All 94 skillsWeb and data4 of 17
stryx:scraping
When data must be pulled off websites, or a scraper comes back empty or blocked.
/stryx:scrapingInside its piece: 30 specks, one for each file on its shelf. Its sixteen group-mates glow on the open book behind it. The light splits toward teal, the band of Web and data.
In numbers
counted 2026-10-12 in the installed set- 22reference files
- 6helper scripts
- 30files in the skill
- 320KB on disk
- 11chapters
- 1agent works by this book
Use it when
in the skill’s own wordsWhen getting data off websites
- "scrape"
- "crawl"
- "extract products/prices/listings/reviews from"
- "pull data from <site>"
- "get all pages"
- "build a scraper"
- A scraper returning 0 items, empty or blocked pages (Cloudflare "Just a moment", captcha, 403/429)
- Choosing between plain HTTP, a hidden JSON API, a headless browser or a pre-built feed
- Pagination, infinite scroll, or thousands of URLs
- Proxies and IP rotation
- Anything Bright Data
- the bdata CLI (scrape, search, discover, pipelines, scraper create/run/heal, browser)
- Web Unlocker
- SERP API
- Web Scraper API
- Browser API / Scraping Browser
- Discover API
- brd.superproxy.io proxies and brd-customer- zones
- the Bright Data MCP server
- the brightdata-sdk or @brightdata/sdk SDKs
- a failed Scraping Browser session
Not for
another skill does it- Where to buy something cheapest→ stryx:price-comparison
- Competitor analysis→ stryx:market-intel
- Research briefs→ stryx:research
- Driving a browser to test or debug an app→ stryx:browser
- SEO audits→ stryx:seo
On its shelf
30 files, 320 KB- references/22
- scripts/6
- SKILL.md1
- evals/1
Inside the book
11 chapters, by title only- Hard rules
- Step 0: what is available?
- Step 1: understand the target
- Step 2: pre-built first
- Step 3: recon
- Step 4: pick the method (the ladder)
- Step 5: extract
- Step 6: paginate and scale
- Step 7: verify
- Bright Data surfaces
- Troubleshooting
Its helper
1 agent works by this book- stryx:regex-and-parserWhen a text pattern (regex) or a parser for imported data must be built or fixed.
Works with
the skills it names most- stryx:browser→When Claude must drive a live web page: open, click, fill a form, take a screenshot.
- stryx:ai-power→When you are not sure which skill fits, or you say "load aipower": it is the map of all skills.
- stryx:market-intel→You want live facts on competitors, a market or what people say about a brand.
- stryx:price-comparison→You want to know where a product is cheapest or in stock.
- stryx:research→You need an answer with evidence and sources: compare libraries, check current versions, map a codebase.
- stryx:seo→When a website is not ranking, or its search setup needs an audit.
Claude loads it by itself when the moment comes; by hand, type the line at the top. It comes with the whole set: Installs all 94 skills, 32 agents and the brain program as one set. The skill’s own text is private source and is not shown here.