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

Meowhub Browser

by zhaojiaqi in zhaojiaqi/MeowHub

Browse the web using Browserless.io cloud browser service. An agent skill from zhaojiaqi/MeowHub.

GPL-3.0Auto-check passedData & Analytics

Install Meowhub Browser

skills CLI
$ npx skills add zhaojiaqi/MeowHub --skill meowhub-browser -a claude-code

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

GitHub CLI
$ gh skill install zhaojiaqi/MeowHub meowhub-browser --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/zhaojiaqi/MeowHub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/src/main/assets/meowhub-workspace/skills/meowhub-browser .claude/skills/meowhub-browser && 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
meowhub-browser
GitHub stars
111
Token cost
~1.6k tokens
SKILL.md length
321 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
GPL-3.0

At a glance

Browse the web using Browserless.io cloud browser service. An agent skill from zhaojiaqi/MeowHub.

  • Works in 5 steps: Get Page Content (HTML/Text) → Take Screenshot → Scrape Structured Data → …
  • You need to fetch web page content
  • SKILL.md covers When to Use This Skill, API Endpoint, Available Tools and Quick Reference, plus 4 more sections
  • Calls curl; reaches production-sfo.browserless.io and news.ycombinator.com

What it does

Meowhub Browser is an agent skill from zhaojiaqi/MeowHub. Browse the web using Browserless.io cloud browser service. Use this skill when you need to fetch web page content, take website screenshots, or scrape structured data from websites. This is a cloud-based browser that works in the Android/Termux environment where local Chrome is not available.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Web scraping and Schema markup. It works with Android and JavaScript. The repository describes itself as: AI Phone Avatar - Create your own phone automation skills with AI | AI 手机分身 - 让每个人都能制作自己的手机 AI 自动化技能. The licence is GPL-3.0.

When your agent uses it

  • You need to fetch web page content
  • Take website screenshots
  • Scrape structured data from websites

Example prompts

  • “/meowhub-browser”

Workflow steps

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

  1. Get Page Content (HTML/Text)
  2. Take Screenshot
  3. Scrape Structured Data
  4. Generate PDF
  5. Execute JavaScript

What it can do on your machine

Read from SKILL.md and the folder at commit 1e56439. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • production-sfo.browserless.io
    • news.ycombinator.com
    • github.com
    • spa-website.com

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Meowhub Browser loads about 1.6k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 321 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 zhaojiaqi/MeowHub at commit 1e56439, republished under its GPL-3.0 licence (© zhaojiaqi). 321 words, ~1,639 tokens.

Download SKILL.mdSave it as .claude/skills/meowhub-browser/SKILL.md (or your agent's skills folder).
name
meowhub-browser
description
Browse the web using Browserless.io cloud browser service. Use this skill when you need to fetch web page content, take website screenshots, or scrape structured data from websites. This is a cloud-based browser that works in the Android/Termux environment where local Chrome is not available.

MeowHub Cloud Browser (Browserless.io)

You have access to a cloud-based headless browser through Browserless.io. Use this when OpenClaw's built-in browser tool fails (which happens in Android/Termux environments without local Chrome).

When to Use This Skill

  • OpenClaw's browser tool reports: "No supported browser found"
  • You need to fetch content from JavaScript-heavy websites (SPAs)
  • You need to take screenshots of web pages
  • You need to scrape structured data from websites

API Endpoint

Base URL: https://production-sfo.browserless.io
Token: 2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc

Available Tools

1. Get Page Content (HTML/Text)

Fetches the rendered HTML content of a webpage (after JavaScript execution).

bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/content?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{"url": "https://example.com"}'

Response: Raw HTML content of the page.

2. Take Screenshot

Captures a screenshot of a webpage.

bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/screenshot?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://example.com",
    "options": {
      "type": "png",
      "fullPage": false
    }
  }' \
  -o /tmp/screenshot.png

Parameters:

  • type: "png" or "jpeg"
  • fullPage: true for full page, false for viewport only
  • quality: 0-100 (jpeg only)
3. Scrape Structured Data

Extract specific elements from a webpage.

bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/scrape?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://example.com",
    "elements": [
      {"selector": "h1"},
      {"selector": "p"},
      {"selector": "a", "timeout": 5000}
    ]
  }'

Response: JSON array with extracted elements.

