agentleFS
mdiri-aimdiri-ai/SoduWork/skills/browser-use/SKILL.md

browser-use

Skill930 starsChanged 6 days agoMITView on GitHub

Use when a real web page must be opened, inspected, interacted with, or validated end to end without connecting to the user's existing browser.

55 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use context7-efficient, configuring-dapr-pubsub and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • hfzarslanSkill

    context7-efficient

    Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.

    Also in 5 projects that use this

  • AbdullahMalik17Skill

    configuring-dapr-pubsub

    Configures Dapr pub/sub components for event-driven microservices with Kafka or Redis. Use when wiring agent-to-agent communication, setting up event subscriptions, or integrating Dapr sidecars. Covers component configuration, subscription patterns, publishing events, and Kubernetes deployment. NOT when using direct Kafka clients or non-Dapr messaging patterns.

    Also in 3 projects that use this

  • AbdullahMalik17Skill

    deploying-cloud-k8s

    Deploys applications to cloud Kubernetes (AKS/GKE/DOKS) with CI/CD pipelines. Use when deploying to production, setting up GitHub Actions, troubleshooting deployments. Covers build-time vs runtime vars, architecture matching, and battle-tested debugging.

    Also in 3 projects that use this

  • dycnnnbSkill

    remote-browser

    Controls a cloud browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web pages, fill forms, take screenshots, or expose local dev servers via tunnels.

    Also in 3 projects that use this

  • mjunaidcaSkill

    building-chatgpt-apps

    Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers. Use when building ChatGPT custom apps with visual UI components, embedded widgets, or rich interactive experiences. Covers widget architecture, MCP server setup with FastMCP, response metadata, and Developer Mode configuration. NOT when building standard MCP servers without widgets (use building-mcp-servers skill instead).

    Also in 3 projects that use this

  • mjunaidcaSkill

    building-chat-interfaces

    Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.

    Also in 3 projects that use this

  • +6 more from AbdullahMalik17

The file

Files
SKILL.md

Browser Use

用项目脚本通过 Chrome DevTools Protocol 驱动自己启动的隔离浏览器。零依赖,只用 Node 22+ 内置 WebSocket;普通会话拥有独立端口、临时用户目录、标记页和 20 分钟空闲看门狗;明确授权的发布任务可选择持久专用会话。

硬规则

  1. 不连接系统里已有的日常 Chrome/Edge。普通会话使用随机端口、独立临时 profile;明确授权的发布/运营任务可用 --persistent,默认专用端口 9337(SODUWORK_PUBLISH_BROWSER_PORT 可配置,0 自动分配)。两种模式都核对归属标记;端口占用时拒绝接管或关闭其他浏览器。
  2. 普通工作流复用同一个 --session,不同任务使用不同 ID,结束后 close。用户明确要求记住登录态的发布任务使用 --persistent 和用户/空间隔离的稳定 ID,跨任务复用;窗口保留,不运行临时会话清理。显式 close --persistent 仅关闭本会话,不删除 profile;并发启动有锁。
  3. 导航只接受 http、https、file 和 about:blank,拒绝带账号密码的 URL;导航失败、CDP 断开、元素不存在或不可编辑都会返回非零退出码。
  4. 不替用户登录或保存凭据,除非当前请求明确授权;不把凭据写入参数、日志、截图。不要点删除、下单、发布等不可逆按钮,除非请求正文明确要求。

快速参考

S=skills/browser-use/scripts/browser.mjs
node $S shot https://example.com out.png --session task-123
node $S text current --session task-123
node $S errors current --session task-123
node $S do current '[{"click":"#open"},{"wait":300},{"shot":"after.png"},{"text":true}]' --session task-123
node $S status --session task-123
node $S close --session task-123

do 支持 goto、click、fill、upload(输入框、文本域和 contenteditable)、wait、eval、shot、text,一次最多 50 步;单步等待最多 30 秒、总等待最多 2 分钟。动作在连接浏览器前先校验,避免无效 JSON 启动会话。点击会自动滚动到可见区域并拒绝隐藏、禁用元素;截图会自动创建父目录。

验证与交付

先用 text 或 shot确认页面和目标,再执行点击/填写;关键动作前后各留一张截图。用 errors 检查控制台,用 status确认会话仍在运行,完成后关闭会话。把页面文字、截图路径和实际结果交回,不要只说“已操作”。

自动发布专用浏览器

仅用户明确要求实际发布、保存登录态或复用该发布会话采集时启用;普通浏览保持临时隔离。使用可见窗口供用户登录/验证码,不能绕过人工验证。profile 位于当前操作系统用户的 SoduWork/publishing-browser 目录,不能复制到工程、日志或插件包。

node "$S" tabs current --persistent --session publishing-<user-workspace-hash>
node "$S" open-tab https://example.com/publish --persistent --session publishing-<user-workspace-hash>
node "$S" text current --tab <targetId> --persistent --session publishing-<user-workspace-hash>
node "$S" do current '[{"upload":{"sel":"input[type=file]","files":["C:/absolute/document.pdf"]}}]' --tab <targetId> --persistent --session publishing-<user-workspace-hash>

先 tabs 检查已有页,每个选定网站复用一个标签页;open-tab 返回 targetId,后续 --tab 只接受此受管浏览器内的标签页。upload 只接受 1..30 个已存在的本地绝对文件路径;先读取实际页面定位输入框,不猜选择器。普通 close 不影响持久会话;需要关闭时加 --persistent,登录态仍保留。测试可加 --headless;业务发布默认可见,等待人工时不能关闭。环境变量 SODUWORK_PUBLISH_BROWSER_ROOT 仅供隔离测试或管理员设定专用数据目录,不能指向日常浏览器 profile。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.