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

Qwen Browser Use

by QwenLM in QwenLM/qwen-code

Controls the user's Chrome through Qwen Code's Node REPL and Browser SDK, with the Qwen Code Chrome extension, profile binding and tab ownership handling.

Apache-2.0Auto-check passedProductivity & Automation

Install Qwen Browser Use

skills CLI
$ npx skills add QwenLM/qwen-code --skill browser-use -a claude-code

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

GitHub CLI
$ gh skill install QwenLM/qwen-code browser-use --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/QwenLM/qwen-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/src/skills/bundled/browser-use .claude/skills/browser-use && 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
browser-use
GitHub stars
28k
Token cost
~1.6k tokens
SKILL.md length
741 words
Files
2
Skills in repo
41
Repo updated
First seen
Licence
Apache-2.0

At a glance

Controls the user's Chrome through Qwen Code's Node REPL and Browser SDK, with the Qwen Code Chrome extension, profile binding and tab ownership handling.

  • Automating tasks in the user's own signed-in Chrome profile
  • SKILL.md covers Setup, Interaction and Finish
  • Runs TypeScript scripts from its folder; calls node
  • Setting up the Qwen Code Chrome extension for browser control

What it does

Browser Use is bundled with Qwen Code and drives Chrome through the generic Node REPL MCP tools and the Qwen Code Chrome extension, so no separate extension or Browser Use MCP server is installed. First use registers a shared Native Messaging host on macOS and Linux, and the SDK checks the real connection rather than Chrome's extension preferences. If the extension does not connect, the agent asks you to open Chrome and check it in the intended profile, with a Chrome Web Store install or a build from packages/chrome-extension as the fallback.

Several Qwen sessions can share a profile, each controlling its own tabs, and a tab held by another session reports TAB_OWNERSHIP_CONFLICT. The runtime binds to the default Chrome profile unless you name one, and switching profiles needs node_repl_reset and a repeat of setup. A newer host is never downgraded, and host files can be inspected or removed with a native-host-setup script. The excerpt ends before the SDK usage steps.

When your agent uses it

  • Automating tasks in the user's own signed-in Chrome profile
  • Setting up the Qwen Code Chrome extension for browser control
  • Working with several Qwen sessions that each control their own tabs

Example prompts

  • “Open my work Chrome profile and fill out the expense form on the intranet page.”
  • “The Qwen Chrome extension will not connect, so walk me through checking it.”
  • “Use a second tab for this task because the first one is held by another Qwen session.”

Requirements

  • Google Chrome with the Qwen Code Chrome extension
  • The Node REPL MCP tools

What it can do on your machine

Read from SKILL.md and the folder at commit fe4d4e3. 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

    Ships script files (TypeScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

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

  • Network

    Links to these hosts (documentation or services it may open):

    • chromewebstore.google.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

Qwen Browser Use loads about 1.6k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 741 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
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 QwenLM/qwen-code at commit fe4d4e3, republished under its Apache-2.0 licence (© QwenLM). 741 words, ~1,593 tokens.

Download SKILL.mdSave it as .claude/skills/browser-use/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
browser-use
description
Control the user's Chrome through the existing persistent Node REPL and the Qwen Browser SDK.

Browser Use

Browser Use is bundled with Qwen Code and uses the generic Node REPL MCP tools and the Qwen Chrome extension. Do not install a separate Qwen extension or start a separate Browser Use MCP server.

Setup

Install and enable the Qwen Code Chrome extension in the profile the user wants to use. On macOS and Linux, first use of this SDK automatically registers the shared Native Messaging host in the user's installation directory. A browser task opts into this local setup, which can finish before the extension connects. The SDK checks the actual connection and protocol instead of reading Chrome's extension preferences.

If the extension does not connect, ask the user to open Chrome and check the extension in the intended profile. It installs from the Chrome Web Store: https://chromewebstore.google.com/detail/qwen-code/hdhmmjclhibojdddmancfgbkleahfaph

If the store reports it is not available in the user's region, they can build it from packages/chrome-extension in the Qwen Code repository (its README) and load dist/extension through chrome://extensions (Developer mode → Load unpacked). After installation or enabling it, retry the connection.

A usable Host of the same protocol is reused. A Host installed by a newer Qwen Code is never downgraded: if setup reports one, tell the user to update Qwen Code and stop. The Host files persist after Qwen exits. The user can inspect or remove them with node <skill-base>/runtime/scripts/native-host-setup.js status or uninstall; install explicitly switches the Host to this Qwen Code's copy from the next time Chrome starts it. A later Browser Use initialization can register the Host again. If required Host files cannot be read or written, report the failing action and path so the user can resolve access and retry.

Multiple Qwen sessions can use the same profile, each controlling its own tabs. A tab held by another session reports TAB_OWNERSHIP_CONFLICT. Use another tab or wait for that session to release it. The setup below binds the runtime to the default profile through browserAgent.browsers.get('chrome'). Only when the user names a specific Chrome profile, call browserAgent.browsers.list() before that line and pass the returned ID to browserAgent.browsers.get(id) instead. The runtime stays bound to the first profile it connects to; to switch profiles, call node_repl_reset and run the setup again.

If node_repl is unavailable, configure it with:

bash
qwen mcp add --scope user node-repl npx -y @qwen-code/node-repl-mcp@0.1.7

Then tell the user to restart Qwen Code and stop. Do not start a separate Browser Use MCP server. Screenshot metadata requires @qwen-code/node-repl-mcp 0.1.7 or later, so keep this exact pin.

Qwen reports the absolute Base directory for this skill when loading this file. Use that directory as <skill-base>. The bundled SDK ships with its dependencies: import it directly, without installing packages or registering module directories, replacing the example skill base below with that absolute path. If the import reports a missing file or an incomplete runtime, stop and report an incomplete Browser Use runtime instead of installing dependencies into the workspace:

js
globalThis.browserAgent ??= await (
  await import('/absolute/skill/base/runtime/index.js')
).setupBrowserRuntime();
globalThis.browser ??= await browserAgent.browsers.get('chrome');
nodeRepl.write(await browser.documentation());

Create a tab or claim an exact result returned by openTabs():

js
globalThis.tab = await browser.tabs.new();
await tab.goto('https://example.com/');
nodeRepl.write(await tab.playwright.domSnapshot());
js
const candidates = await browser.user.openTabs();
nodeRepl.write(candidates);
globalThis.tab = await browser.user.claimTab(
  candidates.find((candidate) => candidate.url === 'https://example.com/'),
);
Show full SKILL.md (257 more words)Show less

Interaction

Observe before acting and observe again after acting. Prefer semantic Playwright locators. Use tab.dom_cua.get_visible_dom() and its node_id values when snapshot refs are clearer, and use tab.cua for visual coordinate targets.

js
await tab.playwright.getByRole('button', { name: 'Continue' }).click();
await tab.playwright.getByLabel('Email').type('user@example.com');
await tab.dom_cua.click({ node_id: 'e4' });
await tab.dom_cua.type({ text: 'hello' });

When an action should navigate, arm the Playwright watcher around it:

js
await tab.playwright.expectNavigation(
  () => tab.playwright.getByRole('link', { name: 'Next' }).click(),
  { url: '**/next.html' },
);

Render screenshots with their metadata:

js
await nodeRepl.emitImage(await tab.screenshot());

The metadata reaches the model only through @qwen-code/node-repl-mcp 0.1.6 or later; an older server accepts the call and silently drops it. If node_repl was registered before this skill existed, check its command with qwen mcp list, and when it pins an older version, re-register it with the qwen mcp add command from Setup above and ask the user to restart Qwen Code.

Use tab.dev.logs() for bounded console diagnostics. Arm tab.playwright.waitForEvent('download' | 'filechooser') before the action that triggers it. Handle JavaScript dialogs through tab.getJsDialog(). Use a focused tab.playwright.evaluate() only when locators cannot obtain the needed data.

Use browser.user.history() only when the task needs browser history, with a focused query and bounded result count.

Finish

Treat browser.tabs.finalize({ keep }) as the final browser action of the turn. Omitted agent-created tabs close; omitted claimed tabs are released without closing. keep is the complete set for this call. Keep a user-facing result as deliverable, and keep a live page under control as handoff. Repeat a handoff in each later turn that still needs it; omitting it from the next finalize call or closing the runtime closes an agent-created tab.

js
await browser.tabs.finalize({
  keep: [{ tab, status: 'deliverable' }],
});

The Node kernel preserves globalThis and top-level bindings across cells. Keep cells short, await every Browser SDK promise, and use nodeRepl.write() to return text or structured data.

© QwenLM, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in packages/core/src/skills/bundled/browser-use of QwenLM/qwen-code.

  • SKILL.md
  • skill.test.ts

Open the folder on GitHubat commit fe4d4e3

Compare with similar skills

Qwen Browser Use 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.

Qwen Browser Use compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Qwen Browser Use this skillQwenLM/qwen-code28k—~1.6kAutomated safety check: PassApache-2.0
AIPex Browser ControlAIPexStudio/AIPex1.3k—~1.8kAutomated safety check: PassMIT
Neo4ier/neo756—~1.8kAutomated safety check: PassNone
Actionbook Browser Action Manualssmallnest/goclaw5981 repos~4.1kAutomated safety check: WarnMIT
Bump Versionopentabs-dev/opentabs967—~167Automated safety check: PassMIT
Competitor Monitorhanzili/hanzi-browse177—~2.8kAutomated safety check: PassCustom licence

Similar skills

  • AIPex Browser Control

    AIPexStudio/AIPex

    Lets an agent drive Chrome through the AIPex extension and its MCP bridge: navigation, clicking, form filling, screenshots, tab management and downloads.

    1.3k GitHub stars~1.8k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

  • Neo

    4ier/neo

    Browse websites, read web pages, interact with web apps, call website APIs, and automate web tasks.

    756 GitHub stars~1.8k tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check passed

  • Actionbook Browser Action Manuals

    smallnest/goclaw

    Looks up action manuals with verified selectors for multi-step website tasks, then drives the browser with the actionbook CLI in a dedicated or an existing Chrome session.

    598 GitHub starsUsed in 1 repo~4.1k tokens
    Productivity & AutomationAuto-check: warnings

  • Bump Version

    opentabs-dev/opentabs

    Bump package versions across all platform packages and plugins in lockstep.

    967 GitHub stars~167 tokensUpdated 5 days ago
    Productivity & AutomationAuto-check passed

  • Competitor Monitor

    hanzili/hanzi-browse

    Monitor competitor websites for changes. An agent skill from hanzili/hanzi-browse.

    177 GitHub stars~2.8k tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check passed

  • Browser Automation

    Prism-Shadow/penguin-harness

    Drive the PenguinHarness agent browser — the desktop app's built-in browser or the user's own Chrome — from the shell with penguin browser: open pages, read them as simplified HTML or text, act with…

    2.5k GitHub stars~2.9k tokensUpdated yesterday
    Productivity & AutomationAuto-check: warnings

More from QwenLM/qwen-code

All 41 skills in this repo

  • Agent Feature Reproduction

    QwenLM/qwen-code

    Reproduces a feature from Codex or Claude Code in Qwen Code by running the reference agent under capture, reading the traces, then implementing matching behavior.

    28k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Qwen Code E2E Testing

    QwenLM/qwen-code

    Guides end-to-end testing of the Qwen Code CLI in headless mode with real model calls, MCP test servers and inspection of raw API traffic.

    28k GitHub stars~2.1k tokensUpdated today
    Auto-check passed

  • Repo Hygiene Scan and Fix

    QwenLM/qwen-code

    Scheduled CI skill that scans a repository for small, certain docs, test and code hygiene issues and fixes them on one branch with a commit per finding.

    28k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Qwen Code Desktop Brand Builder

    QwenLM/qwen-code

    Builds a rebranded Qwen Code desktop package from the Tauri shell using only a brand id and a logo, with sensible derived defaults.

    28k GitHub stars~2.1k tokensUpdated today
    Auto-check passed

  • Qwen Code Memory Leak Debugger

    QwenLM/qwen-code

    Walks through capturing and comparing V8 heap snapshots to find memory leaks in the Qwen Code Node.js CLI, using tmux and the chrome-devtools CLI.

    28k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • tmux Real User Testing

    QwenLM/qwen-code

    Drives Qwen Code in a real tmux session the way a user would and saves a readable step-by-step transcript of each screen for maintainers to review.

    28k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Qwen Browser Use

What does Qwen Browser Use do?

Controls the user's Chrome through Qwen Code's Node REPL and Browser SDK, with the Qwen Code Chrome extension, profile binding and tab ownership handling. Browser Use is bundled with Qwen Code and drives Chrome through the generic Node REPL MCP tools and the Qwen Code Chrome extension, so no separate extension or Browser Use MCP server is installed. First use registers a shared Native Messaging host on macOS and Linux, and the SDK checks the real connection rather than Chrome's extension preferences.

When should I use Qwen Browser Use?

Qwen Browser Use fits situations like: automating tasks in the user's own signed-in Chrome profile; setting up the Qwen Code Chrome extension for browser control; working with several Qwen sessions that each control their own tabs.

How do I install Qwen Browser Use in Claude Code?

Run `npx skills add QwenLM/qwen-code --skill browser-use -a claude-code`. Or copy the skill folder (packages/core/src/skills/bundled/browser-use in QwenLM/qwen-code) into .claude/skills/browser-use in your project. Claude Code loads it when a task matches its description.

How do I install Qwen Browser Use in Codex?

Run `npx skills add QwenLM/qwen-code --skill browser-use -a codex`. Or copy the skill folder (packages/core/src/skills/bundled/browser-use in QwenLM/qwen-code) into .agents/skills/browser-use in your project. Codex loads it when a task matches its description.

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

What does Qwen Browser Use need to run?

Going by SKILL.md and its folder, Qwen Browser Use needs TypeScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Google Chrome with the Qwen Code Chrome extension; The Node REPL MCP tools.

Does Qwen Browser Use access the network?

SKILL.md names 1 domain. As links in the text: chromewebstore.google.com. This is read from the text; nothing was executed.

Is Qwen Browser Use 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 Qwen Browser Use use?

Qwen Browser Use is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Qwen Browser Use use?

About 1.6k tokens (SKILL.md is roughly 6.4k 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 Qwen Browser Use?

Skills that share tags, products or a category with Qwen Browser Use: AIPex Browser Control (AIPexStudio/AIPex, 1.3k stars), Neo (4ier/neo, 756 stars), Actionbook Browser Action Manuals (smallnest/goclaw, 598 stars) and Bump Version (opentabs-dev/opentabs, 967 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Qwen Browser Use?

QwenLM (a GitHub organization) maintains it in QwenLM/qwen-code, which has 28,349 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 8, 2026.

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