Bright Data Agent Skills - Setup Guide¶
Source: brightdata/skills GitHub: brightdata/skills Skills: 22 skills · 26.9K total installs Category: Web Scraping & Research First Seen: catalogued August 15, 2026 evening sweep Quality Tier: 🟢 Production (official org - Bright Data, the web data platform vendor)
Bright Data's official agent skills cover the full web-data lifecycle: scraping, search, SEO audits, competitive intelligence, brand listening, price comparison, data feeds, and a scraping browser debugger - the operational layer for agent-driven web research. Carried in the sweep queue for weeks; drafted now on publisher-page verification of 26.9K installs across 22 skills.
Installation¶
npx skills add brightdata/skills
Prerequisites¶
| Requirement | Details |
|---|---|
| Node.js + npx | For the skill installer |
| Bright Data account | API credentials for most skills |
| Bright Data proxies | For scrape and browser skills at scale |
What It Provides¶
| Skill | Installs | Purpose |
|---|---|---|
| scrape | 10.7K | Structured web scraping |
| search | 7.3K | Web search via Bright Data |
| brightdata-cli | 1.9K | CLI interaction |
| seo-audit | 1.7K | SEO auditing |
| bright-data-best-practices | 1.7K | Platform best practices |
| bright-data-mcp | 956 | MCP server integration |
| agent-onboarding | 518 | Agent onboarding workflow |
| scraper-builder | 276 | Build custom scrapers |
| data-feeds | 267 | Feed-based data collection |
| competitive-intel | 226 | Competitive intelligence gathering |
| design-mirror | 222 | Mirror site designs |
| brd-browser-debug | 189 | Scraping browser debugging |
| brightdata-sdk | 160 | SDK usage |
| price-comparison | 139 | Price comparison scraping |
| scraper-studio | 121 | Scraper Studio workflows |
| brightdata-proxy | 105 | Proxy configuration |
| discover-api | 93 | Discovery API |
| live-research | 90 | Live research workflows |
| brand-listening | 89 | Brand mentions monitoring |
| brightdata-sdk-js / python-sdk-best-practices | 87 / 47 | SDK guidance |
| rag-pipeline | 82 | RAG data pipelines |
Quick Start¶
- Install:
npx skills add brightdata/skills - Start with
scrapeandsearch- the highest-install pair - Ask: "scrape this site and run a competitive intelligence pass on the pricing table"
CorpusIQ Use Cases¶
| Use Case | How |
|---|---|
| Research sweeps | scrape + search as a resilient fallback when primary search backends degrade |
| Competitive research | competitive-intel and price-comparison for market analysis |
| SEO work | seo-audit pairs with our Ahrefs and Search Console connectors |
| Brand monitoring | brand-listening for CorpusIQ mentions across the web |
Integration with CorpusIQ¶
CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.
This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.
Limitations / Verification¶
- Publisher-page install counts verified; individual skill audit pages were not fetched for this multi-skill suite
- Most skills require a paid Bright Data account with proxy allocation
- Scraping must respect robots.txt and site terms - the skills do not override that
npx skills add brightdata/skills # verify install works
Related¶
Powered by CorpusIQ