Skip to content
mcp/skillhub

Agent Skill

QA skill

qabrowser-use/browser-useskills/qa/SKILL.md

QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or app — including a local dev server (e.g. "qa test localhost:5173", "does the checkout work?", "rate this landing page"). Drives a real Browser Use cloud browser, tunneling localhost automatically.

119kMIT

always on

103 tokname + description

once used

2,124 tokSKILL.md body

bundled files

227 KB

repo stars

119kGitHub

Install the QA skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/browser-use/browser-use --skill qa

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/browser-use/browser-use.git /tmp/browser-use
mkdir -p ~/.claude/skills
cp -R /tmp/browser-use/skills/qa ~/.claude/skills/qa

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description103 tok
When the agent uses itThe SKILL.md instructions2,124 tok
Only if opened2 bundled files (27 KB)varies

Until it is used, qa costs about 13× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 7 skills from browser-use/browser-use would load 728 tokens of descriptions. Skills vs MCP study

Checks

  • Tells the agent to pipe a download into a shell (curl … | sh). That runs whatever the URL serves at that moment, with your permissions.

Pre-approved tools (allowed-tools): Bash, Read, Task. The agent can use these without asking while the skill is active.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • QA
  • Inputs
  • Can you see images? (decide this first)
  • Single flow vs. fan-out (only if you can see images)
  • Dependency: browser-harness (required — install it yourself)
  • Procedure

More skills from browser-use/browser-use

All skills in this repo
  1. browser-usebrowser-use/browser-use

    Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client.

    98k57 tok idle · 3,212 in use
  2. cloudbrowser-use/browser-use

    Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP WebSocket connections, stealth browsers, residential proxies, CAPTCHA handling, webhooks, workspaces, skills marketplace, liveUrl streaming, pricing, or integration patterns (chat UI, subagent, adding browser tools to existing agents). Also trigger for questions about n8n/Make/Zapier integration, Playwright/ Puppeteer/Selenium on cloud infrastructure, or 1Password vault integration. Do NOT use this for the open-source Python library (Agent, Browser, Tools config) — use the open-source skill instead.

    119k177 tok idle · 843 in use
  3. open-sourcebrowser-use/browser-use

    Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browser_use, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle hooks, MCP server setup, or monitoring/observability with Laminar or OpenLIT. Also trigger for questions about browser-use installation, prompting strategies, or sensitive data handling. Do NOT use this for Cloud API/SDK usage or pricing — use the cloud skill instead. Do NOT use this for directly automating a browser via CLI commands — use the browser-use skill instead.

    119k137 tok idle · 349 in use
  4. remote-browserbrowser-use/browser-use

    Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.

    119k22 tok idle · 550 in use
  5. x402browser-use/browser-use

    Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or "build it in" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.

    119k175 tok idle · 3,895 in use