← Back to Skills Marketplace
junxuan666

junxuan

by junxuan666 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
300
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install junxuan
Description
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co...
README (SKILL.md)

Browser Automation with agent-browser

Installation

npm recommended

npm install -g agent-browser
agent-browser install
agent-browser install --with-deps

From Source

git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
agent-browser install

Quick start

agent-browser open \x3Curl>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

  1. Navigate: agent-browser open \x3Curl>
  2. Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
  3. Interact using refs from the snapshot
  4. Re-snapshot after navigation or significant DOM changes

Commands

Navigation

agent-browser open \x3Curl>      # Navigate to URL
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser

Snapshot (page analysis)

agent-browser snapshot            # Full accessibility tree
agent-browser snapshot -i         # Interactive elements only (recommended)
agent-browser snapshot -c         # Compact output
agent-browser snapshot -d 3       # Limit depth to 3
agent-browser snapshot -s "#main" # Scope to CSS selector

Interactions (use @refs from snapshot)

agent-browser click @e1           # Click
agent-browser dblclick @e1        # Double-click
agent-browser focus @e1           # Focus element
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing
agent-browser press Enter         # Press key
agent-browser press Control+a     # Key combination
agent-browser keydown Shift       # Hold key down
agent-browser keyup Shift         # Release key
agent-browser hover @e1           # Hover
agent-browser check @e1           # Check checkbox
agent-browser uncheck @e1         # Uncheck checkbox
agent-browser select @e1 "value"  # Select dropdown
agent-browser scroll down 500     # Scroll page
agent-browser scrollintoview @e1  # Scroll element into view
agent-browser drag @e1 @e2        # Drag and drop
agent-browser upload @e1 file.pdf # Upload files

Get information

agent-browser get text @e1        # Get element text
agent-browser get html @e1        # Get innerHTML
agent-browser get value @e1       # Get input value
agent-browser get attr @e1 href   # Get attribute
agent-browser get title           # Get page title
agent-browser get url             # Get current URL
agent-browser get count ".item"   # Count matching elements
agent-browser get box @e1         # Get bounding box

Check state

agent-browser is visible @e1      # Check if visible
agent-browser is enabled @e1      # Check if enabled
agent-browser is checked @e1      # Check if checked

Screenshots & PDF

agent-browser screenshot          # Screenshot to stdout
agent-browser screenshot path.png # Save to file
agent-browser screenshot --full   # Full page
agent-browser pdf output.pdf      # Save as PDF

Video recording

agent-browser record start ./demo.webm    # Start recording (uses current URL + state)
agent-browser click @e1                   # Perform actions
agent-browser record stop                 # Stop and save video
agent-browser record restart ./take2.webm # Stop current + start new recording

Recording creates a fresh context but preserves cookies/storage from your session. If no URL is provided, it automatically returns to your current page. For smooth demos, explore first, then start recording.

Wait

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
agent-browser wait --fn "window.ready"     # Wait for JS condition

Mouse control

agent-browser mouse move 100 200      # Move mouse
agent-browser mouse down left         # Press button
agent-browser mouse up left           # Release button
agent-browser mouse wheel 100         # Scroll wheel

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 "[email protected]"
agent-browser find first ".item" click
agent-browser find nth 2 "a" text

Browser settings

agent-browser set viewport 1920 1080      # Set viewport size
agent-browser set device "iPhone 14"      # Emulate device
agent-browser set geo 37.7749 -122.4194   # Set geolocation
agent-browser set offline on              # Toggle offline mode
agent-browser set headers '{"X-Key":"v"}' # Extra HTTP headers
agent-browser set credentials user pass   # HTTP basic auth
agent-browser set media dark              # Emulate color scheme

Cookies & Storage

agent-browser cookies                     # Get all cookies
agent-browser cookies set name value      # Set cookie
agent-browser cookies clear               # Clear cookies
agent-browser storage local               # Get all localStorage
agent-browser storage local key           # Get specific key
agent-browser storage local set k v       # Set value
agent-browser storage local clear         # Clear all

Network

agent-browser network route \x3Curl>              # Intercept requests
agent-browser network route \x3Curl> --abort      # Block requests
agent-browser network route \x3Curl> --body '{}'  # Mock response
agent-browser network unroute [url]            # Remove routes
agent-browser network requests                 # View tracked requests
agent-browser network requests --filter api    # Filter requests

Tabs & Windows

agent-browser tab                 # List tabs
agent-browser tab new [url]       # New tab
agent-browser tab 2               # Switch to tab
agent-browser tab close           # Close tab
agent-browser window new          # New window

Frames

agent-browser frame "#iframe"     # Switch to iframe
agent-browser frame main          # Back to main frame

Dialogs

agent-browser dialog accept [text]  # Accept dialog
agent-browser dialog dismiss        # Dismiss dialog

JavaScript

agent-browser eval "document.title"   # Run JavaScript

State management

agent-browser state save auth.json    # Save session state
agent-browser state load auth.json    # Load saved state

Example: Form submission

agent-browser open https://example.com/form
agent-browser snapshot -i
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]

agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

Example: Authentication with saved state

# Login once
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "username"
agent-browser fill @e2 "password"
agent-browser click @e3
agent-browser wait --url "/dashboard"
agent-browser state save auth.json

