Skip to content
Agentmart
Submit a tool

browser-use

Drive a real browser to QA a running app.

Skill by Kripu77

IndexedMIT★ 7
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/kripu77-browser-use

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.

Use cases: testing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/browser-use

What's inside

Skill name
browser-use
Description
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
License
MIT
Instructions
42 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Browser use

## Trigger

Need to test a running web app by actually using it. No smoke suite, or the suite does not cover this flow.

Navigate, click, fill, screenshot, assert. Use the harness browser.

## How to drive the browser

Pick the door the runner actually has, in this order:

1. A first-party browser tool on this harness (Grok Bot browserUse, Grok Build browser, Claude computer use).
2. Headed Playwright against the given URL, if Playwright is already in the checkout.
3. Stop and say the harness has no browser.

Do not invent a headless stack. Do not scrape cookies out of a profile to skip login.

## Workflow

1. Resolve the target URL (dispatched, or local app for the repo). Confirm it is up before clicking.
2. Walk the flow as a user. One path. Screenshot each meaningful step.
3. Assert what the user would see: copy, state, error, navigation.
4. If login or 2FA is required, stop and hand that step to a human. Never ask for a password in chat. Never read `.env`.
5. Report. Repro, screenshots, what broke, what was fine.

## Guardrails

- Report only. Do not patch product code.
- Prefer a real click over injecting JS.
- Deterministic waits for visible state, not sleep.
- Stay on the dispatched flow. Do not wander the whole site.
- Never merge.

## Output

- Flow walked
- Screenshots of evidence
- Failures with repro steps
- Anything that could not be tested (auth wall, downed app)

From Kripu77/software-factory, MIT.

Signals

Stars
7
Forks
1
Open issues
7
Last commit (this folder)
Aug 28, 2026 (2 months ago)
Last release
Sep 3, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Kripu77

Cite this page

browser-use skill. Agent Mart. https://agentmart.dev/skills/kripu77-browser-use (last updated 2026-10-24)