Give Claude a real browsing loop for open-ended research -- navigate sites, follow links, and read pages to gather the answer, not just search-result snippets.
Wires up a full browse-click-read loop for research tasks a single search can't answer: comparing options across several vendor or documentation sites, pulling structured information from a page that requires navigation, or verifying a claim by following it back to its source. Distinct from the existing Playwright Browser Automation skill, which is built for scripted QA/testing of a specific app's user flows -- this is aimed at open-ended agentic research and information-gathering across the open web, not test authoring. Modeled on agent-browser (vercel-labs/agent-browser), trending on skills.sh this week at 6.3K installs.
No account needed · Instant delivery · Secure Stripe checkout
Hand-picked Claude skills + tips for getting more out of your AI tools. No spam, unsubscribe anytime.
Weekly tips on using Claude effectively. Unsubscribe anytime.