Abu Browser

Community

PM-Shawn

Abu-Browser

操作阿布应用内置的可见浏览器：打开网页、点击、填写、截图和提取数据。用户要求在阿布内预览或操作网页时使用；无需安装浏览器扩展。

Overview

Publisher	PM-Shawn
Repository	`Abu-Cowork`
Skill name	`Abu-Browser`
Stars	380
Forks	86
Bundled files	1
Links	Skill source Repository Homepage

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 PM-Shawn on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/PM-Shawn/Abu-Cowork.git /tmp/Abu-Cowork
mkdir -p .claude/skills
cp -r /tmp/Abu-Cowork/builtin-skills/Abu-Browser .claude/skills/Abu-Browser

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Abu Browser 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 Abu Browser 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 Abu Browser 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.

Abu-Browser

这是 Abu 随 Electron 客户端提供的内置浏览器。它会在 Abu 工作区中创建可见标签页，用户可以观察、接管或关闭。

Choosing and opening tabs

A top-level approved click or key press may open one same-origin native tab. Call abu-browser__list_tabs after a popup-producing action and use the returned tab IDs; retain the source page. Cross-origin/high-risk or delayed popups are blocked and need separate approval. Never recreate a rejected form POST with navigate, scripts, or a GET request.
Use abu-browser__close_tab only for unused background tabs created by this run. Keep comparison pages and deliverables open. If it returns requires_user_action, leave the page for the user; if closing, do not retry or force-close. Never bypass a refusal with scripts or other tools.
Start with abu-browser__list_tabs to discover existing task tabs without creating a page. Select targets by their returned URL, title and tabId; never guess IDs.
Use abu-browser__create_tab({ url }) for a new HTTP(S) page the user should keep separately. For a comparison of two pages, create one tab for each and retain both for the user to inspect. Do not navigate the first article to the second article's URL.
Use abu-browser__navigate({ tabId, url }) when intentionally continuing navigation in an existing tab, such as refining a search. Reuse an already-open matching page instead of creating duplicates.
get_tabs remains a compatibility entry that creates a blank tab if none exists. Prefer the explicit list/create tools for new work.
Observe with snapshot before interacting; re-observe after navigation or a significant page change. Wait for relevant content with wait_for before extracting or taking a screenshot.
Never substitute OS launch commands, Computer Use, Chrome or another browser for an unavailable built-in browser.

For locator, screenshot and extraction examples, read guide-basics.md.

表单与下拉

下拉一律用 select，一次调用搞定：定位到下拉控件本身、把选项文字作为 value 传进去。不要先点开下拉，也不要自己去点选项——select 会自己打开、找到、点中、关闭。原生 <select> 和 antd / Element Plus / Arco 的自定义下拉都支持；选项名写错时报错会列出实际可选项，照着重试即可。
execute_js 是最后手段，拥有页面的全部权限。读页面用 snapshot / extract_text / extract_table，等待用 wait_for，选下拉用 select；工具报错时先读错误信息，它通常已写明下一步。

安全

支付、删除、提交、发送等不可逆操作前先截图并获得用户确认。
不在用户未授权的页面输入密码、银行卡等敏感信息。
如果 abu-browser__ 工具不可用，明确说明内置浏览器当前没有准备好；不要静默切换到 Chrome、Computer Use 或系统浏览器。

确认操作结果，也不要用脚本

提交、保存这类操作之后要确认结果时：先 wait_for（等成功提示出现、或等 URL 变化），再 extract_text 读页面文字。不要写脚本去挂 fetch、翻 .ant-message、查 DOM——那样每查一次就打断用户一次。页面如果确实没有任何反馈，如实告诉用户"没有看到成功提示"，不要反复探测。

Before a child task finishes, use abu-browser__retain_tab({ tabId }) for each result or handoff page the user should keep. The host moves retained pages to the conversation; unused background pages may close safely. Never retry browser work after the child task has ended.

Embedded forms and control handback

Use snapshot's native frames list. Pass explicit frameId for region observations, locators (including qualified refs), and waits. Cross-origin regions need their own approval. After navigation, frame replacement or handback, observe again and discard old IDs.

While the user has control, stop tools and preserve their page. After cancellation or batch failure, inspect results; never replay writes automatically. Use approved upload_file inputs, not native pickers under automation. See guide-basics.md for details.

Bundled files

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

guide-basics.md4 KB

Frequently asked questions

What does the Abu Browser AI skill do?

操作阿布应用内置的可见浏览器：打开网页、点击、填写、截图和提取数据。用户要求在阿布内预览或操作网页时使用；无需安装浏览器扩展。

Why use Abu Browser on TypingMind?

Because you install it once and use it with any model. Abu Browser 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 Abu Browser in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/PM-Shawn/Abu-Cowork/tree/main/builtin-skills/Abu-Browser. 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 Abu Browser?

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 Abu Browser?

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

Is the Abu Browser AI skill free?

It is published on GitHub by PM-Shawn. Check the repository for licensing terms. 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.

View all

Deployment Patterns

affaan-m

CommunityPopular

Flujos de trabajo de despliegue, patrones de pipeline CI/CD, contenedorización Docker, health checks, estrategias de rollback y listas de verificación de preparación para producción de aplicaciones…

Django Patterns

Patrones de arquitectura Django, diseño de API REST con DRF, buenas prácticas de ORM, caché, señales, middleware y aplicaciones Django de nivel producción.

Docker Patterns

Patrones de Docker y Docker Compose para desarrollo local, seguridad de contenedores, networking, estrategias de volúmenes y orquestación de múltiples servicios.

E2e Testing

Patrones de pruebas E2E con Playwright, Page Object Model, configuración, integración CI/CD, gestión de artefactos y estrategias para pruebas inestables.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Abu-Browser

Choosing and opening tabs

表单与下拉

安全

确认操作结果，也不要用脚本

Embedded forms and control handback

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now