Agent Browser Operator
SkillWeb & browsingAgent Browser Operator lets your AI operate a web browser on your behalf, including on sites that need you to log in. Once added, it can carry out multi-step tasks on dynamic pages while keeping your session active, handling site operations that simple page reading cannot.
Available today. Use it from your connected AI after setup.
No other account needed.
Add the skill, then tell your AI which website task to do. It will operate the browser and carry out the steps for you.
Then ask your AI: use the Agent Browser Operator skill
What your AI can do with it
- Complete multi-step tasks on websites from start to finish
- Work on sites that require logging in
- Handle dynamic pages that change while you interact with them
- Stay signed in across a sequence of site operations
What this skill tells your AI
The instructions your AI receives, as published by agentskillexchange/skills in skills/agent-browser-operator/SKILL.md and read by ahel’s review.
Interactive browser skill for logged-in flows, dynamic pages, and session-aware site operations.
Prerequisites
OpenClaw, browser tool (OpenClaw-managed or Chrome extension relay)
Installation
Use the upstream install or setup path that matches your environment:
- npm install -g @playwright/cli@latest
- npm i playwright
Requirements and caveats from upstream:
Basic usage or getting-started notes:
-
bash
-
Optionally install skills for richer agent integration:
-
playwright-cli install --skills
-
Extracted from upstream docs: https://raw.githubusercontent.com/microsoft/playwright/HEAD/README.md
Documentation
Source
Signals
- GitHub stars
- 38
- Forks
- 53
- Last commit
- Sep 2026
ahel review
K1binfo
installs-packages
Automated review, not a security audit. Ruleset v1+k2.
Advanced
- Catalog kind
- skill
- Gateway key
agent-browser-operator- Source
- github.com/agentskillexchange/skills