New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Nstbrowser AI Agent

by LeoYeAI in LeoYeAI/openclaw-master-skills

Browser automation CLI with Nstbrowser integration for AI agents.

MITAuto-check passedProductivity & Automation

Install Nstbrowser AI Agent

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill nstbrowser-ai-agent -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills nstbrowser-ai-agent --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nstbrowser-ai-agent .claude/skills/nstbrowser-ai-agent && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
nstbrowser-ai-agent
GitHub stars
2.2k
Token cost
~6.1k tokens
SKILL.md length
1,669 words
Files
12 (incl. references)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

Browser automation CLI with Nstbrowser integration for AI agents.

  • Works in 5 steps: Nstbrowser Client Installation → Nstbrowser Service Running → API Key Configuration → …
  • The user needs advanced browser fingerprinting
  • SKILL.md covers Overview, Prerequisites, Quick Start and Core Concepts, plus 3 more sections
  • Runs Shell scripts from its folder; calls npm, npx and jq; needs NST_API_KEY

What it does

Nstbrowser AI Agent is an agent skill from LeoYeAI/openclaw-master-skills. Browser automation CLI with Nstbrowser integration for AI agents. Use when the user needs advanced browser fingerprinting, profile management, proxy configuration, batch operations on multiple browser profiles, or cursor-based pagination for large datasets. Triggers include requests to "use NST profile", "configure proxy for profile", "manage browser profiles", "batch update profiles", "start multiple browsers", "list profiles with pagination", or any task requiring Nstbrowser's anti-detection features.

Its SKILL.md is about 6.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `SECURITY.md`, `_meta.json` and `references/batch-operations.md`).

It sits in Productivity & Automation, covering Browser automation. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • The user needs advanced browser fingerprinting
  • Profile management
  • Proxy configuration
  • Batch operations on multiple browser profiles

Example prompts

  • “use NST profile”
  • “configure proxy for profile”
  • “manage browser profiles”
  • “/nstbrowser-ai-agent”

Requirements

  • Node.js
  • A Bash shell
  • A credential in YOUR_API_KEY
  • A credential in NST_API_KEY
  • Pre-approved tools (allowed-tools): Bash(npx nstbrowser-ai-agent:*), Bash(nstbrowser-ai-agent:*)

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Nstbrowser Client Installation
  2. Nstbrowser Service Running
  3. API Key Configuration
  4. CLI Tool Installation
  5. Verify Installation

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(npx nstbrowser-ai-agent:*)
    • Bash(nstbrowser-ai-agent:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • npm
    • npx
    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • nstbrowser.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • NST_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nstbrowser AI Agent loads about 6.1k tokens when it runs, and up to ~25k if it reads all its reference files. Until then it costs about 132 tokens; SKILL.md has 1,669 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~132
When it runs · the whole SKILL.md, loaded when a task matches
~6.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~25k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,669 words, ~6,120 tokens.

Download SKILL.mdSave it as .claude/skills/nstbrowser-ai-agent/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
nstbrowser-ai-agent
description
Browser automation CLI with Nstbrowser integration for AI agents. Use when the user needs advanced browser fingerprinting, profile management, proxy configuration, batch operations on multiple browser profiles, or cursor-based pagination for large datasets. Triggers include requests to "use NST profile", "configure proxy for profile", "manage browser profiles", "batch update profiles", "start multiple browsers", "list profiles with pagination", or any task requiring Nstbrowser's anti-detection features.
allowed-tools
Bash(npx nstbrowser-ai-agent:*), Bash(nstbrowser-ai-agent:*)

Browser Automation with nstbrowser-ai-agent

Overview

This skill enables AI agents to control browsers using nstbrowser-ai-agent CLI with Nstbrowser integration. Nstbrowser provides advanced browser fingerprinting, profile management, and anti-detection capabilities for professional browser automation.

