Framework Architect logo

Framework Architect

Community
anhtester
Framework Architect

Skill thiết kế và scaffold automation framework hoàn chỉnh cho Playwright, Selenium, và Appium — bao gồm project structure, base classes, config management, reporting, và CI/CD integration.

Overview

Publisheranhtester
Repositoryantigravity-testing-kit
Skill nameFramework Architect
Stars
149
Forks
57
Bundled files
Instructions only
LicenseMIT
Links
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Framework Architect 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/anhtester/antigravity-testing-kit/tree/main/.agent/skills/framework_architect
  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/anhtester/antigravity-testing-kit.git /tmp/antigravity-testing-kit
mkdir -p .claude/skills
cp -r /tmp/antigravity-testing-kit/.agent/skills/framework_architect .claude/skills/anhtester-framework-architect
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Framework Architect 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 Framework Architect 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 Framework Architect 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.

Framework Architect

Description

Skill chuyên biệt giúp agent thiết kế, scaffold và triển khai automation framework từ đầu. Hỗ trợ đa nền tảng (Web, Mobile, API) với các framework phổ biến nhất.

Agent có thể:

  • Thiết kế project structure theo best practices
  • Sinh base classes, config management, driver/browser management
  • Tích hợp reporting (Allure, HTML Report, Playwright Report)
  • Cấu hình CI/CD pipeline (GitHub Actions, GitLab CI, Jenkins)
  • Sinh template Page Object Model, fixtures, helpers
  • Tạo file cấu hình (package.json, pom.xml, build.gradle, playwright.config.ts)

When to Use

Sử dụng skill này khi:

  • User yêu cầu tạo/thiết kế automation framework mới
  • User cần scaffold project structure cho test automation
  • User muốn chuẩn hóa framework hiện tại
  • User cần tích hợp reporting hoặc CI/CD vào framework
  • User hỏi về best practices cho framework design

Trigger keywords: "create framework", "design framework", "scaffold project", "thiết kế framework", "tạo project mới"


Supported Stacks

🌐 Web Automation

StackNgôn ngữRunnerReportBuild Tool
Playwright + TypeScriptTypeScriptPlaywright TestHTML Report, Allurenpm
Playwright + JavaJavaTestNG / JUnit5Allure ReportMaven / Gradle
Playwright + PythonPythonPytestAllure, pytest-htmlpip
Selenium + JavaJavaTestNGAllure, ExtentReportsMaven / Gradle
Selenium + PythonPythonPytestAllure, pytest-htmlpip

📱 Mobile Automation

StackNgôn ngữRunnerReportBuild Tool
Appium + JavaJavaTestNGAllure, ExtentReportsMaven / Gradle
Appium + PythonPythonPytestAllure, pytest-htmlpip

🔌 API Automation

StackNgôn ngữRunnerReport
REST AssuredJavaTestNGAllure
Playwright APITypeScriptPlaywright TestHTML Report
Requests + PytestPythonPytestAllure

Framework Components

Mỗi framework PHẢI bao gồm các thành phần sau (tùy chỉnh theo stack):

1. Project Structure (Mandatory)

  • Cấu trúc thư mục rõ ràng, phân tách pages/tests/utils/config
  • File README.md hướng dẫn setup + chạy test
  • File .gitignore phù hợp

2. Configuration Management (Mandatory)

  • Quản lý environment (dev/staging/prod) qua config file hoặc .env
  • Centralized config — không hardcode giá trị trong test
  • Sensitive data (credentials) qua environment variables, KHÔNG commit vào repo

3. Browser / Driver Management (Mandatory)

  • Playwright: playwright.config.ts / conftest.py với browser setup
  • Selenium: WebDriverManager hoặc Driver Factory pattern
  • Appium: Desired Capabilities factory, Appium server config

4. Base Classes (Mandatory)

  • Base Page — chứa common methods (wait, click, type, screenshot)
  • Base Test — chứa setup/teardown, test lifecycle hooks
  • Không hardcode waits — chỉ dùng smart waits

5. Page Object Model (Mandatory)

  • Mỗi page/screen → 1 Page class
  • Locators khai báo ở đầu class, không inline trong test
  • Methods mô tả hành vi người dùng (không phải thao tác DOM)

6. Test Data Management (Mandatory)

  • Data factory / builder pattern cho test data
  • Data external (JSON/YAML/CSV) cho data-driven tests
  • Data unique + traceable (timestamp/random prefix)

7. Utilities (Mandatory)

  • Wait helpers (smart waits, custom conditions)
  • Screenshot utilities (capture on failure)
  • Logger (structured logging, không dùng print/console.log)
  • Date/Time helpers, String generators

8. Reporting (Mandatory)

  • Tích hợp ít nhất 1 reporting tool
  • Screenshot attach on failure
  • Test execution summary (pass/fail/skip counts)

9. CI/CD Pipeline (Optional — nhưng khuyến khích)

  • GitHub Actions / GitLab CI / Jenkins pipeline template
  • Parallel execution config
  • Artifact upload (reports, screenshots)

Project Structure Templates

Playwright + TypeScript

project-root/
├── playwright.config.ts        # Playwright configuration
├── package.json                # Dependencies + scripts
├── .env.example                # Environment template
├── .gitignore
├── README.md
├── src/
│   ├── pages/                  # Page Object classes
│   │   ├── base.page.ts        # Base page (common methods)
│   │   ├── login.page.ts
│   │   └── dashboard.page.ts
│   ├── fixtures/               # Custom fixtures
│   │   ├── auth.fixture.ts     # Authentication fixture
│   │   └── base.fixture.ts     # Extended test with all fixtures
│   ├── utils/                  # Helpers & utilities
│   │   ├── test-data.ts        # Data generators
│   │   ├── env.config.ts       # Environment config reader
│   │   └── helpers.ts          # Common helper functions
│   └── tests/                  # Test specs
│       ├── auth/
│       │   └── login.spec.ts
│       └── dashboard/
│           └── dashboard.spec.ts
├── test-data/                  # External test data (JSON/YAML)
│   └── users.json
└── .github/
    └── workflows/
        └── playwright.yml      # CI pipeline

