awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
browserbase avatar

browserbase/skills

0
View on GitHub↗

Skills

This repository is a collection of installable browser automation skills and plugins for AI coding agents such as Claude Code. Once installed, whether through a plugin marketplace or a single command, each agent can drive real web browsers from the command line for navigation, testing, scraping, and research. Browsers can be remote cloud sessions with CAPTCHA solving, residential proxies, and a persistent identity, or local ones: either a clean isolated browser or an already running browser whose cookies and login state are reused.

Beyond basic browsing, the skills cover several specialized workflows. Agents can act inside signed-in sessions without asking for credentials, and cookies can be synced from a local profile into a persistent cloud browser context. Captured browser traces can be analyzed to produce a best-effort OpenAPI 3.1 description of a site's endpoints, and site-specific tools can be authored from a site's routes, forms, and actions. Other skills improve agent prompts and browsing tasks through repeated runs, trace analysis, scoring, and unchanged confirmation runs. Further skills let AI exercise a locally running web app to find bugs and apply fixes, test UI changes adversarially, and audit how friendly a product or docs site is to agents.

The wider surface includes fetching static pages and searching the web without starting a browser, summarizing pages, and researching companies, prospects, and competitors into reports. Cloud tooling covers listing projects as JSON, deploying and scaffolding serverless browser functions, and migrating Python automation to TypeScript. Browser traces can be recorded and split into per-page groups for debugging. Agents can also be limited to allowlisted domains or to a scraper's main site.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI
www.browserbase.com/SKILL.md
↗

Features

  • AI Agent Skills - Ships a bundle of installable agent skills and plugins that teach coding agents to drive web browsers for navigation, testing, scraping, and research.
  • Browser Automation Agents - Gives coding agents the ability to drive real web browsers from the command line, including signed-in sessions, remote browsers, and persistent identity.
  • Command-Line Browser Control - Lets coding agents drive real web browsers from the command line, using remote sessions with CAPTCHA solving, residential proxies, and a persistent identity.
  • Agent Skill Installers - Bundles installable skills that teach coding agents to drive web browsers for navigation, testing, scraping, and research tasks.
  • Multi-Agent Skill Installers - Adds a collection of browser automation skills to popular coding agents with a single command so each can drive browsers right after setup.
  • Self-Improving Agent Optimization Loops - Improves agent prompts through repeated runs, trace analysis, scoring, and unchanged confirmation runs until results pass reliably.
  • Agentic Plugin Marketplaces - Distributes browsing plugins and skills for popular coding assistants through plugin marketplaces or a single install command.
  • Cloud Browser Provisioners - Runs browsers in the cloud with CAPTCHA solving, residential proxies, cookie syncing from local profiles, and serverless automation on demand.
  • Cloud Browser Integrations - Runs browsers in the cloud with CAPTCHA solving, residential proxies, persistent identity, and serverless deployment of automation code driven from the command line.
  • Iterative Prompt Optimizers - Improves an agent's system prompt through repeated runs, message traces, session logs, and scoring, finishing with unchanged confirmation runs.
  • Self-Improving Browsing Tasks - Runs a browsing task repeatedly, reads the resulting trace, and improves the navigation instructions until the task passes reliably.
  • Search and Research - Fetches, searches, and reads web pages to summarize content and research companies and competitors into structured reports.
  • OpenAPI Specification Generators - Analyzes captured browser traces of a website to produce a best-effort OpenAPI specification of its endpoints.
  • Signed-In Session Collection - Completes multi-step web actions such as placing an order by reusing an existing signed-in browser session instead of asking for credentials.
  • Browser Cookie Imports - Copies cookies from a local browser profile into a persistent cloud browser context so automated sessions can reach login-protected sites.
  • API Specification Discovery from Traffic - Analyzes captured browser traces to generate OpenAPI specifications and builds site-specific tools from a website's routes, forms, and actions.
  • Traffic-Based API Spec Inference - Analyzes captured browser traces of a site's HTTP traffic to produce a best-effort OpenAPI 3.1 description of its endpoints.
  • Adversarial UI Testing - Analyzes code changes or explores a whole application with AI to find bugs and verify that user interface changes behave correctly.
  • Agentic Web UI Testing - Letting AI exercise a locally running web app's interface to find bugs, verify interface changes, and apply fixes directly to the code.
  • Autonomous Bug Fixing - Opens a locally running web app in a browser, exercises its interface to uncover bugs, and applies fixes directly to the code.
  • Site-Specific Tool Generators - Authors, compiles, and validates site-specific tool scripts and adds first-party tools to a web app based on its routes, forms, and actions.
3,756 stars·242 forks·JavaScript·1 view