This tool requires Nstbrowser service to function. All browser operations are performed through Nstbrowser profiles, which provide:

  • Advanced browser fingerprinting and anti-detection
  • Profile management with persistent sessions
  • Proxy configuration per profile
  • Batch operations on multiple profiles
  • Tag and group organization for profile management

Prerequisites

Before using this tool, ensure you have the following:

1. Nstbrowser Client Installation

Nstbrowser client must be installed and running on your system.

2. Nstbrowser Service Running

The Nstbrowser API service must be accessible:

  • Default endpoint: http://127.0.0.1:8848
  • Verify service is running using the CLI:
    bash
    nstbrowser-ai-agent profile list
  • Expected response: List of profiles or empty list
3. API Key Configuration

Obtain your API key from the Nstbrowser dashboard and configure it:

Method 1: Config File (Recommended)

bash
nstbrowser-ai-agent config set key YOUR_API_KEY

Method 2: Environment Variable

Set the NST_API_KEY environment variable in your shell configuration file.

4. CLI Tool Installation

Install the nstbrowser-ai-agent CLI:

bash
# Using npx (no installation required)
npx nstbrowser-ai-agent --help

# Or install globally
npm install -g nstbrowser-ai-agent
5. Verify Installation

Test your setup:

bash
# Check CLI version
nstbrowser-ai-agent --version

# List profiles (verifies API connection)
nstbrowser-ai-agent profile list

If you see your profiles or an empty list, your environment is configured correctly.

Quick Start

Get started in 5 minutes with these examples:

Option 1: Using Temporary Browser (Fastest)

For quick tests or one-time tasks:

bash
# 1. Start temporary browser
nstbrowser-ai-agent browser start-once

# 2. Open a website
nstbrowser-ai-agent open https://example.com

# 3. Take a snapshot
nstbrowser-ai-agent snapshot -i

# 4. Close browser (auto-cleanup)
nstbrowser-ai-agent close

Note: Temporary browsers don't save session state and are cleaned up after use.

For tasks that require saved sessions, cookies, or login state:

bash
# 1. List available profiles
nstbrowser-ai-agent profile list

# 2. Create a new profile (if needed)
nstbrowser-ai-agent profile create my-profile

# 3. Open browser with profile (auto-starts if not running)
nstbrowser-ai-agent open https://example.com

# 4. Interact with page
nstbrowser-ai-agent snapshot -i
nstbrowser-ai-agent click @e1

# 5. Close browser (session saved to profile)
nstbrowser-ai-agent close

Expected Output:

  • Profile list shows your profiles with IDs and names
  • Browser opens in headless mode
  • Snapshot shows page structure with element refs (@e1, @e2, etc.)
  • Session state persists across browser restarts

Core Concepts

Profiles

Profiles are the foundation of Nstbrowser automation. Each profile is an isolated browser environment that stores:

  • Browser Fingerprints: Canvas, WebGL, fonts, screen resolution, timezone
  • Session Data: Cookies, localStorage, sessionStorage
  • Login State: Persistent authentication across sessions
  • Proxy Settings: Per-profile proxy configuration
  • Browser Configuration: User agent, platform, language settings

Why use profiles?

  • Maintain separate identities for different tasks
  • Preserve login sessions between automation runs
  • Isolate cookies and data between different websites
  • Configure different proxies for different regions
Profile Name vs ID

All profile commands support both profile NAME and profile ID:

Profile Name:

  • User-friendly, easier to remember
  • Example: my-profile, test-account, production-bot
  • Use when: Working interactively or in scripts with descriptive names

Profile ID:

  • UUID format, guaranteed uniqueness
  • Example: 86581051-fb0d-4c4a-b1e3-ebc1abd17174
  • Use when: Scripting with multiple profiles or ensuring exact profile match

UUID Format Auto-Detection:

  • The system automatically detects UUID format in profile names
  • If you provide a UUID-formatted string to --profile, it's treated as a profile ID
  • This prevents accidental profile creation when you meant to use an ID
  • Example: --profile "86581051-fb0d-4c4a-b1e3-ebc1abd17174" is treated as profile ID

Resolution Priority:

  1. --profile flag (profile name or UUID auto-detected as ID)
  2. Use once browser if no profile specified

Profile Resolution Logic: When you specify a profile for a browser action:

  1. Check running browsers - Uses existing browser if already running (earliest if multiple)
  2. Start browser - Starts the profile if it exists but isn't running
  3. Create profile - If profile NAME doesn't exist, creates it automatically
  4. Error - If profile ID doesn't exist, returns an error
  5. Once browser - If no profile specified, uses or creates temporary browser

Important: If multiple profiles have the same name, the earliest started browser will be used.

