Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

agent-browser Web Automation

Drive a real browser from the agent-browser CLI to navigate, click, fill forms, extract data, and capture screenshots.

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

What it does

  • Lets Claude operate a real browser through the agent-browser command-line tool.
  • Standardizes the core loop: open <url> → snapshot -i to list interactive elements with refs (@e1) → act on those refs → re-snapshot after navigation or DOM changes.
  • Provides a full command catalog: navigation, snapshots (depth/selector/compact), click/fill/type/check/select/upload, get text|html|attr|value|count, screenshots and PDF export, multiple wait modes, semantic locators (role/text/label/placeholder), saved auth state, cookies and localStorage, and raw JS eval.
  • Includes a key safety rule: any custom-condition wait must be bounded by both timeout and a max-attempt counter, so a stuck page can't hang the entire agent turn.

Who it's for

  • Developers and QA engineers doing repeated web UI checks
  • Anyone automating logins, form submissions, or data pulls from web apps
  • Users who want the agent to research, read pages, and capture visual evidence

Examples

  1. Form submission: open the page, snapshot -i, fill @e1 / fill @e2, click @e3, wait --load networkidle, then snapshot to verify.
  2. Data extraction: pull product titles with get text, links with get attr href, totals with get count ".item", and save screenshot products.png.
  3. Session reuse: log in once, state save auth.json, then later state load auth.json and jump straight to the dashboard.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/nanocoai/nanoclaw/HEAD/container/skills/agent-browser/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

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 /tmp/nanoclaw && mkdir -p ~/.claude/skills && cp -r /tmp/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 repository: 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. Check the prerequisite: run agent-browser --help. If it isn't found, use the nanoclaw container environment or install the agent-browser CLI per the repo's instructions.
  6. Restart Claude Code and try a prompt like "Open this URL and fill in the login form."
  7. When finished, have the agent run agent-browser close to release the browser.
View source on GitHub ↗License: MIT