Build and run AI-generated Bright Data scrapers from the terminal via `bdata scraper create` and `bdata scraper run`. Use this skill whenever the user wants to generate a scraper from a natural-language description, build a custom scraper without writing code, turn a URL + plain-English description into a reusable scraper, or run an existing Bright Data collector against a URL and get the data back. Triggers on phrases like 'build me a scraper for', 'create a scraper that extracts', 'generate a scraper from a description', 'turn this URL into a scraper', 'run this scraper on', 'run my collector', 'scraper studio', `scraper create`, `scraper run`, `collector_id`, `automate_template`, or `/dca/`. Covers the AI flow (template create → trigger AI generation → poll progress), the run flow (async + poll by default, `--sync` for fast pages), and the silent auto-fallback to the batch endpoint when a URL expands past the realtime page limit. Requires the Bright Data CLI.
This skill does not declare a tool allowlist. The agent host applies whatever default tools are available at runtime.
SKILL.md / Manifest
https://raw.githubusercontent.com/brightdata/skills/main/skills/scraper-studio/SKILL.mdRegistry
github (via claudemarketplaces.com)