datasets · brightdata — Claude Code skill: what it does, how to install
A skill for Claude Code that identifies available pre-collected datasets in the marketplace to replace manual scraping. It triggers when a large generic corpus is requested.
MIT 180 installs ★ 272 updated 2026-10-15
npx skills add brightdata/skills --skill datasets -a claude-codeWhat datasets does
The skill determines if a required data set is already available for purchase as a download. The agent verifies marketplace coverage, but does not execute payments or purchases. Financial decisions and final orders happen in the user's control panel at https://brightdata.com/cp/datasets/browse after reviewing field samples.
It applies only to generic data needs, such as one-time training sets or market research, where data a few months old suffices. If the task requires live inventory or specific input-based data, the agent redirects to the scrape skill. Verification involves up to four calls following the logic defined in references/marketplace.md.
When a user provides a dataset_id corresponding to a marketplace item, the skill clarifies that such records cannot be triggered as live jobs. It instead presents the options to purchase the download via the control panel or to scrape a defined target list using the scrape skill.
What it helps with
- find existing datasets for model training
- purchase pre-collected data for research
- check marketplace availability for large corpora
- avoid unnecessary scraping jobs
Example prompts for the agent
- Find if there is a ready-made dataset for "every US company with more than 50 staff"
- Check if this
dataset_idis available for download in the marketplace - I need a training set, can I buy this as a download?
How to install datasets
1Skills CLI (Vercel)
npx skills add brightdata/skills --skill datasets -a claude-code2Manually: put the files in place
~/.claude/skills/datasets/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/datasets/
1Skills CLI (Vercel)
npx skills add brightdata/skills --skill datasets -a codex2Manually: put the files in place
.agents/skills/datasets/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add brightdata/skills --skill datasets -a cursor2Manually: put the files in place
.cursor/skills/datasets/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install brightdata/skills skills/datasets2Manually: put the files in place
.github/skills/datasets/SKILL.md1Skills CLI (Vercel)
npx skills add brightdata/skills --skill datasets -a gemini-cli2Platform CLI
gemini skills install https://github.com/brightdata/skills --path skills/datasetsManually: put the files in place
.devin/skills/datasets/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add brightdata/skills --skill datasets -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about datasets
How to install datasets in Claude Code?
Run npx skills add brightdata/skills --skill datasets -a claude-code. The file will be available at ~/.claude/skills/datasets/SKILL.md.
What does datasets do?
It checks the marketplace to see if data has already been collected, saving time by suggesting a download instead of building a scraper.
What is required for datasets to work?
Users must have access to the control panel at https://brightdata.com/cp/datasets/browse to review data samples and complete the purchase process.
Source text
SKILL.md · MIT
---
name: datasets
description: Use when the data is already collected and sold as a download, a huge generic corpus needed once where a few months old is fine ("every US company with more than 50 staff", a one-time training set). Also when the user holds a dataset_id that turns out to be a marketplace row, or asks what a ready dataset costs. Not for fresh, specific, or recurring collection, which is scraping and belongs to the scrape skill.
---
# datasets
Buy the download instead of scraping. The Dataset Marketplace sells data that was already collected. Using it involves no scraping at all. The user buys a dataset and downloads it.
## When this is the answer
Three things must all be true. Anything less is a scraping job, not a purchase.
| Condition | Example that passes | Example that fails |
|---|---|---|
| A huge generic corpus, not specific inputs | "every US company with more than 50 staff" | "the follower count for instagram.com/nasa" |
| Needed once, or on a schedule a dataset subscription covers | a one-time training set | a nightly price feed |
| A few months old is fine | market research | live inventory |
Any one of them false and the answer is the `scrape` skill. Need it once, or on a schedule a dataset subscription covers, buy the dataset. Need it fresher, or for specific inputs, scrape it.
## The agent's job: check and route
The agent checks whether the marketplace covers the ask, then hands off. It does not buy. Buying moves money, so a person does it in the control panel at `https://brightdata.com/cp/datasets/browse`, on their own account, after looking at a sample and the field coverage. There is no reason for an agent to be in that loop.
Evidence costs up to four calls: three free reads and one probe. The probe starts nothing for a download for sale or for a scraper with a required input, but it can start a billed job on a scraper with no required input. The exact calls, and which ids are safe to probe, are in `references/marketplace.md`. When the check hits, say it in one line:
> Bright Data already sells a dataset that looks like this, priced per record, so buying the download may be cheaper and faster than scraping it. Browse it at brightdata.com/cp/datasets/browse. Say the word and I will scrape it instead.
Then stop and wait. Do not build a scraper in the background as a hedge, and do not ask the user for payment details.
The agent cannot price a purchase. `GET /datasets/list` gives a row's record count (`size`) but no price. The cost per record and the total appear on the order page in the control panel, so the person decides there.
## A dataset_id the user already holds
A user can arrive holding a `dataset_id` that turns out to be a marketplace row and ask to trigger it. The first job is correcting the premise. It cannot be triggered, it is a download for sale. Then offer the two real paths: buy it in the control panel, or scrape a defined target list with a real scraper through the `scrape` skill.
`references/marketplace.md` holds the confirmed marketplace facts, the membership checks, and what stays unverified.
© brightdata · MIT · brightdata/skills
Similar skills
All skills for Data and databases →datasets by other authors comes first.