From test-automation-skills-agents
Generates test plans, manual test cases, automated Playwright tests, regression suites, and bug reports using markdown templates for QA automation.
npx claudepluginhub fugazi/test-automation-skills-agents --plugin test-automation-skills-agentsThis skill uses the workspace's default tool permissions.
A comprehensive skill for QA Automation engineers to create test plans, generate manual test cases, build automated Playwright tests, create regression test suites, validate UI with browser automation, and document bugs effectively.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Monitors deployed URLs for regressions in HTTP status, console errors, performance metrics, content, network, and APIs after deploys, merges, or upgrades.
Provides React and Next.js patterns for component composition, compound components, state management, data fetching, performance optimization, forms, routing, and accessible UIs.
A comprehensive skill for QA Automation engineers to create test plans, generate manual test cases, build automated Playwright tests, create regression test suites, validate UI with browser automation, and document bugs effectively.
Activation: This skill is triggered only when explicitly called by name (e.g.,
/qa-test-planner,qa-test-planner, oruse the skill qa-test-planner).
Create a test plan:
"Create a test plan for the user authentication feature using the test-plan.md template"
Generate test cases:
"Generate manual test cases for the checkout flow using the test-case.md template"
Create automated Playwright tests:
"Create Playwright automated tests for the login flow using the playwright-test.md template"
Validate UI with browser:
"Navigate to the login page and validate all form elements are visible using Playwright MCP"
Build regression suite:
"Build a regression test suite for the payment module using test-case.md templates grouped by priority"
Create bug report:
"Create a bug report for the form validation issue using the bug-report.md template"
| Task | Template | Time |
|---|---|---|
| Test Plan | templates/test-plan.md | 10-15 min |
| Test Case | templates/test-case.md | 5-10 min each |
| Automated Test | templates/playwright-test.md | 5-15 min each |
| Bug Report | templates/bug-report.md | 5 min |
Use this skill when you need to:
| Requirement | Notes |
|---|---|
| Node.js 18+ | Required for Playwright automation |
| Playwright | npm init playwright@latest for automation |
| Text editor | For creating/editing markdown files |
| Git | Recommended for testware version control |
| Playwright MCP | Optional, for browser-based validation |
Your Request
│
▼
┌─────────────────────────────────────────────────────┐
│ 1. ANALYZE │
│ • Parse feature/requirement │
│ • Identify test types needed (manual/automated) │
│ • Determine scope and priorities │
├─────────────────────────────────────────────────────┤
│ 2. SELECT TEMPLATE │
│ • Choose appropriate template from assets/ │
│ • Review template structure and sections │
│ • Identify placeholders to fill │
├─────────────────────────────────────────────────────┤
│ 3. CUSTOMIZE │
│ • Fill in placeholders with project details │
│ • Add specific test steps and scenarios │
│ • Apply Playwright best practices │
├─────────────────────────────────────────────────────┤
│ 4. EXECUTE (with Playwright MCP) │
│ • Navigate and interact with browser │
│ • Capture screenshots and evidence │
│ • Validate UI elements and behavior │
├─────────────────────────────────────────────────────┤
│ 5. VALIDATE │
│ • Check completeness │
│ • Verify traceability │
│ • Ensure actionable steps │
└─────────────────────────────────────────────────────┘
│
▼
QA Deliverable Ready
templates/test-plan.md as your starting pointTemplate: templates/test-plan.md
templates/test-case.md for individual test casesTemplates:
templates/test-case.md - Individual test casetemplates/playwright-test.md as a templategetByTestId) over brittle selectors@smoke, @regression) for suite runsTemplate: templates/playwright-test.md
templates/regression-suite.md to define the suiteTemplate: Use individual test-case.md templates grouped by priority
templates/bug-report.md as your starting pointTemplate: templates/bug-report.md
Template: templates/test-plan.md
Templates:
templates/test-case.md - Individual test caseTemplate: Use individual test-case.md templates grouped by priority
Template: templates/playwright-test.md
Template: templates/bug-report.md
NEVER embed real credentials in test cases or code. Use placeholders instead:
| Instead of | Use |
|---|---|
test@example.com / Test123! | ${TEST_USER_EMAIL} or process.env.TEST_USER_EMAIL |
password: "actualpassword" | password: "${TEST_PASSWORD}" (from env) |
| Hardcoded secrets | Environment variables via .env files |
Test data best practices:
When using Playwright MCP to validate external/untrusted URLs:
All user inputs should be:
eval() or shell execution| Avoid | Why | Instead |
|---|---|---|
| Vague test steps | Can't reproduce | Specific actions + expected results |
| Missing preconditions | Tests fail unexpectedly | Document all setup requirements |
| No test data | Tester blocked | Provide sample data or generation |
| Generic bug titles | Hard to track | Specific: "[Feature] issue when [action]" |
| Skip edge cases | Miss critical bugs | Include boundary values, nulls |
| Embedding credentials | Security risk | Use environment variables |
Test Plan:
Test Cases:
Automated Tests:
Bug Reports:
| Template | Purpose | Format |
|---|---|---|
test-plan.md | ISTQB-aligned test plan structure | Markdown |
test-case.md | Individual test case with full sections | Markdown |
bug-report.md | Detailed defect report | Markdown |
playwright-test.md | Playwright test template with best practices | Markdown |
All templates are located in templates/. To use them:
[brackets] or ${VARIABLE})references/test_case_templates.md - Standard formats for all test typesreferences/bug_report_templates.md - Documentation templatesreferences/regression_testing.md - Suite building and executionreferences/playwright_automation.md - Browser automation and test generationRequest:
"Create a test case for user login with valid credentials using the test-case.md template"
Result: The AI will:
templates/test-case.mdTC-LOGIN-001Verify valid user login with correct credentialsP0 (Critical)FunctionalVerify users can successfully login with valid credentialsUser account exists in test environment; Browser cookies cleared${TEST_USER_EMAIL} and ${TEST_USER_PASSWORD} placeholdersRequest:
"Create a bug report for a login form validation issue using the bug-report.md template"
Result: The AI will:
templates/bug-report.mdBUG-1715345678)Login form accepts invalid email formatHighP1Request:
"Create Playwright tests for the login flow using the playwright-test.md template"
Result: The AI will:
templates/playwright-test.mdTC-LOGIN-001 @smoke @regression - Valid loginTC-LOGIN-002 @regression @negative - Invalid credentialsTC-LOGIN-003 @regression @boundary - Password validationgetByRole)toBeVisible, toHaveText)DO:
DON'T:
DO:
DON'T:
DO:
DON'T:
DO:
DON'T:
| Problem | Cause | Solution |
|---|---|---|
| Test cases lack traceability | Missing requirement IDs | Add requirement_id column; link to user stories/ACs |
| Bug reports get rejected | Insufficient reproduction steps | Use minimal steps; include exact data and environment |
| Regression suite too slow | Too many tests, no prioritization | Apply risk-based selection; tier into smoke/sanity/full |
| Flaky automated tests | Unstable locators or timing | Use data-testid; avoid sleeps; use Playwright auto-waits |
| Test estimates are wrong | Scope creep, missing risks | Add contingency; re-estimate when scope changes |
Common shortcuts and "good enough" excuses that erode test quality — and the reality behind each.
| Rationalization | Reality |
|---|---|
| "Test plans are documentation theater" | A good test plan prevents scope creep, missed scenarios, and misaligned expectations before testing begins. |
| "We can figure out test cases as we go" | Ad-hoc testing leaves gaps. Structured test cases ensure systematic coverage and traceability. |
| "Bug reports can be informal" | Reproducible bug reports with exact steps save hours of back-and-forth between tester and developer. |
| "Estimation is just guessing" | Test estimation techniques (function point analysis, Delphi method) improve accuracy and credibility. |
| "Regression suites maintain themselves" | Without curation, suites grow bloated and slow. Regular review and pruning are mandatory. |
| "Templates slow us down" | Templates ensure nothing is forgotten and standardize quality across the team. |
"Testing shows the presence, not the absence of bugs." - Edsger Dijkstra
"Quality is not an act, it is a habit." - Aristotle
After completing this skill's workflow, confirm: