How do I install the Agent Browser skill?

Run npx skillmds@latest add leoyeai-openclaw-master-skills/agent-browser in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Browser safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Browser?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Browser free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Browser?

LeoYeAI (@leoyeai-openclaw-master-skills) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Browser by leoyeai-openclaw-master-skills

Name: Agent Browser
Rating: 4.2 (5 reviews)
Author: LeoYeAI

File contents

Agent Browser — Page Crawling and Data Extraction

Installation

CLAWBOT must ensure agent-browser is available before any browsing task:

which agent-browser || npm install -g agent-browser
agent-browser install

Purpose

CLAWBOT uses this in Research Step 2 (explore & collect) when it encounters pages that require JS rendering. Suitable for: project official websites, DApp pages, and dynamic pages on aggregator platforms.

Core Workflow

# 1. Open & wait
agent-browser open <url>
agent-browser wait --load networkidle

# 2. Snapshot — get interactive elements with @refs
agent-browser snapshot -i

# 3. Extract content
agent-browser get text @e1         # element text
agent-browser get html @e1         # innerHTML
agent-browser get attr @e1 href    # attribute
agent-browser get title            # page title
agent-browser get url              # current URL
agent-browser get count ".item"    # count matching elements

# 4. Interact
agent-browser click @e1            # click
agent-browser fill @e2 "keyword"   # fill input (clears first)
agent-browser scroll down 500      # scroll
agent-browser scrollintoview @e1   # scroll element into view
agent-browser press Enter          # press key

# 5. Capture evidence
agent-browser screenshot --full    # full-page screenshot
agent-browser pdf output.pdf       # save as PDF

# 6. Close
agent-browser close

Wait Strategies

agent-browser wait @e1                  # wait for element
agent-browser wait 2000                 # wait milliseconds
agent-browser wait --text "Success"     # wait for text
agent-browser wait --url "/dashboard"   # wait for URL pattern
agent-browser wait --load networkidle   # wait for network idle

Semantic Locators (alternative to @refs)

agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"

Output Format

Add --json for structured output:

agent-browser snapshot -i --json
agent-browser get text @e1 --json

Notes

@ref changes after page navigation; always re-snapshot
Use fill for inputs (clears old value), not type
For dynamic pages, wait --load networkidle before snapshot
Use --headed to see the browser window for debugging

---name: agent-browserdescription: Browser automation tool. Used to capture project websites, DApp pages and other JS-rendered content, extract page text and interactive elements, and assist with research-oriented data collection.---# Agent Browser — Page Crawling and Data Extraction## InstallationCLAWBOT must ensure agent-browser is available before any browsing task:```bashwhich agent-browser || npm install -g agent-browseragent-browser install```## PurposeCLAWBOT uses this in Research Step 2 (explore & collect) when it encounterspages that require JS rendering.Suitable for: project official websites, DApp pages, and dynamic pages onaggregator platforms.## Core Workflow```bash# 1. Open & waitagent-browser open <url>agent-browser wait --load networkidle# 2. Snapshot — get interactive elements with @refsagent-browser snapshot -i# 3. Extract contentagent-browser get text @e1 # element textagent-browser get html @e1 # innerHTMLagent-browser get attr @e1 href # attributeagent-browser get title # page titleagent-browser get url # current URLagent-browser get count ".item" # count matching elements# 4. Interactagent-browser click @e1 # clickagent-browser fill @e2 "keyword" # fill input (clears first)agent-browser scroll down 500 # scrollagent-browser scrollintoview @e1 # scroll element into viewagent-browser press Enter # press key# 5. Capture evidenceagent-browser screenshot --full # full-page screenshotagent-browser pdf output.pdf # save as PDF# 6. Closeagent-browser close```## Wait Strategies```bashagent-browser wait @e1 # wait for elementagent-browser wait 2000 # wait millisecondsagent-browser wait --text "Success" # wait for textagent-browser wait --url "/dashboard" # wait for URL patternagent-browser wait --load networkidle # wait for network idle```## Semantic Locators (alternative to @refs)```bashagent-browser find role button click --name "Submit"agent-browser find text "Sign In" clickagent-browser find label "Email" fill "user@test.com"```## Output FormatAdd `--json` for structured output:```bashagent-browser snapshot -i --jsonagent-browser get text @e1 --json```## Notes- `@ref` changes after page navigation; always re-snapshot- Use `fill` for inputs (clears old value), not `type`- For dynamic pages, `wait --load networkidle` before `snapshot`- Use `--headed` to see the browser window for debugging

Frequently asked questions

Agent Browser