Install
Quick install
npx skills add https://github.com/SawyerHood/dev-browsernpx skills add SawyerHood/dev-browser --agent claude-codenpx skills add SawyerHood/dev-browser --agent cursornpx skills add SawyerHood/dev-browser --agent codexnpx skills add SawyerHood/dev-browser --agent opencodenpx skills add SawyerHood/dev-browser --agent github-copilotnpx skills add SawyerHood/dev-browser --agent windsurfMore install options
Shorthand — useful for multi-skill repos:
npx skills add SawyerHood/dev-browserManual — clone the repo and drop the folder into your agent's skills directory:
git clone https://github.com/SawyerHood/dev-browser.gitcp -r dev-browser ~/.claude/skills/Dev Browser
Web browser capability for agents
What is it?
A Claude Skill that gives AI agents the ability to use a web browser for development tasks. It provides browser automation capabilities including page navigation, content reading, form interaction, and screenshot capture. Essential for agents that need to interact with web applications during development and testing.
How to use it?
Install the skill and it enables Claude to:- Navigate to URLs and interact with web pages
- Read content from web pages including text and structured data
- Fill forms and click buttons for testing workflows
- Take screenshots for visual verification
- Execute JavaScript in the browser console
The browser runs in a controlled environment suitable for development and testing purposes.
Key Features
- Full browser automation for web development tasks
- Page navigation, content extraction, and form interaction
- Screenshot capture for visual verification and debugging
- JavaScript execution in browser console
- Suitable for testing web applications and UI workflows
- Controlled environment for safe browser automationView on GitHub
GitHub Stats
StarsForksLast UpdateAuthorSawyerHoodLicenseMITVersion1.0.0Categories
Developer ToolsTags
webdevFeatures
Related Skills
More from Developer ToolsAlgorithmic Art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration5.3kAnthropicCreativeDeveloper Tools00
Artifacts Builder
Build complex claude.ai HTML artifacts using React, Tailwind CSS, and shadcn/ui components5.3kAnthropicDeveloper Tools00
MCP Builder
Guide for creating high-quality MCP servers to integrate external APIs and services5.3kAnthropicDeveloper Tools00
---
Source: https://github.com/SawyerHood/dev-browser
Author: SawyerHood
License: https://opensource.org/licenses/MIT
GitHub Stars: 3554
Tags: web, dev
SKILL.md source
--- name: Dev Browser description: Web browser capability for agents --- # Dev Browser Web browser capability for agents What is it? A Claude Skill that gives AI agents the ability to use a web browser for development tasks. It provides browser automation capabilities including page navigation, content reading, form interaction, and screenshot capture. Essential for agents that need to interact with web applications during development and testing. ## How to use it? Install the skill and it enables Claude to: * Navigate to URLs and interact with web pages * Read content from web pages including text and structured data * Fill forms and click buttons for testing workflows * Take screenshots for visual verification * Execute JavaScript in the browser console The browser runs in a controlled environment suitable for development and testing purposes. ## Key Features * Full browser automation for web development tasks * Page navigation, content extraction, and form interaction * Screenshot capture for visual verification and debugging * JavaScript execution in browser console * Suitable for testing web applications and UI workflows * Controlled environment for safe browser automationView on GitHub ### GitHub Stats StarsForksLast UpdateAuthorSawyerHoodLicenseMITVersion1.0.0 ### Categories Developer Tools ### Tags webdev ### Features ## Related Skills More from Developer Tools ### Algorithmic Art Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration 5.3kAnthropicCreativeDeveloper Tools00 ### Artifacts Builder Build complex claude.ai HTML artifacts using React, Tailwind CSS, and shadcn/ui components 5.3kAnthropicDeveloper Tools00 ### MCP Builder Guide for creating high-quality MCP servers to integrate external APIs and services 5.3kAnthropicDeveloper Tools00 --- **Source**: https://github.com/SawyerHood/dev-browser **Author**: SawyerHood **License**: https://opensource.org/licenses/MIT **GitHub Stars**: 3554 **Tags**: web, dev
Related skills 6
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
secure-linux-web-hosting
Use when setting up, hardening, or reviewing a cloud server for self-hosting, including DNS, SSH, firewalls, Nginx, static-site hosting, reverse-proxying an app, HTTPS with Let's Encrypt or ACME clients, safe HTTP-to-HTTPS redirects, or optional post-launch network tuning such as BBR.
readme-i18n
Use when the user wants to translate a repository README, make a repo multilingual, localize docs, add a language switcher, internationalize the README, or update localized README variants in a GitHub-style repository.
lark-shared
Use when first setting up lark-cli, running auth login, switching user/bot identity (--as), handling permission denied or scope errors, needing to update lark-cli, or seeing _notice in JSON output.
improve-codebase-architecture
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.
paper-context-resolver
Optional RigorPilot helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacin...