Browser

cloakbrowser-stealth

Name: cloakbrowser-stealth
Author: space-cadet

Stealth browser automation using CloakBrowser to bypass bot detection on protected sites. Use when web_fetch fails with anti-bot blocks, CAPTCHA, or access denied errors. Use for scraping reviews, protected pages, or any site that blocks standard Playwright/Puppeteer automation. Not for sites requiring login credentials or solving interactive CAPTCHAs.

What it does

**Use CloakBrowser when:** returns 403, bot challenge, or empty body Target uses standard fingerprint detection (WebDriver, plugins, WebGL) Reviews, public listings, non-login content

The skill document

CloakBrowser Stealth Fetch

Quick Start

Fetch content from a protected site:

cd ~/.openclaw/workspace/skills/cloakbrowser-stealth/scripts
python3 fetch.py "https://example.com" --wait-ms 3000

Common Patterns

Extract specific elements

python3 fetch.py "URL" --selector "[data-testid='review-title']" --output text

Full page with screenshot

python3 fetch.py "URL" --wait-ms 4000 --screenshot /tmp/page.png --output json

Humanize for aggressive detection

python3 fetch.py "URL" --humanize --wait-ms 5000

JSON output for structured processing

python3 fetch.py "URL" --output json | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['text'][:500])"

When It Works / When It Doesn't

Use CloakBrowser when:

web_fetch returns 403, bot challenge, or empty body
Target uses standard fingerprint detection (WebDriver, plugins, WebGL)
Reviews, public listings, non-login content

Don't use when:

Site requires login (use session cookies instead)
Interactive CAPTCHA (hCaptcha, reCAPTCHA v2 checkbox)
IP-reputation blocks (use proxy, see references/config.md)
Rate-limited after repeated requests

Exit Codes

Code	Meaning
0	Success, content extracted
1	Anti-bot blocked (check output for "blocked: true")
2	Navigation timeout or error
3	Script/dependency error

Script Reference

scripts/fetch.py — Unified fetch wrapper with anti-bot detection, element extraction, screenshot, JSON/text/html output

For full configuration options, proxy setup, and target site status: see references/config.md

Related skills

Playwright (Automation + MCP + Scraper)

Write, debug, and tune Playwright specs with locator strategy, trace diagnosis, and CI-aware timeouts.

by ivangdavila1.3k installs130 stars

Memory

Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.

by Iván559 installs18 stars

Join meeting

Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.

by johnpatternai22 installs8 stars

AdMapix

Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.

by fly0pants4.3k installs296 stars

diagram-generator

Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.

by nssa.io1.0k installs47 stars

Productivity

Find why your productivity system keeps failing, then apply the smallest fix — capacity math, bottleneck routing, durable local notes.

by Iván855 installs69 stars

More from space-cadet

Browse all skills

Mem Update Publish

Memory Bank Update Workflow — v6.12 compliant with project-repo awareness. Use when the user invokes $mem-update or asks for this workflow by name. Triggers on "update memory bank", "create edit chunk", "update tasks.md", "update session cache", "memory bank update workflow". NOT for database-native workflows (use mb-db-workflow instead).

by space-cadet2 installs