qa-automation-engineer
Skill28 starsChanged 4 months agoMITView on GitHub
Skill hỗ trợ agent thực hiện các tác vụ QA automation testing bao gồm generate test cases, automation scripts, API tests, locators, phân tích flaky tests, và tạo test data.
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analyze-flaky-testsSkill
- analyze-requirement-documentSkill
- fetch-jira-requirementsSkill
- flaky-test-analyzerSkill
- framework-architectSkill
- generate-api-tests-from-swaggerSkill
- generate-application-test-planSkill
- generate-automation-frameworkSkill
- generate-automation-from-testcasesSkill
- generate-automation-from-ui-flowSkill
- generate-combinatorial-test-dataSkill
- generate-cross-module-test-planSkill
- generate-locatorSkill
- generate-manual-testcases-rbtSkill
- generate-requirements-from-websiteSkill
- generate-testcases-from-requirementsSkill
- generate-test-dataSkill
- import-test-results-xraySkill
- jira-integrationSkill
- locator-healer-agentSkill
- rbt-manual-testingSkill
- requirements-analyzerSkill
- smart-locator-agentSkill
- test-data-generatorSkill
- ui-debug-agentSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 10 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Use this skill when the user asks about:
- Very specific: line 60
When the user request matches a specific task, select the appropriate workflow skill from .agents/skills/.
- Very specific: line 66
Use workflow: $generate-testcases-from-requirements (QUICK mode) hoặc $generate-manual-testcases-rbt (FULL RBT mode).
- Very specific: line 71
write manual test cases → delegate to $rbt-manual-testing (QUICK mode)
- Very specific: line 72
test scenarios from requirement → delegate to $rbt-manual-testing (QUICK mode)
- Distinctive: line 97
run UI steps and generate Selenium script
- Distinctive: line 132
test nhiều module liên kết
- Distinctive: line 134
test tính năng có nhiều điều kiện kết hợp
- Distinctive: line 163
create regression test suite
- Distinctive: line 264
import user stories from jira
- Distinctive: line 276
import test execution to jira
- Distinctive: line 304
Avoid fragile locators such as auto-generated class names or positional xpaths.
- Distinctive: line 316
Avoid fragile selectors such as dynamic class names.
- Distinctive: line 357
Test data (structured, randomized, traceable)
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
QA Automation Engineer
Description
This skill enables the agent to assist with software testing and automation tasks.
The agent can:
- Generate manual test cases from requirements
- Generate test automation scripts from test cases or UI flows
- Generate API tests from Swagger/OpenAPI specifications
- Explore applications and discover test scenarios
- Generate automation frameworks
- Generate test data
- Analyze flaky tests
- Generate stable locators
- Generate requirements from website analysis
This skill is designed for modern QA workflows and automation development.
When to Use
Use this skill when the user asks about:
- Test automation
- Manual testing
- Automation frameworks
- API testing
- UI testing
- Test data generation
- Flaky test debugging
- Locator generation
- Requirements analysis from website
- Jira integration (fetch requirements, push test results)
- Xray test management
Typical prompts include:
- Generate test cases from requirement
- Generate Selenium automation from test case
- Generate automation from UI steps
- Generate API tests from Swagger
- Generate regression suite → (redirect sang
$generate-application-test-planhoặc$generate-manual-testcases-rbt) - Generate test data
- Analyze flaky test
- Generate locator for element
- Generate requirements from website
Workflow Routing
When the user request matches a specific task, select the appropriate workflow skill from .agents/skills/.
Generate test cases from requirements
Delegate: Tác vụ này thuộc skill
$rbt-manual-testing— không phải$qa-automation-engineer.
Use workflow: $generate-testcases-from-requirements (QUICK mode) hoặc $generate-manual-testcases-rbt (FULL RBT mode).
Triggers when user asks:
- generate test cases → delegate to
$rbt-manual-testing(QUICK mode) - write manual test cases → delegate to
$rbt-manual-testing(QUICK mode) - test scenarios from requirement → delegate to
$rbt-manual-testing(QUICK mode) - sinh test cases đầy đủ / quy trình 6 bước → delegate to
$rbt-manual-testing(FULL RBT mode)
Generate automation from manual test case
Use workflow: $generate-automation-from-testcases
Triggers when user asks:
- convert test case to automation
- generate Selenium automation
- generate Playwright automation from test case
Generate automation from UI steps
Use workflow: $generate-automation-from-ui-flow
Triggers when user asks:
- automate this UI flow
- generate automation from steps
- run UI steps and generate Selenium script
Generate API tests
Use workflow: $generate-api-tests-from-swagger
Triggers when user provides:
- Swagger URL
- OpenAPI specification
Generate test data
Use workflow: $generate-test-data
Triggers when user asks:
- generate test data
- generate boundary test data
Analyze cross-module feature & generate combinatorial matrix
Use workflow: $generate-cross-module-test-plan
Workflow dành cho tính năng phức tạp đi qua nhiều modules nối tiếp. Sinh Data Flow Map + Ma trận kết hợp đa chiều (Pairwise / Business-critical / Full Cartesian).
