

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/ScrapeGraphAI/just-scrape.git /tmp/just-scrape
mkdir -p ~/.claude/skills
cp -R /tmp/just-scrape/skills/just-scrape ~/.claude/skills/just-scrape

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description80 tok
When the agent uses itThe SKILL.md instructions3,004 tok
Only if openedNo bundled files—

Until it is used, just-scrape costs about 17× less than the median MCP server we measured (1,362 tokens on every turn). Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Pre-approved tools (allowed-tools): Bash. The agent can use these without asking while the skill is active.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • just-scrape CLI
  • 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
  • Security
  • Environment Variables