Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Creating and running scrapers from a description v1.0.0

Use this resource to generate a scraper from a description and run it on URLs

New

  • 559 downloads
  • 219 likes
  • 147 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install generate-scraper-from-description

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent creates the scraper from the description, keeps the collector_id returned, then runs that collector on one or more URLs. You get extracted data that can be reused in a batch.

Mostly picked by

Updated November 2, 2026

Card for the “Creating and running scrapers from a description” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: create and run commands, the collector_id role and run modes
  • references/api-flow.md, prompts.md and recipes.md: API flow, prompt wording and recipes

Good fit for

  • You want a custom scraper without writing code
  • You must apply the same collector to a list of URLs

Not for

    Tags

    • scraper
    • generation
    • collector

    About

    You say

    “Build a scraper that extracts name, price and rating from each listing on this page.”

    Card for the “Creating and running scrapers from a description” skill

    Skill published by brightdata under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to generate a scraper from a description and run it on URLs
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/api-flow.md7.7 KB
    • references/prompts.md5 KB
    • references/recipes.md6.2 KB
    • SKILL.md23.2 KB

    Origin and licence

    Listed unmodified

    Author
    brightdata
    Source
    github.com/brightdata/skills/tree/37503c1ba31056370323a9d5ba88dd003a280008/skills/scraper-studio
    Licence
    MIT

    Notice

    « scraper-studio » (brightdata, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.