# Later sessions: load saved state
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard

Sessions (parallel browsers)

agent-browser --session test1 open site-a.com
agent-browser --session test2 open site-b.com
agent-browser session list

JSON output (for parsing)

Add --json for machine-readable output:

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

Debugging

agent-browser open example.com --headed              # Show browser window
agent-browser console                                # View console messages
agent-browser console --clear                        # Clear console
agent-browser errors                                 # View page errors
agent-browser errors --clear                         # Clear errors
agent-browser highlight @e1                          # Highlight element
agent-browser trace start                            # Start recording trace
agent-browser trace stop trace.zip                   # Stop and save trace
agent-browser record start ./debug.webm              # Record from current page
agent-browser record stop                            # Save recording
agent-browser --cdp 9222 snapshot                    # Connect via CDP

Troubleshooting

  • If the command is not found on Linux ARM64, use the full path in the bin folder.
  • If an element is not found, use snapshot to find the correct ref.
  • If the page is not loaded, add a wait command after navigation.
  • Use --headed to see the browser window for debugging.

Options

  • --session \x3Cname> uses an isolated session.
  • --json provides JSON output.
  • --full takes a full page screenshot.
  • --headed shows the browser window.
  • --timeout sets the command timeout in milliseconds.
  • --cdp \x3Cport> connects via Chrome DevTools Protocol.

Notes

  • Refs are stable per page load but change on navigation.
  • Always snapshot after navigation to get new refs.
  • Use fill instead of type for input fields to ensure existing text is cleared.

Reporting Issues

Usage Guidance
This SKILL.md appears to describe the 'agent-browser' CLI but the skill registry entry is named 'junxuan' with no homepage and a different owner id — that mismatch is suspicious. The instructions tell you to run network installs (npm install -g, git clone, pnpm build) and an 'agent-browser install' step that likely downloads native components; these operations should only be run after you verify the package and upstream repo. Before installing or running this skill: (1) confirm the npm package name and publisher on the official npm registry; (2) verify the GitHub repository and its maintainers (ensure the URL is correct and matches the package); (3) avoid running global installs or build steps as root — run them in an isolated environment or container; (4) note the SKILL.md references tools not listed in required binaries (git, pnpm) — ensure the runtime has the expected tooling and review what 'agent-browser install' does (network endpoints, binaries downloaded). If you can't verify the source/publisher, treat the skill as untrusted and do not run its install commands on sensitive hosts.
Capability Analysis
Type: OpenClaw Skill Name: junxuan Version: 1.0.0 The skill bundle provides a comprehensive interface for the 'agent-browser' CLI (a legitimate Vercel Labs project) to enable AI-driven web automation. It includes standard browser automation features such as navigation, element interaction, state management (cookies/localStorage), and debugging. No evidence of malicious intent, unauthorized data exfiltration, or prompt injection was found; the capabilities provided are consistent with the tool's stated purpose of headless browser automation.
Capability Assessment
ℹ Purpose & Capability
SKILL.md documents a browser automation CLI (agent-browser) and the requested binaries (node, npm) are consistent with an npm-distributed CLI. However the skill registry entry (name: junxuan, no homepage, unknown source) and included _meta.json refer to agent-browser/agent-browser packaging; the mismatch between the skill slug/owner and the documented upstream is anomalous and worth verifying.
ℹ Instruction Scope
Instructions stay within the expected scope of a browser automation CLI (navigate, snapshot, interact, record, set headers/credentials). They instruct network operations (npm install -g, git clone, pnpm build) and running an 'agent-browser install' step which may download native components — expected for such a CLI but the documentation is vague about what 'install' does and what network endpoints it contacts.
⚠ Install Mechanism
The skill has no formal install spec, but SKILL.md instructs doing npm global installs, git clone from GitHub, and pnpm build. Those steps perform network downloads and native builds; the registry metadata did not declare git or pnpm as required binaries. Lack of declared install instructions plus external downloads increases risk — verify the npm package and upstream repository before running installs.
✓ Credentials
The skill does not request environment variables or credentials in the registry metadata. Runtime commands include options to set HTTP basic auth or headers, but those are CLI actions and not declared env requirements. No disproportionate credential requests were found in the manifest.
✓ Persistence & Privilege
The skill is not always-on, does not request config paths, and uses the platform default for autonomous invocation. Nothing in the metadata suggests it will forcibly persist or modify other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install junxuan
  3. After installation, invoke the skill by name or use /junxuan
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Agent Browser initial release – a Rust & Node.js-based CLI for AI-powered web automation. - Added CONTRIBUTING.md and _meta.json for contribution guidelines and metadata. - Removed obsolete skill_main.py. - Replaced SKILL.md: now documents agent-browser CLI usage for browser automation, structured data extraction, interaction commands, workflow, and installation. - Provides detailed guides for automating navigation, DOM interactions, snapshots, screenshots, recording, network interception, browser state, and more. - Lists concise, consistent command examples for all supported use cases.
Metadata
Slug junxuan
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is junxuan?

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co... It is an AI Agent Skill for Claude Code / OpenClaw, with 300 downloads so far.

How do I install junxuan?

Run "/install junxuan" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is junxuan free?

Yes, junxuan is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does junxuan support?

junxuan is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created junxuan?

It is built and maintained by junxuan666 (@junxuan666); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments