Comprehensive QA Testing skill theo chuẩn Agent Skills — tương thích Claude Code, Cursor, VS Code, Kiro, Gemini CLI, và 40+ agentic clients khác.
Cách 1 — Global (dùng được ở mọi project):
git clone git@github.com:SoftwareOneHN/qa-testing-kit.git ~/.claude/skills/qa-testing-kitCách 2 — Project-level (chỉ áp dụng cho 1 project):
git clone git@github.com:SoftwareOneHN/qa-testing-kit.git .claude/skills/qa-testing-kitCách 3 — Symlink (dev workflow, dễ pull updates):
git clone git@github.com:SoftwareOneHN/qa-testing-kit.git ~/Projects/qa-testing-kit
ln -s ~/Projects/qa-testing-kit ~/.claude/skills/qa-testing-kitGlobal vs Project-level:
~/.claude/skills/là global — skill tự động available trong mọi project..claude/skills/(trong repo) là project-level — chỉ hoạt động khi bạn đang ở repo đó.
Verify:
ls ~/.claude/skills/qa-testing-kit/SKILL.md— thấy file là OK.
Copy thư mục qa-testing-kit/ vào .cursor/skills/ hoặc .vscode/skills/.
Copy thư mục qa-testing-kit/ vào .kiro/skills/ hoặc cài từ Power registry.
Đặt thư mục qa-testing-kit/ vào vị trí skills mà client hỗ trợ.
qa-testing-kit/
├── SKILL.md # Required: metadata + core instructions
├── README.md # File này
├── references/ # Detailed docs (loaded on-demand)
│ ├── rules-appium.md # Appium-specific rules
│ ├── rules-automation.md # General automation rules
│ ├── rules-locator-strategy.md # Locator strategy guidelines
│ ├── rules-playwright.md # Playwright-specific rules
│ ├── rules-selenium.md # Selenium-specific rules
│ ├── workflow-api-tests.md # API testing workflow
│ ├── workflow-automation.md # Automation script generation
│ ├── workflow-cross-module.md # Cross-module combinatorial
│ ├── workflow-flaky-tests.md # Flaky test analysis & fix
│ ├── workflow-framework.md # Framework scaffolding
│ ├── workflow-jira-integration.md # Jira/Xray integration
│ ├── workflow-locator.md # Locator generation
│ ├── workflow-requirements.md # Requirements analysis
│ ├── workflow-test-data.md # Test data generation
│ ├── workflow-testcases-quick.md # Quick test case generation
│ └── workflow-testcases-rbt.md # Full 6-step RBT test cases
└── scripts/
└── jira-xray-mcp/ # MCP server for Jira/Xray
├── index.js
└── package.json
Theo chuẩn Agent Skills, skill hoạt động theo 3 giai đoạn:
- Discovery (~100 tokens): Chỉ load
name+descriptiontừ frontmatter - Activation (~4000 tokens): Load toàn bộ
SKILL.mdbody khi task match - Execution (on-demand): Load reference files cụ thể khi cần chi tiết step
Sau khi cài, nói tự nhiên:
| Bạn nói | Agent làm |
|---|---|
| "Phân tích requirements từ website này" | Crawl → extract → structure requirements |
| "Tạo test cases cho module login" | Quick mode → generate test cases |
| "Tạo test cases đầy đủ 6-step RBT" | Full RBT workflow |
| "Convert TC sang Playwright" | Automation script generation |
| "Scaffold framework Playwright + TypeScript" | Framework scaffolding |
| "Phân tích flaky tests" | Log analysis → root cause → fix |
| "Generate test data cho form registration" | Structured test data (positive, negative, boundary) |
| "Tạo API tests từ Swagger" | Parse spec → generate API tests |
| "Fetch requirements từ Jira" | Jira integration → pull issues |
| "Push results lên Xray" | Xray integration → import results |
- Lifecycle-driven: requirements → test-plan → test-cases → automation → execution → report
- State-aware: tự detect vị trí hiện tại, recommend next step
- Impact analysis: đánh giá ảnh hưởng trước khi thay đổi artifacts
- Multi-framework: Playwright, Selenium, Appium, REST Assured
- Multi-language: TypeScript, Java, Python
- Auto-heal: test fail → tự phân tích → fix → re-run (max 5 rounds)
- Jira/Xray MCP: fetch requirements, push results trực tiếp
| Platform | Framework | Language | Runner |
|---|---|---|---|
| Web | Playwright | TypeScript/Java/Python | Playwright Test/TestNG/Pytest |
| Web | Selenium | Java/Python | TestNG/Pytest |
| Mobile | Appium | Java | TestNG |
| API | REST Assured | Java | TestNG |
| API | Playwright API | TypeScript | Playwright Test |
MIT