Sticky Sessions

Once you start a session with a profile, that session "locks" to that browser instance. Subsequent commands automatically reuse the same browser without repeating the --profile flag.

bash
# First command: link session to profile
nstbrowser-ai-agent --profile my-profile open https://example.com

# Subsequent commands: Stays in 'my-profile' automatically
nstbrowser-ai-agent snapshot -i
nstbrowser-ai-agent click @e1
nstbrowser-ai-agent fill @e2 "data"

This makes automation scripts cleaner and reduces the need to specify the profile repeatedly.

Refs

Elements are identified by refs (e.g., @e1, @e2) from snapshots, making automation more reliable than CSS selectors.

bash
# Get snapshot with refs
nstbrowser-ai-agent snapshot -i

# Output shows elements with refs:
# @e1 button "Submit"
# @e2 textbox "Email"
# @e3 textbox "Password"

# Use refs to interact
nstbrowser-ai-agent fill @e2 "user@example.com"
nstbrowser-ai-agent fill @e3 "password"
nstbrowser-ai-agent click @e1

Note: For modern web frameworks (React, Vue, Angular), CSS selectors may be more reliable than refs.

Configuration

Store configuration persistently in ~/.nst-ai-agent/config.json:

bash
# Set API key (required)
nstbrowser-ai-agent config set key YOUR_API_KEY

# Optional: Set custom host
nstbrowser-ai-agent config set host api.example.com

# Optional: Set custom port
nstbrowser-ai-agent config set port 9000

# View all configuration
nstbrowser-ai-agent config show

# Get specific value
nstbrowser-ai-agent config get key

Configuration persists across sessions and takes priority over environment variables.

Environment Variables

Alternative to config file:

bash
# Nstbrowser API credentials (required if not using config)
# Set NST_API_KEY in your environment

# Optional: Nstbrowser API endpoint
# Set NST_HOST and NST_PORT if using custom endpoint

# Optional: Specify profile for each command
# nstbrowser-ai-agent open https://example.com --profile "my-profile"

Priority: Config file > Environment variables > Defaults

Common Commands

Profile Management

List Profiles

bash
# List all profiles
nstbrowser-ai-agent profile list

# List with JSON output
nstbrowser-ai-agent profile list --json

# List with pagination (for large datasets)
nstbrowser-ai-agent profile list-cursor --page-size 50

Show Profile Details

bash
# Show by name or ID
nstbrowser-ai-agent profile show my-profile --json
nstbrowser-ai-agent profile show 86581051-fb0d-4c4a-b1e3-ebc1abd17174 --json

Create Profile

bash
nstbrowser-ai-agent profile create my-profile \
  --proxy-host proxy.example.com \
  --proxy-port 8080 \
  --proxy-type http \
  --platform Windows

Delete Profile

bash
# Delete single profile
nstbrowser-ai-agent profile delete <profile-name-or-id>

# Delete multiple profiles
nstbrowser-ai-agent profile delete id-1 id-2 id-3
Browser Control

Start Browser

bash
# Start with profile name
nstbrowser-ai-agent browser start my-profile

# Start with profile ID
nstbrowser-ai-agent browser start 86581051-fb0d-4c4a-b1e3-ebc1abd17174

# Start temporary browser
nstbrowser-ai-agent browser start-once

# Start temporary browser
nstbrowser-ai-agent browser start-once

Stop Browser

bash
# Stop specific browser
nstbrowser-ai-agent browser stop my-profile

# Stop all browsers
nstbrowser-ai-agent browser stop-all

List Running Browsers

bash
nstbrowser-ai-agent browser list
Page Navigation

Open URL

bash
# Auto-launches browser if not running
nstbrowser-ai-agent open https://example.com

