01
It starts by itself
weekly query run. Runs in Claude Code routine or cron.
- ↻ weekly query run
0 7 * * 1
brightdata · 7K installsBright Data Search skill
Runs by itself, weekly query run.
Fresh search results, checked.
Install the Bright Data Search skill and make it a habit: follow https://gethabit.dev/skills/brightdata/search.md
- 1Copy
- 2Paste into Claude Code, Codex or Cursor
- 3It runs by itself
7K installs268 starsMIT licenceSource on GitHub ↗
Bright Data Search
by brightdata · 7K installs
The skill
The bright data search skill runs web searches through the Bright Data CLI, with keyword SERP results from bdata search and intent-ranked pages from bdata discover.
Only when you ask.
The habit
Fresh search results, checked.
↻ Runs by itselfweekly query run
How the habit works.
You don't have to.
When does it start? How does it check its work? What does it remember?
One run, step by step.
Then it stops.
Stops after twenty queries per run, with one retry per query.
- 01
Run the setup gate
Your agent checks that bdata is installed and that bdata zones works, else it stops.
- 02
Pick the command
It uses bdata search for keyword rankings and bdata discover for intent-ranked pages.
- 03
Set the geo
It sets --country, --language and --device so results can be compared run to run.
- 04
Run the queries
It runs each query with --json and pages with --page when more results are needed.
- 05
Check the output
It runs the verification gate: valid JSON, results present, title and link fields, no block pages.
- 06
Dedup and log
It removes URLs seen before and writes the new ones to the log.
- 07
Hand off
It passes chosen URLs to scrape or platform data needs to data-feeds.
What it may do.
Nothing more.
It writes only in its own folder and asks you before anything goes out.
- Writes only inloops/bright-data-search-loop/**
- Talks tono outside service
- Sendsnothing
- Your OKNothing goes out, so it needs no OK.
Is it for you?
Use it when it fits.
Read both lists. If the left one sounds like you, the Bright Data Search skill helps.
Use it when
- ✓ You need Google, Bing or Yandex results
- ✓ You want URLs to feed a scraper
- ✓ You want pages that match an intent
Skip it when
- – You need structured data from a known platform
- – You already have the URLs
Bright Data Search skill, answered.
When do I use search and when discover?
Use search to see what ranks for an exact keyword. Use discover for pages that match a meaning or intent.
Where are the results in the JSON?
For bdata search they sit at .organic[]. For bdata discover they sit at .results[].
What if a query returns nothing?
The agent relaxes the query and runs it again, and tells you if it stays empty.
How do I install the Bright Data Search skill?
Copy the prompt at the top into your agent. It installs the skill from brightdata/skills and sets up the habit. Or run npx skills add brightdata/skills --skill search.
Is the Bright Data Search skill free?
Yes. It is published under MIT. Habit is free too.
Bright Data Search. Now as a habit.
Install the Bright Data Search skill and make it a habit: follow https://gethabit.dev/skills/brightdata/search.md
All brightdata skills →More seo skills →
Works in
- Claude Code
- Codex
- Cursor
- ChatGPT
- Claude app
Made by brightdata, published under MIT. Habit links to the original and never changes it. Is this your skill?