Xpersona
W

Web Pilot

CLAWHUB · Unverified

Search the web and read page contents without API keys. Use when you need to search via DuckDuckGo/Brave/Google (multi-page), extract readable text from URLs... Skill: Web Pilot Owner: liranudi Summary: Search the web and read page contents without API keys. Use when you need to search via DuckDuckGo/Brave/Google (multi-page), extract readable text from URLs... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-02-17T17:37:36.982Z | user Initial release: browser automation & accessibility skill with 20+ actions — search, browse, interact, screenshot, form fill, JS eval, PDF e

62
Rank
84
Safety
11k
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 10.7K downloads reported by the source. Last updated 11/16/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: medium.

clawhub skill install s174mhw1c5ff0ww2acte2g78mn885mr5:web-pilot
  1. Setup complexity is MEDIUM. Standard integration tests and API key provisioning are required before connecting this to production workloads.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-liranudi-web-pilot-eb-pilot-2/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

14,872 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: web-pilot
description: Search the web and read page contents without API keys. Use when you need to search via DuckDuckGo/Brave/Google (multi-page), extract readable text from URLs, browse interactively with a persistent visible browser (with tabs, click, screenshot, text search), download files/PDFs, or dismiss cookie banners. Supports JSON/markdown/text output. Powered by Playwright + Chromium.
---

# Web Pilot

Four scripts, zero API keys. All output is JSON by default.

**Dependencies:** `requests`, `beautifulsoup4`, `playwright` (with Chromium).
**Optional:** `pdfplumber` or `PyPDF2` for PDF text extraction.

Install: `pip install requests beautifulsoup4 playwright && playwright install chromium`

## 1. Search the Web

```bash
python3 scripts/google_search.py "query" --pages N --engine ENGINE
```

- `--engine` — `duckduckgo` (default), `brave`, or `google`
- Returns `[{title, url, snippet}, ...]`

## 2. Read a Page (one-shot)

```bash
python3 scripts/read_page.py "https://url" [--max-chars N] [--visible] [--format json|markdown|text] [--no-dismiss]
```

- `--format` — `json` (default), `markdown`, or `text`
- Auto-dismisses cookie consent banners (skip with `--no-dismiss`)

## 3. Persistent Browser Session

```bash
python3 scripts/browser_session.py open "https://url"              # Open + extract
python3 scripts/browser_session.py navigate "https://other"        # Go to new URL
python3 scripts/browser_session.py extract [--format FMT]          # Re-read page
python3 scripts/browser_session.py screenshot [path] [--full]      # Save screenshot
python3 scripts/browser_session.py click "Submit"                  # Click by text/selector
python3 scripts/browser_session.py search "keyword"                # Search text in page
python3 scripts/browser_session.py tab new "https://url"           # Open new tab
python3 scripts/browser_session.py tab list                        # List all tabs
python3 scripts/browser_session.py tab switch 1                    # Switch to tab index
python3 scripts/browser_session.py tab close [index]               # Close tab
python3 scripts/browser_session.py dismiss-cookies                 # Manually dismiss cookies
python3 scripts/browser_session.py close                           # Close browser
```

- Cookie consent auto-dismissed on open/navigate
- Multiple tabs supported — open, switch, close independently
- Search returns matching lines with line numbers
- Extract supports json/markdown/text output

## 4. Download Files

```bash
python3 scripts/download_file.py "https://example.com/doc.pdf" [--output DIR] [--filename NAME]
```

- Auto-detects filename from URL/headers
- PDFs: extracts text if pdfplumber/PyPDF2 installed
- Returns `{status, path, filename, size_bytes, content_type, extracted_text}`

README.md

# 🌐 Web Pilot — OpenClaw Skill

[![Ko-fi](https://img.shields.io/badge/Ko--fi-Support%20this%20project-FF5E5B?logo=ko-fi&logoColor=white)](https://ko-fi.com/liranudi)

A web search, page reading, and browser automation skill for [OpenClaw](https://github.com/openclaw/openclaw). No API keys required.

## ♿ Accessibility

This skill enables AI agents to **read, navigate, and interact with the web on behalf of users** — making it a powerful accessibility tool for people with visual impairments, motor disabilities, or cognitive challenges.