Navigate

bash
nstbrowser-ai-agent back
nstbrowser-ai-agent forward
nstbrowser-ai-agent reload
Page Inspection

Get Snapshot

bash
# Accessibility snapshot with refs (best for AI)
nstbrowser-ai-agent snapshot -i

# Compact snapshot
nstbrowser-ai-agent snapshot -c

# Custom depth
nstbrowser-ai-agent snapshot -d 3

Get Page Info

bash
nstbrowser-ai-agent get title
nstbrowser-ai-agent get url

Take Screenshot

bash
nstbrowser-ai-agent screenshot output.png

# Annotated screenshot with element labels
nstbrowser-ai-agent screenshot --annotate output.png
Element Interaction

Click

bash
# Click by ref
nstbrowser-ai-agent click @e1

# Click by CSS selector
nstbrowser-ai-agent click 'button[type="submit"]'

Fill Input

bash
# Fill by ref
nstbrowser-ai-agent fill @e2 "text"

# Fill by CSS selector
nstbrowser-ai-agent fill 'input[name="email"]' "user@example.com"

Type Text

bash
nstbrowser-ai-agent type @e3 "text"

Get Element Text

bash
nstbrowser-ai-agent get text @e4
nstbrowser-ai-agent get text '.product-price'
Wait Commands

Wait for Element

bash
nstbrowser-ai-agent wait 'button.submit'

Wait for Time

bash
# Wait 3 seconds
nstbrowser-ai-agent wait 3000

Wait for Page Load

bash
nstbrowser-ai-agent wait --load networkidle
JavaScript Execution

Execute JavaScript

bash
nstbrowser-ai-agent eval "document.title"
nstbrowser-ai-agent eval "document.querySelectorAll('a').length"

# Execute from stdin
echo "document.body.innerHTML" | nstbrowser-ai-agent eval --stdin
Proxy Management

Show Proxy

bash
nstbrowser-ai-agent profile proxy show my-profile --json

Update Proxy

bash
nstbrowser-ai-agent profile proxy update my-profile \
  --host proxy.example.com \
  --port 8080 \
  --type http \
  --username proxyuser \
  --password proxypass

Reset Proxy

bash
nstbrowser-ai-agent profile proxy reset <profile-name-or-id>

Batch Proxy Operations

bash
# Batch update
nstbrowser-ai-agent profile proxy batch-update id-1 id-2 id-3 \
  --host proxy.example.com \
  --port 8080 \
  --type http

# Batch reset
nstbrowser-ai-agent profile proxy batch-reset id-1 id-2 id-3

Workflow Examples

Pattern 1: Profile-based Automation

Use Case: Automate tasks that require persistent login sessions or cookies.

bash
# 1. List profiles to verify connection
nstbrowser-ai-agent profile list

# 2. Set profile by name
nstbrowser-ai-agent config set profile my-profile

# 3. List profiles to find target
nstbrowser-ai-agent profile list

# 4. Open browser with profile (auto-starts if not running)
nstbrowser-ai-agent open https://example.com --profile "my-profile"
nstbrowser-ai-agent open https://example.com

# 6. Get snapshot
nstbrowser-ai-agent snapshot -i

# 7. Interact with page
nstbrowser-ai-agent click @e1
nstbrowser-ai-agent fill @e2 "data"

# 8. Close (session saved to profile)
nstbrowser-ai-agent close
Pattern 2: Batch Profile Management

Use Case: Manage multiple profiles efficiently (update proxies, add tags, organize).

bash
# Get multiple profile IDs
PROFILE_IDS=$(nstbrowser-ai-agent profile list --json | jq -r '.data.profiles[0:3] | map(.profileId) | join(" ")')

# Batch update proxy
nstbrowser-ai-agent profile proxy batch-update $PROFILE_IDS \
  --host proxy.example.com \
  --port 8080 \
  --type http

# Batch add tags
nstbrowser-ai-agent profile tags batch-create $PROFILE_IDS \
  automated:blue batch-updated:green

# Batch move to group
GROUP_ID=$(nstbrowser-ai-agent profile groups list --json | jq -r '.data.groups[0].groupId')
nstbrowser-ai-agent profile groups batch-change $GROUP_ID $PROFILE_IDS
Pattern 3: Login and Scrape

Use Case: Log in to a website, navigate to data pages, and extract information.

bash
# 1. Open login page
nstbrowser-ai-agent --profile my-profile open https://site.com/login

# 2. Wait for page to load
nstbrowser-ai-agent wait --load networkidle

# 3. Fill and submit using CSS selectors
nstbrowser-ai-agent fill 'input[placeholder="Email"]' "user@example.com"
nstbrowser-ai-agent fill 'input[type="password"]' "userpassword"
nstbrowser-ai-agent click 'button[type="submit"]'

# 4. Wait for navigation
nstbrowser-ai-agent wait --load networkidle

# 5. Navigate to target page
nstbrowser-ai-agent open https://site.com/data

# 6. Extract data
nstbrowser-ai-agent snapshot -i > data.txt
nstbrowser-ai-agent eval "document.querySelector('.info')?.textContent"

# 7. Close (session saved to profile)
nstbrowser-ai-agent close

Error Handling

Common Errors (by frequency)
1. "NST_API_KEY is required"

Cause: API key not configured.

Solution:

bash
# Method 1: Config file (recommended)
nstbrowser-ai-agent config set key YOUR_API_KEY

# Method 2: Set environment variable in your shell

Verify:

bash
nstbrowser-ai-agent config get key
2. "Failed to connect to Nstbrowser"

Cause: Nstbrowser service not running or wrong endpoint.

Solution:

  1. Check if NST agent is running:
    bash
    nstbrowser-ai-agent nst status
  2. Ensure Nstbrowser client is running
  3. If using custom host/port, configure:
    bash
    nstbrowser-ai-agent config set host YOUR_HOST
nstbrowser-ai-agent config set port YOUR_PORT

Verify:

bash
# Should show "NST agent is running and responsive"
nstbrowser-ai-agent nst status

# Should return list of profiles
nstbrowser-ai-agent profile list
3. "Profile not found"

Cause: Specified profile doesn't exist.

Solution:

  1. List available profiles:
    bash
    nstbrowser-ai-agent profile list
  2. Create a new profile:
    bash
    nstbrowser-ai-agent profile create my-profile
  3. Or use temporary browser:
    bash
    nstbrowser-ai-agent browser start-once

Verify:

bash
# Should show your profile
nstbrowser-ai-agent profile show my-profile
4. "Element not found" or "Action timed out"

Cause: Element ref is stale or page structure changed.

Solution:

  1. Get fresh snapshot:
    bash
    nstbrowser-ai-agent snapshot -i
  2. Use CSS selectors instead of refs:
    bash
    # Instead of: nstbrowser-ai-agent click @e1
# Use: nstbrowser-ai-agent click 'button[type="submit"]'
  3. Inspect page elements:
    bash
    nstbrowser-ai-agent eval "Array.from(document.querySelectorAll('input')).map(el => ({type: el.type, placeholder: el.placeholder}))"

Verify:

bash
# Element should be visible
nstbrowser-ai-agent is visible 'button[type="submit"]'
Ref System Limitations

The ref system (@e1, @e2, etc.) may not work reliably with modern web frameworks (Vue.js, React, Angular) due to dynamic DOM updates.

Workaround - Use CSS Selectors:

bash
# 1. Inspect page elements
nstbrowser-ai-agent eval "Array.from(document.querySelectorAll('input')).map(el => ({type: el.type, placeholder: el.placeholder}))"

# 2. Use CSS selectors directly
nstbrowser-ai-agent fill 'input[placeholder="Email"]' "user@example.com"
nstbrowser-ai-agent fill 'input[type="password"]' "password"
nstbrowser-ai-agent click 'button[type="submit"]'

Command Reference

Profile Commands
  • profile list - List all profiles
  • profile list-cursor - List profiles with cursor pagination
  • profile show <name-or-id> - Show profile details
  • profile create <name> - Create new profile
  • profile delete <name-or-id> [name-or-id...] - Delete profile(s)
  • profile groups list - List all groups
  • profile groups change <group-id> <profile-name-or-id> [...] - Move profile(s) to group
  • profile groups batch-change <group-id> <id> [...] - Batch change group
  • profile cache clear <id> [id...] - Clear profile cache
  • profile cookies clear <id> [id...] - Clear profile cookies
Show full SKILL.md (654 more words)Show less
Proxy Commands
  • profile proxy show <name-or-id> - Show proxy configuration
  • profile proxy update <name-or-id> - Update proxy settings
  • profile proxy reset <id> [id...] - Reset proxy settings
  • profile proxy batch-update <id> [id...] - Batch update proxy
  • profile proxy batch-reset <id> [id...] - Batch reset proxy
Tag Commands
  • profile tags list - List all tags
  • profile tags create <id> <tag> - Add tag to profile
  • profile tags update <id> <tag:color> [...] - Update profile tags
  • profile tags clear <id> [id...] - Clear profile tags
  • profile tags batch-create <id> [id...] <tag:color> - Batch create tags
  • profile tags batch-update <id> [id...] <tag:color> - Batch update tags
  • profile tags batch-clear <id> [id...] - Batch clear tags
Browser Commands
  • browser list - List running browsers
  • browser start <name-or-id> - Start browser with profile
  • browser start-once - Start temporary browser
  • browser stop <name-or-id> - Stop browser
  • browser stop-all - Stop all browsers
  • browser pages <name-or-id> - Get browser pages list
  • browser debugger <name-or-id> - Get debugger URL
  • browser cdp-url <name-or-id> - Get CDP WebSocket URL
  • browser cdp-url-once - Get CDP URL for temporary browser
  • browser connect <name-or-id> - Connect and get CDP URL
  • browser connect-once - Connect to temporary browser and get CDP URL
Navigation Commands
  • open <url> - Navigate to URL
  • back - Go back
  • forward - Go forward
  • reload - Reload page
Inspection Commands
  • snapshot [-i] [-c] [-d <depth>] - Get page snapshot
  • get title - Get page title
  • get url - Get current URL
  • get text <sel> - Get element text
  • screenshot [path] - Take screenshot
  • is visible <sel> - Check if element is visible
Interaction Commands
  • click <sel> - Click element
  • fill <sel> <text> - Fill input
  • type <sel> <text> - Type into element
  • press <key> - Press key
  • wait <sel|ms> - Wait for element or time
Utility Commands
  • eval <js> - Execute JavaScript
  • close - Close browser
  • session list - List active sessions
  • update check - Check for available updates
  • nst status - Check if NST agent is running
  • config set <key> <value> - Set configuration
  • config get <key> - Get configuration value
  • config show - Show all configuration

JSON Output

All commands support --json flag for machine-readable output:

bash
nstbrowser-ai-agent profile list --json
nstbrowser-ai-agent snapshot -i --json
nstbrowser-ai-agent get text @e1 --json

Best Practices

  1. Use Profile Names: More readable than IDs for most use cases
  2. Leverage Sticky Sessions: No need to repeat --profile flag once browser is running
  3. Use Batch Operations: More efficient for multiple profiles
  4. Organize with Groups and Tags: Keep profiles organized
  5. Prefer CSS Selectors for Modern Apps: Refs may not work with Vue/React/Angular
  6. Wait Appropriately: Use wait --load networkidle after navigation
  7. Close Cleanly: Always close browser to save session state
  8. Handle Errors: Check command output and retry if needed
  9. Use Proxies Per Profile: Configure proxies for geo-targeting or privacy
  10. Keep Updated: Run nstbrowser-ai-agent update check periodically

Updates

Automatic Update Checks

The CLI automatically checks for updates once every 24 hours and notifies you when a new version is available.

