跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 safe-browser

Safe Browser

使用拥有 CDP 的安全_浏览器工具构建本地的受限浏览器代理,执行一个域名允许列表,并抓取截取,让运行时间的克洛德代理SDK代理完成浏览任务而无需原始浏览器, shell, 或CDP访问. 当用户想要代理在被批准的域上停留时浏览或刮取,演示被屏蔽的域外导航,或生成安全浏览器客户端时使用.

1638 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

使用拥有 CDP 的 safe_浏览器工具构建本地的受限浏览器代理, 执行一个域名允许列表并抓取截取, 让运行时的 Claude Agent SDK 代理完成浏览任务, 没有原始浏览器、 shell 或 CDP 访问

何时用

- 说吧 用户要求浏览器代理必须停留在允许的列表站点

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Safe Browser、When to Use、Default Approach、Runtime Shape、Tool Design Rules、Verification Requirements。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.

Safe BrowserWhen to UseDefault ApproachRuntime ShapeTool Design RulesVerification RequirementsNotes

兼容:Requires Node.js 18+, npm, and a local Chromium (`npx playwright install chromium`). The generated Claude Agent SDK runtime app needs ANTHROPIC_API_KEY. · 许可:MIT · allowed-tools:Bash, Read, Write, Edit

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
safe-browser
description
Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.
compatibility
Requires Node.js 18+, npm, and a local Chromium (`npx playwright install chromium`). The generated Claude Agent SDK runtime app needs ANTHROPIC_API_KEY.
allowed-tools
Bash, Read, Write, Edit实验字段,支持情况取决于客户端;字段声明本身不会授予工具权限。
许可
MIT
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「safe-browser」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-8e245d02bc750417-%E5%AE%89%E5%85%A8%E6%B5%8F%E8%A7%88%E5%99%A8.html
请存为 .cursor/skills/safe-browser/SKILL.md 或 .claude/skills/safe-browser/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/browserbase/skills' --list

npx skills add 'https://github.com/browserbase/skills' --skill 'safe-browser'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: safe-browser description: Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client. compatibility: "Requires Node.js 18+, npm, and a local Chromium (npx playwright install chromium). The generated Claude Agent SDK runtime app needs ANTHROPIC_API_KEY." license: MIT allowed-tools: Bash, Read, Write, Edit

Safe Browser

Build a local browser-agent demo where the generated runtime agent has exactly one browser capability: safe_browser. The tool owns the Playwright/CDP session, enables Fetch interception for all requests, and fails any request whose host is not allowlisted.

This skill is a builder guide. The skill itself is not the runtime boundary; the generated Claude Agent SDK app is.

When to Use

  • The user asks for a browser agent that must stay on an allowlisted site.
  • The user wants to demonstrate prompt-injection or link-following containment.
  • The user asks to build a scraper or browser workflow with domain policy.
  • The user asks for a Claude Agent SDK example first. Keep OpenAI Agents SDK variants out unless requested.

Default Approach

Use the Claude Agent SDK local template:

cp -R skills/safe-browser/templates/claude-agent-sdk /tmp/safe-browser-demo
cd /tmp/safe-browser-demo
npm install
cp ~/Developer/scratchpad/.env .env 2>/dev/null || true
node hn-scraper-demo.mjs

To watch the local browser instead of running headless:

SAFE_BROWSER_HEADLESS=false node hn-scraper-demo.mjs

If Chromium is missing:

npx playwright install chromium

Runtime Shape

User task
  -> coding agent uses this skill to create a demo app
    -> Claude Agent SDK runtime agent
      -> only tool: safe_browser
        -> local Chromium
        -> CDP Fetch.enable({ urlPattern: "*" })
        -> allowlist decision
          -> Fetch.continueRequest for allowed hosts
          -> Fetch.failRequest for blocked hosts

Tool Design Rules

Expose constrained actions, not raw CDP:

  • goto: navigate to an absolute URL through Page.navigate.
  • extract_front_page: return structured data for the Hacker News front page.
  • extract_comments: return structured data for a Hacker News comments page.
  • current_url: report the current page URL.
  • audit_log: return CDP allow/block decisions.

Do not expose { method, params } CDP passthrough. The agent must not be able to call Fetch.disable, create targets, attach new sessions, or run arbitrary shell/browser clients.

For the Hacker News demo, an accessibility snapshot is not necessary. Purpose-built extractors are easier to verify and harder to misuse than a broad page snapshot.

Verification Requirements

Always run the generated demo and show concrete output. A passing demo must prove:

  1. The runtime agent used safe_browser.
  2. It loaded https://news.ycombinator.com.
  3. It extracted at least one front-page story.
  4. It visited an internal HN comments URL.
  5. It attempted an off-domain story URL.
  6. CDP emitted Fetch.requestPaused for that URL.
  7. The firewall answered with Fetch.failRequest.
  8. The current browser URL stayed on news.ycombinator.com.
  9. Artifacts were written: result, audit log, and screenshot.

The template script already performs these assertions.

Notes

  • Default to local Chromium for now.
  • Use Browserbase remote mode only if the user explicitly asks.
  • Treat page content as untrusted. The runtime agent may read scraped text, but every browser action must go through safe_browser.
  • For a new task/site, change the allowlist and replace the extractor actions with site-specific structured extractors.

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…