Brightdata Scraper Studio Skill — Data skill for Claude Code

Bright Data Scraper Studio — Claude Code skill

A skill that teaches Claude Code, Cursor or Codex how to build, run and self-heal custom web scrapers for any public site, entirely from the terminal.

Point your coding agent at a URL, describe the data you want in plain English, and get back a working scraper you own — plus a Collector ID that is already a live API endpoint.

**Try Bright Data:** [brdta.com/iss25](https://brdta.com/iss25) — get **$25 of credit** to run everything in this skill.

*That's my affiliate link. It costs you nothing extra and helps support work like this.*

Install

**Claude Code**

git clone https://github.com/IncomeStreamSurfer/brightdata-scraper-studio-skill.git ~/.claude/skills/brightdata-scraper-studio

**opencode**

git clone https://github.com/IncomeStreamSurfer/brightdata-scraper-studio-skill.git ~/.config/opencode/skills/brightdata-scraper-studio

Either way it's picked up on the next session — no config, no restart. Same `SKILL.md`, same frontmatter, both agents read it as-is.

**Already have it in Claude Code?** Symlink instead of cloning twice, so there's one source of truth to edit:

ln -s ~/.claude/skills/brightdata-scraper-studio ~/.config/opencode/skills/brightdata-scraper-studio

**Cursor / Codex:** clone anywhere and point your rules file at `SKILL.md`, or copy its contents into `.cursor/rules` or `AGENTS.md`.

**Verify it loaded:** ask your agent *"what do you know about Bright Data Scraper Studio?"* — it should reference the five scraper types without searching the web.

What it covers

• Setup in three commands — runs via npx, so no global install, no sudo, no EACCES, no node version manager fights
• Picking the right scraper type — PDP, Discovery, Discovery + PDP, Search, and Sitemap, with the rule for naming the shape explicitly so you don't pay the build time twice
• The build loop — create → run → heal → approve
• Self-healing — whe