Disable automatic checks:

bash
# Set environment variable
NSTBROWSER_AI_AGENT_NO_UPDATE_CHECK=1
Manual Update Check
bash
# Check for updates
nstbrowser-ai-agent update check

# JSON output
nstbrowser-ai-agent update check --json
Updating to Latest Version
bash
# If installed globally
npm install -g nstbrowser-ai-agent@latest

# If using npx
npx nstbrowser-ai-agent@latest

# If installed locally in project
npm install nstbrowser-ai-agent@latest

Deep-Dive Documentation

For more detailed information, see:

ReferenceWhen to Use
references/nst-api-reference.mdComplete NST API reference with all commands
references/profile-management.mdProfile creation, organization, and lifecycle
references/proxy-configuration.mdProxy setup, testing, and troubleshooting
references/batch-operations.mdEfficient batch operations on multiple profiles
references/troubleshooting.mdCommon issues and diagnostic commands

Ready-to-Use Templates

TemplateDescription
templates/profile-setup.shProfile initialization with proxy and tags
templates/batch-proxy-update.shBatch proxy update for multiple profiles
templates/automated-workflow.shComplete automation workflow example
bash
./templates/profile-setup.sh my-profile --proxy-host proxy.com --proxy-port 8080
./templates/batch-proxy-update.sh "id1 id2 id3" --proxy-host proxy.com --proxy-port 8080
./templates/automated-workflow.sh my-profile https://example.com

Notes

  • Nstbrowser is required: This tool only works with Nstbrowser service
  • Profile name/ID support: All commands accept both names and IDs
  • Auto-start: Browser automatically starts when using profile if not running
  • Name resolution: Profile names are resolved to IDs automatically via API
  • Sticky sessions: Profile persists across commands in the same session
  • Profiles managed by Nstbrowser: Profiles are created and stored by Nstbrowser client
  • Daemon auto-starts: Daemon starts on first command and persists between commands
  • Session persistence: Session state is automatically saved to profiles when browser closes
  • Temporary browsers: Use browser start-once for disposable sessions that don't save state

CDP Integration

Get Chrome DevTools Protocol (CDP) WebSocket URLs to connect external tools:

bash
# Get CDP URL for existing browser
nstbrowser-ai-agent browser cdp-url my-profile

# Get CDP URL for temporary browser
nstbrowser-ai-agent browser cdp-url-once

# Connect to browser and get CDP URL (starts if not running)
nstbrowser-ai-agent browser connect my-profile

# Connect to temporary browser and get CDP URL
nstbrowser-ai-agent browser connect-once

Use cases:

  • Connect Puppeteer/Playwright to Nstbrowser-managed browsers
  • Attach Chrome DevTools for debugging
  • Integrate with custom CDP-based automation tools
  • Monitor browser activity with external tools

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in skills/nstbrowser-ai-agent of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • SECURITY.md
  • _meta.json
  • references/batch-operations.md
  • references/nst-api-reference.md
  • references/profile-management.md
  • references/proxy-configuration.md
  • references/troubleshooting.md
  • skill.json
  • templates/automated-workflow.sh
  • templates/batch-proxy-update.sh
  • templates/profile-setup.sh

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Nstbrowser AI Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nstbrowser AI Agent compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nstbrowser AI Agent this skillLeoYeAI/openclaw-master-skills2.2k—~6.1kAutomated safety check: PassMIT
Agent Browserquran/quran.com-frontend-next1.9k40 repos~3.3kAutomated safety check: PassNone
Dev-Browser CLI AutomationSawyerHood/dev-browser6.7k1 repos~455Automated safety check: PassMIT
Browser Automationopenclaw/openclaw392k—~2.9kAutomated safety check: PassMIT
Camoufox CLIBin-Huang/camoufox-cli3501 repos~4.5kAutomated safety check: PassMIT
BrowserVibiumDev/vibium2.9k—~4.8kAutomated safety check: PassApache-2.0

Similar skills

  • Agent Browser

    quran/quran.com-frontend-next

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    1.9k GitHub starsUsed in 40 repos~3.3k tokens
    Productivity & AutomationAuto-check passed

  • Dev-Browser CLI Automation

    SawyerHood/dev-browser

    Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web…

    6.7k GitHub starsUsed in 1 repo~455 tokens
    Productivity & AutomationAuto-check passed

  • Browser Automation

    openclaw/openclaw

    A skill your agent uses when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.

