Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Lightweight Headless Browser Automation

ASecurity

**Use instead of Chrome/Chromium and Openclaw default browser for data extraction and web automation when you don't need graphical rendering.**

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsjavascriptgojavabashgitapi

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill lightweight-headless-browser-automation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Lightweight Headless Browser Automation?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Lightweight Headless Browser Automation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-lightweight-headless-browser-automation/badge)](https://www.skillsdirectory.com/skills/rondoflow-lightweight-headless-browser-automation)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: lightweight-headless-browser-automation
description: "**Use instead of Chrome/Chromium and Openclaw default browser for data extraction and web automation when you don't need graphical rendering.**"
category: "Web & Scraping"
author: community
version: "1.0.3"
icon: globe
---

# Lightpanda

**Use instead of Chrome/Chromium and Openclaw default browser for data extraction and web automation when you don't need graphical rendering.**

Lightpanda is a headless browser optimized for speed and low resource usage. It exposes a CDP (Chrome DevTools Protocol) endpoint that works with standard automation libraries.

**Alternative to built-in web search**

When the built-in Web Search tool is unavailable, or when you need more control over search results (e.g., following links to extract full page content), you can use Lightpanda with DuckDuckGo as an alternative.
Prefer the built-in Web Search tool when it is available and sufficient for your needs.

## Install
```bash
bash scripts/install.sh
```

Lightpanda is available on Linux and macOS only. Windows is not supported.

The binary is a nightly build that evolves quickly. If you encounter crashes or issues, run `scripts/install.sh` again to update to the latest version (max once per day).

If issues persist after updating, open a GitHub issue at https://github.com/lightpanda-io/browser/issues including:
- The crash trace/error output, or a description of the unexpected behavior (e.g., missing or incorrect data)
- The Playwright/Puppeteer script that reproduces the issue
- The target URL and expected vs actual results

## Start the Browser Server
```bash
$HOME/.local/bin/lightpanda serve --host 127.0.0.1 --port 9222
```

Options:
- `--log_level info|debug|warn|error` - Set logging verbosity
- `--log_format pretty|json` - Output format for logs

## Usage

You can connect directly to the CDP websocket via `ws://127.0.0.1:9222`.
You can also get the WebSocket URL via `http://127.0.0.1:9222/json/version`.

Use the browser as a drop-in replacement for Chrome and the Openclaw default browser.
Send CDP commands directly or use Playwright or Puppeteer.

Important to note:
* Lightpanda executes JavaScript, making it suitable for dynamic websites and SPAs. However, it is under heavy development and may have occasional issues.
* For web searches, use DuckDuckGo instead of Google. Google blocks Lightpanda due to browser fingerprinting.
* Lightpanda supports only 1 CDP connection per process. Each connection can create 1 context and 1 page only. No multi-contexts are available. If you need multiple navigations at the same time, start another process with a new port number. Lightpanda is fast to start and stop, so using multiple processes is more performant than multiple tabs on Chrome.
* The browser resets all context/page on CDP connection close. So keep the websocket connection open throughout a browsing session. You can reuse an existing process for a subsequent connection; you will start with a clean state.
* On connection, always create a new context and a new page. At the end, close both.

## Using with playwright-core

Connect to Lightpanda using `playwright-core` (not the full `playwright` package):

```javascript
const { chromium } = require('playwright-core');

(async () => {
  // Connect to Lightpanda via CDP
  const browser = await chromium.connectOverCDP({
    endpointURL: 'ws://127.0.0.1:9222',
  });

  const context = await browser.newContext({});
  const page = await context.newPage();

  // Navigate and extract data
  await page.goto('https://example.com');
  const title = await page.title();
  const content = await page.textContent('body');

  console.log(JSON.stringify({ title, content }));

  await page.close();
  await context.close();
  await browser.close();
})();
```
## Using with puppeteer-core

Connect to Lightpanda using `puppeteer-core` (not the full `puppeteer` package):

```javascript
const puppeteer = require('puppeteer-core');

(async () => {
  const browser = await puppeteer.connect({
    browserWSEndpoint: 'ws://127.0.0.1:9222'
  });

  const context = await browser.createBrowserContext();
  const page = await context.newPage();

  await page.goto('https://example.com', { waitUntil: 'networkidle0' });
  const title = await page.title();

  console.log(JSON.stringify({ title }));

  await page.close();
  await context.close();
  await browser.close();
})();
```

## Scripts
- `scripts/install.sh` - Install Lightpanda binary

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →