Run any Skill in Manus with one click

browser-use

Stars1

Forks0

UpdatedApril 20, 2026 at 15:56

Web browser automation skill for navigating pages, filling forms, clicking elements, taking screenshots, and extracting web data using AI-driven browser control.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

sievepub-2000

sievepub-2000/octocode

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	browser-use
description	Web browser automation skill for navigating pages, filling forms, clicking elements, taking screenshots, and extracting web data using AI-driven browser control.

browser-use

Automate web browser interactions using AI-driven browser control.

When to use

The user needs to interact with a web page (fill forms, click buttons, navigate).
Web scraping or data extraction from dynamic pages is required.
Visual verification of web applications (screenshots, element inspection).
Testing web UIs or checking deployment status.

Instructions

Tool selection: Prefer the browser-use MCP server if available. Fallback to the built-in web-browse tool for simple page fetching.
Navigation: Use browser-use open <url> to navigate to pages. Wait for load completion.
Interaction sequence: Plan the interaction as a series of steps:
- open → navigate to URL
- click → click on element by selector or text
- type → enter text into input fields
- screenshot → capture current page state
- extract → pull structured data from page
Element identification: Use CSS selectors, ARIA labels, or visible text to identify elements. Prefer semantic selectors over brittle XPath.
Error handling: If an element isn't found, take a screenshot to diagnose, then retry with an alternative selector.
Data extraction: Output extracted data as structured JSON or Markdown tables.
Rate limiting: Add reasonable delays between actions to avoid rate limiting or bot detection.
Security: Never enter real credentials. Use test/demo accounts only. Never screenshot sensitive information.
Reference: browser-use/browser-use — 88k+ stars, MIT license, Python + Chromium required.

More from this repository

same repository

matt-pocock-engineering

sievepub-2000/octocode

Use when: applying Matt Pocock engineering skills for diagnosis, TDD, architecture improvement, issue breakdown, PRD creation, or rigorous TypeScript/codebase analysis.

2026-05-061

mattpocock-improve-codebase-architecture

sievepub-2000/octocode

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

2026-05-061

mattpocock-setup-matt-pocock-skills

sievepub-2000/octocode

Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.

2026-05-061

mattpocock-to-issues

sievepub-2000/octocode

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

2026-05-061

mattpocock-to-prd

sievepub-2000/octocode

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

2026-05-061

openai-plugins

sievepub-2000/octocode

Use when: working with OpenAI Codex plugins, plugin marketplaces, plugin manifests, plugin-bundled skills, or the openai/plugins repository. Helps inspect .codex-plugin/plugin.json, .agents/plugins/marketplace.json, and installed Codex plugin cache.

2026-05-061

name	browser-use
description	Web browser automation skill for navigating pages, filling forms, clicking elements, taking screenshots, and extracting web data using AI-driven browser control.

browser-use

Automate web browser interactions using AI-driven browser control.

When to use

The user needs to interact with a web page (fill forms, click buttons, navigate).
Web scraping or data extraction from dynamic pages is required.
Visual verification of web applications (screenshots, element inspection).
Testing web UIs or checking deployment status.

Instructions

Tool selection: Prefer the browser-use MCP server if available. Fallback to the built-in web-browse tool for simple page fetching.
Navigation: Use browser-use open <url> to navigate to pages. Wait for load completion.
Interaction sequence: Plan the interaction as a series of steps:
- open → navigate to URL
- click → click on element by selector or text
- type → enter text into input fields
- screenshot → capture current page state
- extract → pull structured data from page
Element identification: Use CSS selectors, ARIA labels, or visible text to identify elements. Prefer semantic selectors over brittle XPath.
Error handling: If an element isn't found, take a screenshot to diagnose, then retry with an alternative selector.
Data extraction: Output extracted data as structured JSON or Markdown tables.
Rate limiting: Add reasonable delays between actions to avoid rate limiting or bot detection.
Security: Never enter real credentials. Use test/demo accounts only. Never screenshot sensitive information.
Reference: browser-use/browser-use — 88k+ stars, MIT license, Python + Chromium required.