Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

agent-browser Automation

Lets Claude drive a real browser to research, click, fill forms, screenshot and extract data.

AutomationIntermediate★ 30,471⑂ 12,865AI score 8/10Last updated: Aug 9, 2026

What it does

Wraps the agent-browser CLI into a repeatable loop: open a page → snapshot -i to list interactive elements with refs (@e1, @e2) → act on those refs.

  • Navigation, click/double-click, hover, checkboxes, selects, file upload
  • Read text, HTML, attributes, input values, element counts
  • Full-page screenshots and PDF export
  • Semantic locators by role, text, label, or placeholder
  • Saved auth state (state save/load), cookie & localStorage control, raw JS eval
  • A strong safety section: never write unbounded wait loops — always cap with timeout plus a max-attempt counter so the agent turn can't hang

Who it's for

  • Anyone doing web research or working inside logged-in web apps
  • QA/devs who want quick form and flow checks without writing Playwright code
  • Analysts collecting recurring data plus screenshot evidence

Examples

  1. Form submission: open the form, snapshot -i to find the email/password/submit refs, fill and click, then wait --load networkidle and re-snapshot to verify.
  2. Data extraction: on a product listing, pull titles with get text and links with get attr href, then save screenshot products.png.
  3. Session reuse: log in once, state save auth.json, and later state load auth.json to jump straight into the dashboard.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the container/skills/agent-browser folder from the GitHub repo nanocoai/nanoclaw into my ~/.claude/skills/nanocoai-agent-browser/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/nanocoai/nanoclaw.git && mkdir -p ~/.claude/skills && cp -r nanoclaw/container/skills/agent-browser ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/nanocoai/nanoclaw.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r nanoclaw/container/skills/agent-browser ~/.claude/skills/
  5. Install the agent-browser CLI (and its browser runtime, e.g. Playwright) per the repo docs; verify with agent-browser --help.
  6. Restart Claude Code and try a prompt like "open this page and pull the pricing table".
  7. Note: files such as auth.json store live login state locally — delete them after use on shared machines.
View source on GitHub ↗License: MIT