MCP.directory

browser-setup-devtools

by different-ai
24
3
Source

Guide users through browser automation setup using Chrome DevTools MCP as the primary path and the OpenCode browser extension as a fallback. Use when the user asks to set up browser automation, Chrome DevTools MCP, browser MCP, browser extension, or runs the browser-setup command.

Install

mkdir -p .claude/skills/browser-setup-devtools && curl -L -o skill.zip "https://mcp.directory/api/skills/download/1504" && unzip -o skill.zip -d .claude/skills/browser-setup-devtools && rm skill.zip

Installs to .claude/skills/browser-setup-devtools

About this skill

Browser automation setup (DevTools MCP first)

Principles

  • Keep prompts minimal; do as much as possible with tools and commands.
  • Always attempt Chrome DevTools MCP first; only fall back to the browser extension when DevTools MCP cannot be used.

Workflow

  1. Ask: "Do you have Chrome installed on this computer?"
  2. If no or unsure:
    • Offer to open the download page yourself and do it if possible.
    • Provide a clickable link: https://www.google.com/chrome/
    • Continue after installation is confirmed.
  3. Check DevTools MCP availability:
    • Call chrome-devtools_list_pages.
    • If pages exist, select one with chrome-devtools_select_page.
    • If no pages, create one with chrome-devtools_new_page (use https://example.com) and then select it.
  4. If DevTools MCP calls fail:
    • Ask the user to open Chrome and keep it running.
    • Retry chrome-devtools_list_pages.
    • If it still fails, ensure opencode.jsonc includes mcp.control-chrome with command ['chrome-devtools-mcp'] and ask the user to restart OpenWork/OpenCode.
    • Retry the DevTools MCP check.
  5. If DevTools MCP is ready:
    • Offer a first task ("Let's try opening a webpage").
    • If yes, use chrome-devtools_navigate_page or chrome-devtools_new_page to open the URL and confirm completion.
  6. Fallback only if DevTools MCP cannot be used:
    • Check availability with browser_version or browser_status.
    • If missing, run npx @different-ai/opencode-browser install yourself.
    • Open the Extensions page yourself when possible:
      • macOS: open -a "Google Chrome" "chrome://extensions"
      • Windows: start chrome://extensions
      • Linux: xdg-open "chrome://extensions"
    • Tell the user to enable Developer mode, click "Load unpacked", and select ~/.opencode-browser/extension, then pin the extension.
    • Re-check availability with browser_version.
    • Offer a first task and use browser_open_tab.

Response rules

  • Keep each user prompt to one short sentence when possible.
  • Use direct offers like "I can open Chrome now" and follow with tool actions.
  • Always present links as clickable URLs.

More by different-ai

View all skills by different-ai →

opencode-bridge

different-ai

Bridge between OpenWork UI and OpenCode runtime

577

tauri-solidjs

different-ai

Tauri 2.x + SolidJS stack for OpenWork native app

443

openwork-core

different-ai

Core context and guardrails for OpenWork native app

51

opencode-mirror

different-ai

Maintain the local OpenCode mirror for self-reference

71

cargo-lock-manager

different-ai

Manages Cargo.lock file updates and resolves --locked flag issues in CI/CD. Triggers when user mentions: - "cargo test --locked failed" - "cannot update the lock file" - "Cargo.lock is out of date" - "PR failed with --locked error" - "fix Cargo.lock"

11

openwork-debug

different-ai

Debug OpenWork sidecars, config, and audit trail

11

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

1,5731,370

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

1,1161,191

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

1,4181,109

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

1,197748

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

1,154684

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

1,318617

Related MCP Servers

Browse all servers
Chrome DevTools MCPChrome DevTools MCP

AI-driven control of live Chrome via Chrome DevTools: browser automation, debugging, performance analysis and network mo

28,1380 tools
Chrome DevToolsChrome DevTools

Use Chrome DevTools for web site test speed, debugging, and performance analysis. The essential chrome developer tools f

28,13326 tools
Bright DataBright Data

Access real-time web scraping with Bright Data. Scrape any website and extract structured data easily using advanced web

2,1680 tools
OpenDiaOpenDia

OpenDia is a web based diagram tool enabling real-time collaborative diagram creation and editing via easy-to-use web in

1,78118 tools
ExcelExcel

Unlock powerful Excel automation: read/write Excel files, create sheets, and automate workflows with seamless integratio

8666 tools
HyperbrowserHyperbrowser

Hyperbrowser enables web scraping, internet scraping, and automation to scrape any website for data extraction or web cr

7420 tools

Stay ahead of the MCP ecosystem

Get weekly updates on new skills and servers.