⚠️

重要前提

安装AI Skills的关键前提是：必须科学上网，且开启TUN模式，这一点至关重要，直接决定安装能否顺利完成，在此郑重提醒三遍：科学上网，科学上网，科学上网。查看完整安装教程 →

Kernel Python SDK：浏览器自动化与Playwright服务器端执行开发工具包

kernel-python-sdk by kernel/skills

205 周安装量

3 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/kernel/skills --skill kernel-python-sdk

Python Web框架自动化测试

🇨🇳中文介绍

何时使用此技能

在以下场景中使用 Kernel Python SDK：

构建浏览器自动化脚本 - 创建控制远程浏览器的 Python 程序
执行服务器端自动化 - 直接在浏览器虚拟机中运行 Playwright 代码，无需本地依赖
以编程方式管理浏览器会话 - 通过代码创建、配置和控制浏览器
构建可扩展的爬虫/测试工具 - 使用浏览器池和配置文件进行大规模自动化
将自动化部署为动作 - 将脚本打包为 Kernel 动作，以便通过 API 调用

何时不应使用：

对于 CLI 命令（例如 kernel browsers create），请改用 kernel-cli 技能
对于快速的一次性任务，CLI 可能比编写代码更简单

核心概念

SDK 架构

SDK 按基于资源的模块进行组织：

kernel.browsers - 浏览器会话管理（创建、列出、删除）
kernel.browsers.playwright - 服务器端 Playwright 执行
kernel.browsers.computer - 操作系统级控制（鼠标、键盘、截图）

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

两种自动化方法

1. 服务器端执行（推荐）

使用 kernel.browsers.playwright.execute(session_id, code="...") 直接在浏览器虚拟机中执行 Playwright 代码
session_id 必须作为位置参数（第一个参数）传递，而不是作为 id= 关键字参数
通过 response.result 访问响应 - 必须在代码中使用 return 来获取数据
最适合：大多数用例、生产自动化、并行执行、动作

2. CDP 连接（客户端）

通过 CDP WebSocket URL 将 Playwright 连接到浏览器
代码在本地运行，浏览器在远程运行；需要本地安装 Playwright
最适合：复杂调试、特定的本地开发需求

标准：from kernel import Kernel
对于动作：import kernel 和 from kernel import Kernel
对于类型化负载：from typing import TypedDict
对于 CDP：from playwright.async_api import async_playwright

client = Kernel() 会自动从环境中读取 KERNEL_API_KEY

动作处理器模式

from typing import TypedDict
from kernel import Kernel

app = kernel.App("app-name")

class TaskInput(TypedDict):
    task: str

@app.action("action-name")
async def my_action(ctx: kernel.KernelContext, input_data: TaskInput):
    # 访问输入：input_data["task"] 或 input_data.get("task")
    ...

CDP 连接模式（客户端）

async with async_playwright() as playwright:
    browser = await playwright.chromium.connect_over_cdp(kernel_browser.cdp_ws_url)
    context = browser.contexts[0] if browser.contexts else await browser.new_context()
    page = context.pages[0] if context.pages else await context.new_page()

二进制数据处理

二进制数据（截图、PDF）以 Node.js Buffer 形式返回：{'data': [byte_array], 'type': 'Buffer'}

# 遵循上述规范模式，然后：
if response.success and response.result:
    data = bytes(response.result['data'])
    with open("output.png", "wb") as f:
        f.write(data)

uv pip install kernel 或 pip install kernel
对于 CDP：uv pip install playwright

🇺🇸English

When to Use This Skill

Use the Kernel Python SDK when you need to:

Build browser automation scripts - Create Python programs that control remote browsers
Execute server-side automation - Run Playwright code directly in the browser VM without local dependencies
Manage browser sessions programmatically - Create, configure, and control browsers from code
Build scalable scraping/testing tools - Use browser pools and profiles for high-volume automation
Deploy automation as actions - Package scripts as Kernel actions for invocation via API

When NOT to use:

For CLI commands (e.g., kernel browsers create), use the kernel-cli skill instead
For quick one-off tasks, the CLI may be simpler than writing code

Core Concepts

SDK Architecture

The SDK is organized into resource-based modules:

kernel.browsers - Browser session management (create, list, delete)
kernel.browsers.playwright - Server-side Playwright execution
kernel.browsers.computer - OS-level controls (mouse, keyboard, screenshots)
kernel.browser_pools - Pre-warmed browser pool management
kernel.profiles - Persistent browser profiles (auth state)
kernel.auth.connections - Managed auth (create, login, submit, follow, retrieve, delete)
kernel.credential_providers - External credential providers (1Password)
kernel.proxies - Proxy configuration
kernel.extensions - Chrome extension management
kernel.deployments - App deployment
kernel.invocations - Action invocation

Two Automation Approaches

1. Server-side Execution (RECOMMENDED)

Execute Playwright code directly in browser VM using kernel.browsers.playwright.execute(session_id, code="...")
session_id must be passed as a positional argument (first parameter), not as id= keyword
Response accessed via response.result - MUST usereturn in code to get data back
Best for: Most use cases, production automation, parallel execution, actions

2. CDP Connection (Client-side)

Connect Playwright to browser via CDP WebSocket URL
Code runs locally, browser runs remotely; requires local Playwright installation
Best for: Complex debugging, specific local development needs

Patterns Reference

Import Patterns

Standard: from kernel import Kernel
For actions: import kernel and from kernel import Kernel
For typed payloads: from typing import TypedDict
For CDP: from playwright.async_api import async_playwright

SDK Initialization

client = Kernel() reads KERNEL_API_KEY from environment automatically

Action Handler Pattern

from typing import TypedDict
from kernel import Kernel

app = kernel.App("app-name")

class TaskInput(TypedDict):
    task: str

@app.action("action-name")
async def my_action(ctx: kernel.KernelContext, input_data: TaskInput):
    # Access input: input_data["task"] or input_data.get("task")
    ...

CDP Connection Pattern (Client-side)

async with async_playwright() as playwright:
    browser = await playwright.chromium.connect_over_cdp(kernel_browser.cdp_ws_url)
    context = browser.contexts[0] if browser.contexts else await browser.new_context()
    page = context.pages[0] if context.pages else await context.new_page()

Binary Data Handling

Binary data (screenshots, PDFs) returns as Node.js Buffer: {'data': [byte_array], 'type': 'Buffer'}

# Follow canonical pattern above, then:
if response.success and response.result:
    data = bytes(response.result['data'])
    with open("output.png", "wb") as f:
        f.write(data)

Installation

uv pip install kernel or pip install kernel
For CDP: uv pip install playwright

References

Kernel Documentation : https://www.kernel.sh/docs
API Reference : https://www.kernel.sh/docs/api-reference/
Templates : https://www.kernel.sh/docs/reference/cli/create#available-templates
Quickstart Guide : https://www.kernel.sh/docs/quickstart
Examples : examples

Weekly Installs

141

Repository

kernel/skills

GitHub Stars

First Seen

Jan 30, 2026

Security Audits

Gen Agent Trust HubFail SocketPass SnykWarn

Installed on

cursor138

claude-code136

codex136

opencode21

gemini-cli20

github-copilot18

Skills CLI 使用指南：AI Agent 技能包管理器安装与管理教程

48,700 周安装