TypingMindTypingMindThe best frontend for AI
Browser Task logo

Browser Task

CommunityPopular
openakita
browser-task

Smart browser task agent - describe what you want done in natural language and it completes automatically. PREFERRED tool for multi-step browser operations like searching, form filling, and data extraction.

Overview

Publisheropenakita
Repositoryopenakita
Skill namebrowser-task
Stars
2K
Forks
284
Bundled files
1
LicenseAGPL-3.0
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by openakita on GitHub. Read the source before you install it.

Installation

Install the Browser Task AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/openakita/openakita/tree/main/skills/system/browser-task
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/openakita/openakita.git /tmp/openakita
mkdir -p .claude/skills
cp -r /tmp/openakita/skills/system/browser-task .claude/skills/browser-task
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Browser Task in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Browser Task on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Browser Task is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

browser_task - 智能浏览器任务

推荐优先使用 - 这是浏览器操作的首选工具。

基于 browser-use 开源项目实现。

用法

python
browser_task(
    task="要完成的任务描述",
    max_steps=15  # 可选，默认 15
)

参数

参数类型必填说明
taskstring是任务描述，用自然语言描述你想完成的操作
max_stepsinteger否最大执行步骤数，默认 15

何时使用（优先）

  • 任何涉及多步骤的浏览器操作
  • 网页搜索、表单填写、信息提取
  • 不确定具体操作步骤时
  • 复杂的网页交互流程

示例

搜索任务

python
browser_task(task="打开百度搜索福建福州天气")

表单填写

python
browser_task(task="打开 example.com 的注册页面，填写用户名 test123")

信息提取

python
browser_task(task="打开 GitHub 首页，获取今日热门项目的名称")

截图任务

python
browser_task(task="打开百度搜索福建福州，截图保存")

浏览器 & 网站操作工具选用指引

系统提供多条路径操作网站和浏览器，按场景选择最可靠的方案：

场景推荐工具说明
目标网站有 opencli adapteropencli_run（最可靠）确定性命令 + JSON 输出，复用 Chrome 登录态
需要登录但无 adapterbrowser_task → 手动组合先尝试 browser_task，失败则用 click/type 手动操作
仅需读取网页内容web_fetch最快最省资源，无需浏览器
仅需搜索web_searchDuckDuckGo 直接搜索
复杂多步浏览器交互browser_task适合登录、填表、筛选等
单步浏览器操作browser_navigate/browser_click 等精确控制单个操作
操作用户已登录的 Chromecall_mcp_tool("chrome-devtools", ...)需用户 Chrome 开启调试端口

决策顺序：opencli_run（有 adapter 时）→ web_fetch/web_search（只读时）→ browser_task → 手动 browser_click/type 组合 → chrome-devtools MCP。

何时使用细粒度工具

仅在以下情况使用 browser_navigate、browser_click 等细粒度工具：

  • browser_task 执行失败需要手动介入
  • 仅需单步操作（如只截图 browser_screenshot）
  • 需要精确控制特定元素

返回值

json
{
    "success": true,
    "result": {
        "task": "打开百度搜索福建福州",
        "steps_taken": 5,
        "final_result": "搜索完成，已显示福建福州相关结果",
        "message": "任务完成: 打开百度搜索福建福州"
    }
}

注意事项

  1. 任务描述要清晰具体，避免歧义
  2. 复杂任务可能需要增加 max_steps
  3. 首次使用会自动启动浏览器（可见模式）
  4. 自动继承系统 LLM 配置，无需额外配置 API Key

技术细节

  • 通过 CDP (Chrome DevTools Protocol) 复用 OpenAkita 已启动的浏览器
  • 自动继承 OpenAkita 系统配置的 LLM（来自 llm_endpoints.json）
  • 基于 browser-use 开源项目

高级：操作用户已打开的 Chrome

如果想让 OpenAkita 操作你已打开的 Chrome 页面，需要以调试模式启动 Chrome：

Windows:

cmd
"C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222

macOS:

bash
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222

Linux:

bash
google-chrome --remote-debugging-port=9222

启动后，OpenAkita 会自动检测并连接，可以操作你已打开的标签页。

相关技能

  • browser_screenshot - 单独截图
  • browser_navigate - 单独导航
  • deliver_artifacts - 发送结果给用户

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Browser Task AI skill do?

Smart browser task agent - describe what you want done in natural language and it completes automatically. PREFERRED tool for multi-step browser operations like searching, form filling, and data extraction.

Why use Browser Task on TypingMind?

Because you install it once and use it with any model. Browser Task is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Browser Task in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openakita/openakita/tree/main/skills/system/browser-task. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Browser Task?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Browser Task?

As many as you like. As long as a model supports skills, you can use Browser Task with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Browser Task AI skill free?

Yes. It is published on GitHub by openakita under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
openclaw logo

Release Openclaw Ci

openclaw
OrganizationPopular

Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

82.2K
391K
3 files
View
openclaw logo

Release Openclaw Mac

openclaw
OrganizationPopular

Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion.

82.2K
391K
Instructions
View
openclaw logo

Release Openclaw Maintainer

openclaw
OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

82.2K
391K
11 files
View
openclaw logo

Release Openclaw Plugin Testing

openclaw
OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

82.2K
391K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