How do I install the Browser skill?

Run npx skillmds@latest add yashaiguy-dev/browser in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Browser safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Browser?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Browser free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Browser?

yashaiguy-dev (@yashaiguy-dev) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Browser by yashaiguy-dev — Agent Skill

Name: Browser
Author: yashaiguy-dev

Browser

Control a real Chromium browser — navigate pages, click buttons, fill forms, take screenshots, read page content via accessibility tree. Use when the user asks to open a browser, visit a website, interact with a web page, or scrape visible content.

yashaiguy-dev ea2c341 5 files · 30.0 KB Updated Sep 17, 2026

File contents

Browser Control Skill

You have a browser control tool at ~/.qwen/skills/browser/browser_tool.py that controls a real visible Chromium browser via CDP.

First-Time Setup

If the tool isn't installed yet, run:

python3 ~/.qwen/skills/browser/browser_tool.py install

Architecture

launch starts Chromium as a detached process with --remote-debugging-port=9222
All other commands connect via CDP, do their work, disconnect
Browser stays open independently — no blocking needed
Persistent profile at ~/.browser-tool/profile/ — logins survive across sessions

Commands

BT="python3 ~/.qwen/skills/browser/browser_tool.py"

# Launch (NOT background — it detaches automatically)
$BT launch                      # Playwright
$BT launch --patchright          # Anti-detection mode
$BT launch --connect 9222       # Attach to existing Chrome

# Navigation & interaction
$BT navigate "https://example.com"
$BT click "button.submit"
$BT type "input[name=email]" "user@example.com"
$BT type "input[name=email]" "new@example.com" --clear

# Observation
$BT snapshot                     # accessibility tree — structured text, token-efficient
$BT snapshot --selector "main"   # scoped to a section
$BT screenshot                   # saves /tmp/browser_screenshots/latest.png
$BT screenshot --name "step1"    # saves /tmp/browser_screenshots/step1.png
$BT screenshot --full            # full page
$BT html                         # get full page HTML
$BT html --selector "div.main"   # get element HTML
$BT evaluate "document.title"    # run JS

# Waiting
$BT wait --selector "div.loaded" --timeout 15

# Management
$BT pages                        # list tabs
$BT status                       # check if running
$BT close                        # kill browser

Rules

Launch first — always run launch before any other command
Use snapshot for AI reasoning — when you need to understand page structure, use snapshot first — it's faster and more accurate than screenshots
Use Patchright for sites with Cloudflare, DataDome, or other bot detection
Profile persists — user logs in once, stays logged in next time
launch is NOT blocking — it detaches the browser process and returns immediately

---name: browserdescription: Control a real Chromium browser — navigate pages, click buttons, fill forms, take screenshots, read page content via accessibility tree. Use when the user asks to open a browser, visit a website, interact with a web page, or scrape visible content.---# Browser Control SkillYou have a browser control tool at `~/.qwen/skills/browser/browser_tool.py` that controls a real visible Chromium browser via CDP.## First-Time SetupIf the tool isn't installed yet, run:```bashpython3 ~/.qwen/skills/browser/browser_tool.py install```## Architecture- `launch` starts Chromium as a **detached process** with `--remote-debugging-port=9222`- All other commands **connect via CDP**, do their work, disconnect- Browser stays open independently — no blocking needed- Persistent profile at `~/.browser-tool/profile/` — logins survive across sessions## Commands```bashBT="python3 ~/.qwen/skills/browser/browser_tool.py"# Launch (NOT background — it detaches automatically)$BT launch # Playwright$BT launch --patchright # Anti-detection mode$BT launch --connect 9222 # Attach to existing Chrome# Navigation & interaction$BT navigate "https://example.com"$BT click "button.submit"$BT type "input[name=email]" "user@example.com"$BT type "input[name=email]" "new@example.com" --clear# Observation$BT snapshot # accessibility tree — structured text, token-efficient$BT snapshot --selector "main" # scoped to a section$BT screenshot # saves /tmp/browser_screenshots/latest.png$BT screenshot --name "step1" # saves /tmp/browser_screenshots/step1.png$BT screenshot --full # full page$BT html # get full page HTML$BT html --selector "div.main" # get element HTML$BT evaluate "document.title" # run JS# Waiting$BT wait --selector "div.loaded" --timeout 15# Management$BT pages # list tabs$BT status # check if running$BT close # kill browser```## Rules1. **Launch first** — always run `launch` before any other command2. **Use snapshot for AI reasoning** — when you need to understand page structure, use `snapshot` first — it's faster and more accurate than screenshots3. **Use Patchright** for sites with Cloudflare, DataDome, or other bot detection4. **Profile persists** — user logs in once, stays logged in next time5. **launch is NOT blocking** — it detaches the browser process and returns immediately

Frequently asked questions