    392k GitHub stars~2.9k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Camoufox CLI

    Bin-Huang/camoufox-cli

    Anti-detect browser automation CLI & Skills for AI agents. An agent skill from Bin-Huang/camoufox-cli.

    350 GitHub starsUsed in 1 repo~4.5k tokens
    Productivity & AutomationAuto-check passed

  • Browser

    VibiumDev/vibium

    Automate browsers with the Vibium CLI. An agent skill from VibiumDev/vibium.

    2.9k GitHub stars~4.8k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Use Agent Browser For Airi

    moeru-ai/airi

    Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts.

    50k GitHub stars~1.1k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo

  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes

  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed

  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed

  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed

  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes

  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Nstbrowser AI Agent

What does Nstbrowser AI Agent do?

Browser automation CLI with Nstbrowser integration for AI agents. Nstbrowser AI Agent is an agent skill from LeoYeAI/openclaw-master-skills. Browser automation CLI with Nstbrowser integration for AI agents.

When should I use Nstbrowser AI Agent?

Nstbrowser AI Agent fits situations like: the user needs advanced browser fingerprinting; profile management; proxy configuration; batch operations on multiple browser profiles.

How do I install Nstbrowser AI Agent in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill nstbrowser-ai-agent -a claude-code`. Or copy the skill folder (skills/nstbrowser-ai-agent in LeoYeAI/openclaw-master-skills) into .claude/skills/nstbrowser-ai-agent in your project. Claude Code loads it when a task matches its description.

How do I install Nstbrowser AI Agent in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill nstbrowser-ai-agent -a codex`. Or copy the skill folder (skills/nstbrowser-ai-agent in LeoYeAI/openclaw-master-skills) into .agents/skills/nstbrowser-ai-agent in your project. Codex loads it when a task matches its description.

Can I use Nstbrowser AI Agent in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill nstbrowser-ai-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nstbrowser-ai-agent, .gemini/skills/nstbrowser-ai-agent, .github/skills/nstbrowser-ai-agent and .opencode/skills/nstbrowser-ai-agent in your project.

What does Nstbrowser AI Agent need to run?

Going by SKILL.md and its folder, Nstbrowser AI Agent needs a shell for the scripts in its folder, the command-line tools its instructions call (npm, npx and jq) and credentials named NST_API_KEY. Our summary lists: Node.js; A Bash shell; A credential in YOUR_API_KEY; A credential in NST_API_KEY. Its frontmatter pre-approves these tools: Bash(npx nstbrowser-ai-agent:*), Bash(nstbrowser-ai-agent:*).

Does Nstbrowser AI Agent access the network?

SKILL.md names 1 domain. As links in the text: nstbrowser.io. This is read from the text; nothing was executed.

Is Nstbrowser AI Agent safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Nstbrowser AI Agent use?

Nstbrowser AI Agent is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nstbrowser AI Agent use?

About 6.1k tokens (SKILL.md is roughly 24k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 19k tokens, read only when the agent opens those files.

What are the alternatives to Nstbrowser AI Agent?

Skills that share tags, products or a category with Nstbrowser AI Agent: Agent Browser (quran/quran.com-frontend-next, 1.9k stars), Dev-Browser CLI Automation (SawyerHood/dev-browser, 6.7k stars), Browser Automation (openclaw/openclaw, 392k stars) and Camoufox CLI (Bin-Huang/camoufox-cli, 350 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nstbrowser AI Agent?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.