Agentcore

Run agent-browser on AWS Bedrock AgentCore cloud browsers. Use when the user wants to use AgentCore, run browser automation on AWS, use a cloud browser with AWS credentials, or needs a managed browser session backed by AWS infrastructure. Triggers include "use agentcore", "run on AWS", "cloud browser with AWS", "bed...

概览

Agentcore is a specialized skill designed to integrate the vercel-labs/agent-browser repository with AWS Bedrock AgentCore cloud browsers. This tool enables AI agents, such as Codex and Claude, to execute browser automation tasks within a managed AWS environment. By leveraging AWS infrastructure, users can run cloud-based browser sessions that utilize AWS credentials for secure and scalable operations. The skill is particularly useful for developers requiring managed browser environments without local setup. As part of the popular agent-browser project, which has garnered over 37,000 stars on GitHub, Agentcore provides a bridge between agentic workflows and cloud-native browser execution. It facilitates complex web interactions directly through AWS Bedrock, ensuring reliable performance for automated browsing requirements.

使用场景

Executing browser automation tasks within managed AWS Bedrock cloud environments.
Running cloud browser sessions that require integration with AWS credentials.
Scaling agentic web interactions using AWS-backed infrastructure instead of local resources.

安装说明

# Review source first
open https://github.com/vercel-labs/agent-browser/blob/main/skill-data/agentcore/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

安全提示

This skill utilizes AWS infrastructure to manage browser sessions, requiring appropriate AWS credentials for operation. Users should ensure that permissions are correctly configured within their AWS environment to maintain secure access to Bedrock AgentCore resources.

相关 Skills

CI Cd And Automation

addyosmani/agent-skills

DevOps

自动化 CI/CD 流水线设置。适用于设置或修改构建和部署流水线。当需要自动化质量门禁、在 CI 中配置测试运行器或建立部署策略时使用。

typescriptsecurity
80,654 StarsMIT

Core

vercel-labs/agent-browser

DevOps

Core agent-browser 使用指南。在运行任何 agent-browser 命令前请阅读此内容。涵盖了快照与引用(snapshot-and-ref)工作流、页面导航、元素交互(点击、填充、键入、选择)、提取文本和数据、截屏、标签页管理、表单与身份验证处理、等待内容加载、并行运行多个浏览器会话以及常见故障排除。当用户要求与网站交互、填写表单、点击内容、提取数据或截屏时使用。

CodexClaude
reacttesting
39,283 StarsApache-2.0

Agent Browser

vercel-labs/agent-browser

DevOps

为 AI 智能体提供的浏览器自动化 CLI。当用户需要与网站交互时使用,包括页面导航、填写表单、点击按钮、截取屏幕截图、提取数据、测试 Web 应用或自动化任何浏览器任务。触发场景包括“打开网站”、“填写表单”、“点击按钮”、“截屏”、“从页面抓取数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”等请求,或任何需要程序化 Web 交互的任务。还可用于

CodexClaude Code
testingbrowser
39,283 StarsApache-2.0

Cloudflare Email Service

cloudflare/skills

DevOps

使用 Cloudflare Email Service (Email Sending + Email Routing) 发送和接收事务性电子邮件。用于构建电子邮件发送(Workers 绑定或 REST API)、电子邮件路由、Agents SDK 电子邮件处理,或将电子邮件集成到任何应用程序中 — Workers、Node.js、Python、Go 等。还可用于电子邮件送达率、SPF/DKIM/DMARC、wrangler 电子邮件设置、MCP 电子邮件工具,或当编码代理需要发送电子邮件时。即使是像“为我的 Worker 添加电子邮件”这样的简单请求 — 此技能也包含关键配置

Claude CodeClaude
typescriptpython
2,491 StarsApache-2.0

Cloudflare

cloudflare/skills

DevOps

全面的 Cloudflare 平台技能,涵盖 Workers、Pages、存储(KV、D1、R2)、AI(Workers AI、Vectorize、Agents SDK)、特性标志(Flagship)、网络(Tunnel、Spectrum)、安全(WAF、DDoS)以及基础设施即代码(Terraform、Pulumi)。适用于任何 Cloudflare 开发任务。相比预训练知识,更倾向于从 Cloudflare 文档中检索信息。

securitybrowser
2,491 StarsApache-2.0

Agents SDK

cloudflare/skills

DevOps

使用 Agents SDK 在 Cloudflare Workers 上构建 AI 智能体。在创建有状态智能体、持久化工作流、实时 WebSocket 应用、定时任务、MCP 服务器、聊天应用、语音智能体或浏览器自动化时加载。涵盖 Agent 类、状态管理、可调用 RPC、Workflows、持久化执行、队列、重试、可观测性和 React hooks。倾向于从 Cloudflare 文档检索信息,而非依赖预训练知识。

typescriptreact
2,491 StarsApache-2.0