4. Generate PDF

Create a PDF from a webpage.

bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/pdf?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://example.com",
    "options": {
      "format": "A4",
      "printBackground": true
    }
  }' \
  -o /tmp/page.pdf
5. Execute JavaScript

Run custom JavaScript on a page and get results.

bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/function?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{
    "code": "module.exports = async ({ page }) => { await page.goto(\"https://example.com\"); return await page.title(); }"
  }'

Quick Reference

TaskEndpointKey Parameters
Get HTML content/chrome/contenturl
Screenshot/chrome/screenshoturl, options.type, options.fullPage
Scrape elements/chrome/scrapeurl, elements[].selector
Generate PDF/chrome/pdfurl, options.format
Run JS function/chrome/functioncode

Advanced Options

Wait for Element/Network
bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/content?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://example.com",
    "waitForSelector": {"selector": ".content", "timeout": 10000},
    "waitForTimeout": 2000
  }'
Set Viewport Size
bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/screenshot?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://example.com",
    "viewport": {"width": 1920, "height": 1080}
  }'
Block Ads/Trackers
bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/content?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://example.com",
    "blockAds": true
  }'

Error Handling

HTTP StatusMeaning
200Success
400Bad request (check JSON syntax)
401Invalid or expired token
429Rate limit exceeded
500Browser error (site may be blocking)

Usage Tips

  1. Always use $PREFIX/bin/curl - System curl is broken on Android
  2. For large pages, use /chrome/scrape to extract specific elements instead of full HTML
  3. For SPAs, add waitForSelector to ensure content is loaded
  4. Save screenshots to /tmp/ for temporary files
  5. Rate limits: Free tier has limited concurrent sessions, add small delays between requests

Examples

Get news headlines
bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/scrape?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://news.ycombinator.com",
    "elements": [{"selector": ".titleline > a"}]
  }'
Screenshot a webpage
bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/screenshot?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{"url": "https://github.com", "options": {"type": "jpeg", "quality": 80}}' \
  -o /tmp/github.jpg && echo "Screenshot saved to /tmp/github.jpg"
Get rendered text from SPA
bash
$PREFIX/bin/curl -s -X POST \
  'https://production-sfo.browserless.io/chrome/content?token=2U7NAYZYDRFMq5Kcaefbd50a04bd202480938068f2aadeefc' \
  -H 'Content-Type: application/json' \
  -d '{
    "url": "https://spa-website.com",
    "waitForSelector": {"selector": "#app-content", "timeout": 10000}
  }'

Note: This is a cloud service. All requests go through Browserless.io servers. Do not use for sensitive/private browsing. Token usage is metered.

© zhaojiaqi, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in app/src/main/assets/meowhub-workspace/skills/meowhub-browser of zhaojiaqi/MeowHub.

Open the folder on GitHubat commit 1e56439

Compare with similar skills

Meowhub Browser 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.

Meowhub Browser compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Meowhub Browser this skillzhaojiaqi/MeowHub111—~1.6kAutomated safety check: PassGPL-3.0
Agent Readiness Auditindranilbanerjee/digital-marketing-pro8621 repos~3.7kAutomated safety check: PassMIT
Axyusukebe/ax7191 repos~918Automated safety check: PassMIT
Chatgpt SearchSeifBenayed/cloclo114—~1.7kAutomated safety check: NotesMIT
SEO Firecrawlseranking/seo-skills161—~2.3kAutomated safety check: PassMIT
Facebook Page Postsbrowser-act/skills6.1k—~2.3kAutomated safety check: PassMIT

Similar skills

  • Agent Readiness Audit

    indranilbanerjee/digital-marketing-pro

    Audit agent readiness by script: AI-crawler rules, product schema, no-JS HTML, feeds.

    862 GitHub starsUsed in 1 repo~3.7k tokens
    Data & AnalyticsAuto-check passed

  • Ax

    yusukebe/ax

    Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or extract structured data from HTML.

    719 GitHub starsUsed in 1 repo~918 tokens
    Data & AnalyticsAuto-check passed

  • Chatgpt Search

    SeifBenayed/cloclo

    Search ChatGPT and extract the full response + hydration JSON that powers the UI.

    114 GitHub stars~1.7k tokensUpdated 6 mo ago
    Data & AnalyticsAuto-check: notes

  • SEO Firecrawl

    seranking/seo-skills

    Ad-hoc web scraping, site mapping, and full-site crawling via Firecrawl MCP.

    161 GitHub stars~2.3k tokensUpdated 3 mo ago
    Data & AnalyticsAuto-check passed

  • Facebook Page Posts

    browser-act/skills

    Scrapes posts from any public Facebook Page timeline, returning structured data including post text, author info, engagement metrics (likes/comments/shares), reaction breakdowns…

    6.1k GitHub stars~2.3k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed

  • Facebook Page Profile Posts

    browser-act/skills

    Scrapes posts from any public Facebook Page or personal Profile timeline, returning structured data including post text, author info with profile picture, engagement metrics (likes/comments/shares)…

    6.1k GitHub stars~2.7k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed

More from zhaojiaqi/MeowHub

  • Meowhub Device

    zhaojiaqi/MeowHub

    Control your Android phone via MeowHub — screenshot, tap, swipe, type, open apps, execute shell commands, make/accept/end calls, and control audio channels.

    111 GitHub stars~3.5k tokensUpdated 4 mo ago
    Auto-check passed

Works with

Categories

Questions about Meowhub Browser

What does Meowhub Browser do?

Browse the web using Browserless.io cloud browser service. An agent skill from zhaojiaqi/MeowHub. Meowhub Browser is an agent skill from zhaojiaqi/MeowHub.io cloud browser service.

When should I use Meowhub Browser?

Meowhub Browser fits situations like: you need to fetch web page content; take website screenshots; scrape structured data from websites.

How do I install Meowhub Browser in Claude Code?

Run `npx skills add zhaojiaqi/MeowHub --skill meowhub-browser -a claude-code`. Or copy the skill folder (app/src/main/assets/meowhub-workspace/skills/meowhub-browser in zhaojiaqi/MeowHub) into .claude/skills/meowhub-browser in your project. Claude Code loads it when a task matches its description.

How do I install Meowhub Browser in Codex?

Run `npx skills add zhaojiaqi/MeowHub --skill meowhub-browser -a codex`. Or copy the skill folder (app/src/main/assets/meowhub-workspace/skills/meowhub-browser in zhaojiaqi/MeowHub) into .agents/skills/meowhub-browser in your project. Codex loads it when a task matches its description.

Can I use Meowhub Browser 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 zhaojiaqi/MeowHub --skill meowhub-browser -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/meowhub-browser, .gemini/skills/meowhub-browser, .github/skills/meowhub-browser and .opencode/skills/meowhub-browser in your project.

What does Meowhub Browser need to run?

Going by SKILL.md and its folder, Meowhub Browser needs the command-line tools its instructions call (curl).

Does Meowhub Browser access the network?

SKILL.md names 4 domains. In commands or code: production-sfo.browserless.io, news.ycombinator.com, github.com and spa-website.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Meowhub Browser 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 Meowhub Browser use?

Meowhub Browser is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Meowhub Browser use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Meowhub Browser?

Skills that share tags, products or a category with Meowhub Browser: Agent Readiness Audit (indranilbanerjee/digital-marketing-pro, 862 stars), Ax (yusukebe/ax, 719 stars), Chatgpt Search (SeifBenayed/cloclo, 114 stars) and SEO Firecrawl (seranking/seo-skills, 161 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Meowhub Browser?

zhaojiaqi (a GitHub user) maintains it in zhaojiaqi/MeowHub, which has 111 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on June 7, 2026.

Source: zhaojiaqi/MeowHub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.