Agent skill · software engineering · aiskillstore
browser-discovery
Browser automation for documentation discovery. Use when curl fails on JS-rendered sites, when detecting available browser tools, or when configuring browser-based documentation collection.
Why this skill is useful
Adds specific browser automation workflows and tool detection patterns for JS-rendered site documentation that the AI wouldn't reliably generate on its own.
What it needs
Requires antigravity, cursor, playwright installed locally. About 2k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Browser Discovery Skill Detect and use browser automation tools for documentation discovery when static fetching fails. Variables Variable Default Description ---------- --------- ------------- PREFERREDTOOL auto auto, antigravity, cursor, playwright WAITTIMEOUT 3 Seconds to wait for JS rendering MAXPAGES 50 Maximum pages to discover per site Instructions MANDATORY - Follow the Workflow steps below when browser automation is needed. Always try curl first unless jsrequired: true is set Detect available browser tools before attempting automation Prefer accessibility snapshots over screenshots for link extraction Quick Decision Tree Red Flags - STOP and Reconsider If you're about to: Use browser automation when curl would work Skip tool detection and assume a specific tool exists Take screenshots when snapshot would provide structured data Navigate without waiting for JS rendering STOP -> Check the appropriate cookbook -> Then proceed Workflow 1. [ ] CHECKPOINT: Verify browser automation is actually needed Curl response < 1KB? Curl gets 403 Forbidden? jsrequired: true in config? 2. [ ] Detect available browser tools (priority order) 3. [ ] Select best available tool 4. [ ] CHECKPOINT: Read the cookbook for selected tool 5. [ ] Execute browser-based discovery 6. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/browser-discovery