← All skills

scrape

97 / 100 · Low risk

Fine to try. Some of what it can do is expected: a data skill usually connects to databases or online services with your credentials.

By brightdata/skills (GitHub) · data · 271 stars · scanned at commit 103b4cf

Use when the user wants to scrape or extract structured data from any site: profiles, posts, products, reviews, prices, followers, job or property listings. Also for building a scraper, crawling a site for data, discovery by keyword or category, asks that say "data fields" or "recurring", or that name a dataset_id, snapshot_id, Web Scraper API, or Scraper Studio. Not the page itself (use fetch), not a search query (use search), not cost or credits (use billing).

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'scrape' ] || [ -L ~/.agents/skills/'scrape' ]; then echo 'A skill folder named scrape already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/brightdata/skills' "$d" && git -C "$d" checkout --quiet '103b4cf933618ffa2fc85281e45dce60421e180d' -- 'skills/scrape' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/scrape' ~/.agents/skills/'scrape' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'scrape' ~/.claude/skills/'scrape' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for brightdata/skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/brightdata/skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/brightdata/skills/)

Score history