Star history

Star history chart for browserbase/skillsStar history chart for browserbase/skills

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Projects sharing features with Skills

These projects share indexed features with Skills. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • microsoft/vscode-copilot-chatmicrosoft avatar

    microsoft/vscode-copilot-chat

    9,493View on GitHub↗

    This project is an AI-powered IDE extension and LLM coding assistant that provides a conversational interface for generating, refactoring, and debugging code. It functions as an AI agent framework and a Model Context Protocol client, connecting AI models to external data sources and tools to automate complex development tasks. The system is distinguished by its use of autonomous AI agents capable of multi-step task execution, including the ability to read files, modify code, and run terminal commands iteratively. It supports recursive agent orchestration through subagent delegation and employ

    TypeScript
    View on GitHub↗9,493
  • builderio/skillsBuilderIO avatar

    BuilderIO/skills

    4,650View on GitHub↗

    This is a curated collection of installable skills that extend AI coding agents with reusable workflows, instructions, and tool integrations. Skills can be added through an interactive command line installer or a plugin marketplace, at user or project level, with optional instruction blocks and a pull request recap action. The collection centers on overseeing and steering agent work. Some skills audit another agent's output by reconstructing the original request from a transcript, pull request, or branch and reporting gaps. Others compare competing agent plans and produce a decision memo befo

    JavaScriptskills
    View on GitHub↗4,650
  • google-gemini/computer-use-previewgoogle-gemini avatar

    google-gemini/computer-use-preview

    2,815View on GitHub↗

    This project is a browser automation system that connects Google's Gemini API to a web browser, enabling an AI agent to perform tasks on a user's behalf by interpreting natural language instructions. At its core, it operates through a continuous screenshot-based action loop, where the agent captures the browser's current state, sends the image to the Gemini model, and executes the model's returned commands to click, type, and navigate. The system distinguishes itself through a dual browser backend abstraction, supporting both local Playwright-controlled browsers and remote Browserbase cloud i

    Python
    View on GitHub↗2,815
  • vercel-labs/agent-browservercel-labs avatar

    vercel-labs/agent-browser

    46,764View on GitHub↗

    This project is an agentic framework designed to enable autonomous web navigation and browser automation. It functions as a controller that translates natural language instructions into deterministic browser actions, allowing agents to interact with websites, perform data extraction, and manage complex authentication flows. By leveraging accessibility trees and semantic element resolution, the framework mimics human-like navigation, moving beyond brittle DOM selectors to interact reliably with modern web interfaces. The framework distinguishes itself through its focus on secure, scalable exec

    Rust
    View on GitHub↗46,764
Compare all 30 related projects→

Frequently asked questions

What does browserbase/skills do?

This repository is a collection of installable browser automation skills and plugins for AI coding agents such as Claude Code. Once installed, whether through a plugin marketplace or a single command, each agent can drive real web browsers from the command line for navigation, testing, scraping, and research. Browsers can be remote cloud sessions with CAPTCHA solving, residential proxies, and a persistent identity, or local ones: either a clean isolated browser or an…

What are the main features of browserbase/skills?

The main features of browserbase/skills are: AI Agent Skills, Browser Automation Agents, Command-Line Browser Control, Agent Skill Installers, Multi-Agent Skill Installers, Self-Improving Agent Optimization Loops, Agentic Plugin Marketplaces, Cloud Browser Provisioners.

Which projects share features with browserbase/skills?

Projects with overlapping indexed features include: microsoft/vscode-copilot-chat — This project is an AI-powered IDE extension and LLM coding assistant that provides a conversational interface for… builderio/skills — This is a curated collection of installable skills that extend AI coding agents with reusable workflows, instructions,… google-gemini/computer-use-preview — This project is a browser automation system that connects Google's Gemini API to a web browser, enabling an AI agent… vercel-labs/agent-browser — This project is an agentic framework designed to enable autonomous web navigation and browser automation. It functions… testsprite/testsprite-cli — TestSprite CLI is a command-line tool for creating, running, and managing automated tests for web frontends and… mastra-ai/mastra — Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and…