Triggers when user asks:
- phân tích tính năng cross-module
- test nhiều module liên kết
- sinh ma trận kết hợp / combinatorial matrix
- test tính năng có nhiều điều kiện kết hợp
- analyze multi-module feature
- pairwise testing
- decision table đa chiều / nhiều chiều
Generate combinatorial test data (multi-module pipeline)
Use workflow: $generate-combinatorial-test-data
Sinh test data cho ma trận kết hợp. Hỗ trợ 2 modes: GENERATE (sinh offline) và PIPELINE (chạy thật trên browser qua N modules).
Triggers when user asks:
- sinh data cho ma trận kết hợp
- tạo test data cho combinatorial matrix
- chạy pipeline tạo data qua nhiều module
- generate combinatorial test data
- setup data cho cross-module test
Generate regression suite
Không có workflow riêng. Dùng
$generate-application-test-plan(Mode PLAN) hoặc$generate-manual-testcases-rbt(FULL RBT) tùy theo input.
Triggers when user asks:
- create regression test suite
- generate regression scenarios
Generate automation framework
Delegate: Tác vụ này sử dụng skill
$framework-architectđể thiết kế framework.
Use workflow: $generate-automation-framework
Triggers when user asks:
- create automation framework
- design Selenium framework
- design Playwright framework
- design Appium framework
- scaffold automation project
- thiết kế framework mới
Explore application and generate test plan
Use workflow: $generate-application-test-plan
Workflow này có 2 modes: PLAN (mặc định — chỉ test plan) và FULL (test plan + automation skeleton). Khi user yêu cầu "full automation suite" hoặc "bootstrap automation" → tự động chọn Mode FULL.
Triggers when user asks:
- explore application
- discover test scenarios
- generate test plan
- generate full automation suite
- bootstrap automation for project
Analyze flaky tests
Use workflow: $analyze-flaky-tests
Triggers when user asks:
- why is this test flaky
- analyze unstable automation
Generate stable locators
Use workflow: $generate-locator
Triggers when user asks:
- generate locator for this element
- find stable selector
- create automation locator
Generate requirements from website
Use workflow: $generate-requirements-from-website
Triggers when user asks:
- generate requirements from website
- analyze website module and create requirements
- extract user stories from web page
Analyze requirement document
Delegate: Tác vụ này sử dụng skill
$requirements-analyzerđể phân tích requirement documents.
Use workflow: $analyze-requirement-document
Workflow chỉ phân tích requirement — KHÔNG sinh test cases. Output là tài liệu phân tích chi tiết gồm: AC breakdown, dependencies, ambiguities, risks.
Triggers when user asks:
- phân tích requirement document
- review yêu cầu / analyze this ticket
- phân tích Jira ticket / requirement
- tìm điểm mơ hồ trong requirement
- analyze requirement / review requirement document
Fetch requirements from Jira
Use workflow: $fetch-jira-requirements
Triggers when user asks:
- fetch jira requirements
- lấy requirement từ jira
- get jira ticket
- import user stories from jira
Import test results to Xray
Use workflow: $import-test-results-xray
Triggers when user asks:
- push test results to xray
- đẩy kết quả test lên xray
- import test execution to jira
- upload playwright results to xray
Automation Framework
Default automation stack:
- Language: Java
- UI automation: Selenium WebDriver or Playwright
- Test framework: TestNG
- API automation: REST Assured
- Mobile automation: Appium
- Design pattern: Page Object Model (POM)
Locator Strategy
Selenium Locator Priority
iddata-testidnamecss selectorxpath(last resort)
Avoid fragile locators such as auto-generated class names or positional xpaths.
Playwright Locator Priority
getByRole()getByLabel()getByPlaceholder()getByText()getByTestId()css selectorxpath(last resort)
Avoid fragile selectors such as dynamic class names.
Note: For detailed locator rules, refer to
.agents/rules/locator_strategy.md.
Rules References
The agent MUST also follow the detailed rules defined in .agents/rules/:
- automation_rules.md — General automation best practices
- locator_strategy.md — Detailed locator selection rules
- playwright_rules.md — Playwright-specific rules
- selenium_rules.md — Selenium-specific rules
- appium_rules.md — Appium mobile automation rules
References
The agent may consult additional documentation in the references/ folder:
PROJECT_CONTEXT.md— Project domain, tech stack, key modulesTEST_STRATEGY.md— Testing objectives, scope, execution planPROMPT_TEMPLATES.md— Reusable prompt templates for common QA tasks
External references (thay thế cho các file đã gộp):
plans/automation/project_architecture/README.md— Repository structure & project architecture (thay thế REPOSITORY_MAP.md).agents/rules/delivery_checklist.md— Quality checklist / Definition of Done
Output
Depending on the request, the agent may return:
- Manual test cases (structured format)
- Automation scripts (Java/TypeScript)
- API tests (REST Assured)
- Locator recommendations
- Test data (structured, randomized, traceable)
- Automation framework design
- Requirements documents
Automation outputs should include:
- Page Object classes
- Test classes
- Assertions validating expected behavior
- Clean, readable, maintainable code (no debug logs, no commented code)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