- **Screen reading on steroids** — extracts clean, structured text from any webpage, stripping away visual clutter, ads, and navigation noise
- **Voice-driven browsing** — when paired with an AI assistant, users can browse the web entirely through natural language ("scroll down", "click Sign In", "read me the Overview section")
- **Targeted content extraction** — grab specific sections, search for text, or screenshot regions without needing to visually scan a page
- **Form interaction** — fill inputs and submit forms via commands, removing the need for precise mouse/keyboard control
- **Cookie banner removal** — automatically dismisses consent popups that are notoriously difficult for screen readers

## Features

- **Web Search** — Multi-engine (DuckDuckGo, Brave, Google) with pagination
- **Page Reader** — Extract clean text from any URL with JS rendering
- **Persistent Browser** — Visible or headless browser with 20+ actions
- **Cookie Auto-Dismiss** — Automatically clears cookie consent banners
- **File Download** — Download files with auto-detection, PDF text extraction
- **Output Formats** — JSON, markdown, or plain text
- **Zero API Keys** — Everything runs locally
- **Partial Screenshots** — Capture viewport, full page, single elements, or ranges between two elements

## Requirements

- Python 3.8+
- `pip install requests beautifulsoup4 playwright Pillow`
- `playwright install chromium`
- Optional: `pip install pdfplumber` for PDF text extraction

## Installation

### As an OpenClaw Skill

```bash
cp -r web-pilot/ $(dirname $(which openclaw))/../lib/node_modules/openclaw/skills/web-pilot
```

### Standalone

```bash
git clone https://github.com/LiranUdi/web-pilot.git
cd web-pilot
pip install requests beautifulsoup4 playwright Pillow
playwright install chromium
```

## Usage

### 1. Search the Web

```bash
python3 scripts/google_search.py "search term" --pages 3 --engine brave
```

| Flag | Description | Default |
|------|-------------|---------|
| `--pages N` | Result pages (~10 results each) | 1 |
| `--engine` | `duckduckgo`, `brave`, or `google` | duckduckgo |

**Engine notes:**
- **duckduckgo** — Most reliable, no CAPTCHA
- **brave** — More results per page, broader sources
- **google** — Often blocked by CAPTCHA; last resort

### 2. Read a Page

```bash
python3 scripts/read_page.py "https://example.com" --max-chars 10000 --format markdown
```

| Flag | Description | Default |
|------|-------------|----

_meta.json

{
  "ownerId": "kn72vgg7f9v52jr01p0yamfz1n81b8n5",
  "slug": "web-pilot",
  "version": "1.0.0",
  "publishedAt": 1771349856982
}

skill-card.md

## Description:

Web Pilot lets agents search the web, extract readable page text, run persistent browser sessions, download files and PDFs, dismiss cookie banners, and return JSON, markdown, or text without API keys.

This skill is ready for commercial/non-commercial use.

## Publisher:

[liranudi](https://clawhub.ai/user/liranudi)

### License/Terms of Use:

MIT

## Use Case:

Developers, engineers, and agent users use this skill to search the web, extract readable page text, run stateful browser actions, capture screenshots, and download files without external API keys. It can support accessibility workflows where an agent reads, navigates, and interacts with webpages on a user's behalf.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Broad browser automation can interact with websites, click controls, fill forms, execute JavaScript, and preserve session state.

Mitigation: Use the skill only in isolated environments or for trusted tasks, supervise authenticated or sensitive browsing, and review actions before form submission.

Risk: Search queries, page interactions, and downloaded content can expose sensitive information or introduce untrusted files.

Mitigation: Avoid secrets in search queries, treat downloaded files as untrusted, and scan or sandbox downloaded artifacts before opening them.

Risk: Persistent browser and download behavior has weak local controls according to the security summary.

Mitigation: Avoid shared or high-trust environments unless the persistent-browser and download handling are hardened.

## Reference(s):

- [Web Pilot ClawHub Skill Page](https://clawhub.ai/liranudi/skills/web-pilot)
- [OpenClaw Project](https://github.com/openclaw/openclaw)

## Skill Output:

**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]

**Output Format:** [JSON by default, with markdown and plain text options for page extraction]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May write downloaded files, screenshots, and PDF exports to local paths when those actions are requested.]

## Skill Version(s):

1.0.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Sponsored

Ads related to Web Pilot and adjacent AI workflows.