Selenium + Java (Maven + TestNG)

project-root/
├── pom.xml                     # Maven config + dependencies
├── testng.xml                  # TestNG suite config
├── .env.example
├── .gitignore
├── README.md
├── src/
│   ├── main/java/
│   │   └── com/project/
│   │       ├── pages/          # Page Object classes
│   │       │   ├── BasePage.java
│   │       │   ├── LoginPage.java
│   │       │   └── DashboardPage.java
│   │       ├── drivers/        # Driver management
│   │       │   └── DriverFactory.java
│   │       ├── config/         # Configuration
│   │       │   └── ConfigReader.java
│   │       └── utils/          # Utilities
│   │           ├── WaitHelper.java
│   │           ├── ScreenshotUtil.java
│   │           └── TestDataGenerator.java
│   └── test/java/
│       └── com/project/
│           ├── base/
│           │   └── BaseTest.java
│           └── tests/
│               ├── LoginTest.java
│               └── DashboardTest.java
├── test-data/
│   └── users.json
└── .github/
    └── workflows/
        └── selenium.yml

Appium + Java (Maven + TestNG)

project-root/
├── pom.xml
├── testng.xml
├── .env.example
├── .gitignore
├── README.md
├── src/
│   ├── main/java/
│   │   └── com/project/
│   │       ├── screens/        # Screen Object classes (mobile POM)
│   │       │   ├── BaseScreen.java
│   │       │   ├── LoginScreen.java
│   │       │   └── HomeScreen.java
│   │       ├── drivers/        # Appium driver management
│   │       │   ├── AppiumDriverFactory.java
│   │       │   └── CapabilitiesManager.java
│   │       ├── config/
│   │       │   └── AppConfig.java
│   │       └── utils/
│   │           ├── MobileGestures.java    # Swipe, scroll, tap
│   │           ├── ScreenshotUtil.java
│   │           └── TestDataGenerator.java
│   └── test/java/
│       └── com/project/
│           ├── base/
│           │   └── BaseTest.java
│           └── tests/
│               ├── LoginTest.java
│               └── HomeTest.java
├── apps/                       # APK/IPA files
│   └── .gitkeep
├── test-data/
│   └── users.json
└── .github/
    └── workflows/
        └── appium.yml

Playwright + Python (Pytest)

project-root/
├── playwright.config.py        # Pytest-playwright config (nếu có)
├── pyproject.toml              # Python project config
├── requirements.txt            # Dependencies
├── conftest.py                 # Root fixtures + browser setup
├── .env.example
├── .gitignore
├── README.md
├── src/
│   ├── pages/
│   │   ├── base_page.py
│   │   ├── login_page.py
│   │   └── dashboard_page.py
│   ├── utils/
│   │   ├── config.py           # Env config reader
│   │   ├── test_data.py        # Data generators
│   │   └── helpers.py
│   └── tests/
│       ├── conftest.py         # Test-level fixtures
│       ├── test_login.py
│       └── test_dashboard.py
├── test-data/
│   └── users.json
└── .github/
    └── workflows/
        └── playwright.yml

Design Principles

  1. DRY (Don't Repeat Yourself) — Mỗi logic chỉ viết 1 lần, tái sử dụng qua Base classes và Utils
  2. Single Responsibility — Mỗi class/module làm 1 việc (Page chỉ chứa UI interaction, Test chỉ chứa test logic)
  3. Open/Closed — Framework dễ mở rộng (thêm page, thêm test) mà không sửa core
  4. Configuration over Code — Env, browser, timeout... quản lý qua config, không hardcode
  5. Fail Fast, Log Rich — Screenshot on failure, structured logging, clear assertion messages

Anti-Patterns (FORBIDDEN)

❌ Anti-Pattern✅ Đúng cách
Hardcode URL/credentials trong codeĐọc từ .env hoặc config file
Locator inline trong testKhai báo trong Page class
Thread.sleep() / waitForTimeout()Smart waits (expect(), WebDriverWait)
Global mutable stateIsolated fixtures/setup per test
Monolithic test file (1 file 500+ dòng)Tách theo module/feature
System.out.println() / console.log()Logger framework (Log4j, winston, logging)

Rules References

Agent PHẢI tuân thủ các rules chi tiết:

  • .agent/rules/automation_rules.md — General automation best practices
  • .agent/rules/locator_strategy.md — Locator selection priority
  • .agent/rules/playwright_rules.md — Playwright-specific rules
  • .agent/rules/selenium_rules.md — Selenium-specific rules
  • .agent/rules/appium_rules.md — Appium mobile automation rules

Frequently asked questions

What does the Framework Architect AI skill do?

Skill thiết kế và scaffold automation framework hoàn chỉnh cho Playwright, Selenium, và Appium — bao gồm project structure, base classes, config management, reporting, và CI/CD integration.

Why use Framework Architect on TypingMind?

Because you install it once and use it with any model. Framework Architect 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 Framework Architect in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anhtester/antigravity-testing-kit/tree/main/.agent/skills/framework_architect. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Framework Architect?

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 Framework Architect?

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

Is the Framework Architect AI skill free?

Yes. It is published on GitHub by anhtester under the MIT 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.

View all

Set up your own AI workspace now

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