Agent skill · software engineering · aiskillstore
agent-browser
Browser automation CLI for AI agents. Use for website interaction, form automation, screenshots, scraping, and web app verification. Prefer snapshot refs (@e1, @e2) for deterministic actions.
Why this skill is useful
Adds executable scripts for browser automation that significantly extend the AI's capabilities in web interaction and verification.
What it needs
Requires agent-browser installed locally. About 2k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
agent-browser - Browser Automation for AI Agents When to use this skill Open websites and automate UI actions Fill forms, click controls, and verify outcomes Capture screenshots/PDFs or extract content Run deterministic web checks with accessibility refs Execute parallel browser tasks via isolated sessions Core workflow Always use the deterministic ref loop: 1. agent-browser open <url> 2. agent-browser snapshot -i 3. interact with refs (@e1, @e2, ...) 4. agent-browser snapshot -i again after page/DOM changes Command patterns Use && chaining when intermediate output is not needed. High-value commands: Navigation: open, close Snapshot: snapshot -i, snapshot -i -C, snapshot -s "#selector" Interaction: click, fill, type, select, check, press Verification: diff snapshot, diff screenshot --baseline <file> Capture: screenshot, screenshot --annotate, pdf Wait: wait --load networkidle, wait <selector @ref ms> Verification patterns Use explicit evidence after actions. Safety and reliability Refs are invalid after navigation or significant DOM updates; re-snapshot before next action. Prefer wait --load networkidle or selector/ref waits over fixed sleeps. For multi-step JS, use eval --stdin (or base64) to avoid shell escaping breakage. For concurrent tasks, isolate with --session <name>. Use output controls in long pages to reduce context flooding. Optional hardening in sensitive flows: domain allowlist and action policies. Optional hardening examples: Example policy.json: CLI-flag equivalent: Troubleshooting command not found: install and run agent-browser install. Wrong element clicked: run snapshot -i again and use fresh refs. Dynamic SPA content missing: wait with --load networkidle or targeted wait selector. Session collisions: assign unique --session names and close each session. Large output pressure: narrow snapshots (-i, -c, -d, -s) and extract only needed text. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/agent-browser--02dfe3