borghei/Claude-Skills / engineering/senior-qa
senior-qa
VerifiedTesting for React/Next.js with Jest, React Testing Library, and Playwright. Use when generating tests, writing unit tests, analyzing coverage, scaffolding E2E tests, configuring Jest, or improving test quality.
Senior QA Engineer
Test automation, coverage analysis, and quality assurance patterns for React and Next.js applications. Generates Jest + React Testing Library unit test stubs, analyzes Istanbul/LCOV coverage for gaps, and scaffolds Playwright E2E suites for App Router and Pages Router projects.
Core Capabilities
- Unit test generation — scan React/TypeScript components and emit Jest + RTL stubs (render, interaction, state, optional
jest-axea11y). - Coverage analysis — parse Istanbul/LCOV reports, identify gaps by severity, flag critical business-logic paths, and emit text/HTML/JSON recommendations.
- E2E scaffolding — detect Next.js routes (dynamic segments, route groups, auth pages) and generate Playwright specs, Page Object Models, fixtures, and config.
- Test strategy — the testing pyramid, coverage targets by code type, and test organization patterns.
- Automation patterns — Page Object Model, data factories, MSW mocking, fixtures, and custom render utilities.
- Quality practices — testable code design, AAA structure, test isolation, flaky-test elimination, and quality metrics.
When to Use
- Setting up unit tests for new or existing React components.
- Improving test coverage or preparing for release.
- Setting up Playwright E2E tests for a Next.js project.
- Configuring Jest thresholds or improving overall test quality.
Clarify First
Before generating tests, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.
- Test layer: unit (Jest+RTL) vs E2E (Playwright) (selects
test_suite_generatorvse2e_test_scaffolder). - Source path: the components or Next.js routes to generate tests from (the scaffolder's input).
- Coverage focus: happy path only vs interaction/state/a11y (
jest-axe) (sets which test stubs are emitted).
Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.
Tools Overview
| Tool | Purpose | Example (runs as written) |
|---|---|---|
test_suite_generator.py | Jest + RTL stubs from React components; reads the XProps interface to build typed mockProps for required props (--output, --include-a11y, --scan-only, --json) | python scripts/test_suite_generator.py assets/sample_components --output /tmp/qa/tests |
coverage_analyzer.py | Istanbul JSON / LCOV gap analysis with critical-path weighting (--threshold, --strict, --critical-paths, --format text/html/json, --json) | python scripts/coverage_analyzer.py assets/sample_lcov.info --threshold 80 --strict |
e2e_test_scaffolder.py | Playwright specs, page objects, fixtures and playwright.config.ts from Next.js routes, all written under --output | python scripts/e2e_test_scaffolder.py assets/sample_app/app --output /tmp/qa/e2e |
Exit codes: 0 ok; 1 coverage below --threshold when --strict is set (without
--strict the analyzer always reports and exits 0, so use --strict in CI); 2 bad input
(path not found, unparseable report). With --json the report goes to stderr and stdout is
pure JSON.
Generated stubs are a starting point: they render with valid required props and leave
TODO assertions, so they compile but assert nothing until you write the checks. The
sample LCOV has a payment file at 37.5% line coverage, so --strict --threshold 80 exits 1.
Workflow
- Generate stubs or scaffold E2E specs into the project's test folder (always pass
--output). - Replace every
TODOwith an assertion on behaviour the user can see (role, text, called handler); delete stubs that test nothing useful. - Run the project's tests with coverage, then
coverage_analyzer.py <report> --threshold <n> --strict. - Done when the suite passes, the analyzer exits 0, and no generated test is still assertion-free.
References
Load the reference that matches the task — keep this file lean and pull detail on demand:
- references/qa-workflows-and-tools.md — quick start, the three tool overviews with sample output, the unit-test/coverage/E2E workflows, common pattern snippets (RTL queries, async, MSW, Playwright locators, jest thresholds), common commands, troubleshooting table, and success criteria. Read when running a workflow.
- references/tool-cli-reference.md — full flag tables, examples, output formats, and generated artifacts for all three scripts. Read before running the scripts.
- references/testing_strategies.md — the testing pyramid, testing types, coverage targets and thresholds, and test organization patterns. Read when designing test strategy.
- references/test_automation_patterns.md — Page Object Model, data factories, fixture management, mocking strategies (MSW), and custom test utilities. Read when writing test code.
- references/qa_best_practices.md — writing testable code, naming conventions, AAA pattern, test isolation, flaky-test debugging, and quality metrics. Read when improving test quality.
Scope & Limitations
This skill covers:
- Unit test stub generation for React/TypeScript functional and class components using Jest and React Testing Library.
- Coverage analysis and gap identification from Istanbul JSON and LCOV report formats.
- E2E test scaffolding for Next.js App Router and Pages Router projects using Playwright.
- Accessibility test generation via
jest-axeintegration.
This skill does NOT cover:
- Backend API testing (see
senior-backendfor Express/Node.js testing patterns). - Performance or load testing (see
senior-devopsfor infrastructure and performance tooling). - Visual regression testing or screenshot comparison workflows.
- Mobile-native testing (React Native, Flutter) -- this skill targets web browser-based testing only.
Anti-Patterns
Shipping Generated Stubs as Tests
Mistake: Committing the generated files with their TODO assertions still in place.
Why it happens: They run green and raise the coverage number.
Instead: A render with no assertion only proves the component does not throw. Write the assertion or delete the case.
Querying by Test ID First
Mistake: Reaching for getByTestId for every element.
Why it happens: It is the most stable selector to write.
Instead: Prefer getByRole and getByLabelText: they test what users and assistive tech see, and fail when accessibility regresses. Keep test IDs for elements with no accessible name.
Gating on Overall Coverage Only
Mistake: Passing CI because the project average clears 80%.
Why it happens: One number is easy to configure.
Instead: Use --critical-paths and read the per-file gaps: a 37% payment module hidden behind a 90% average is the bug that ships.
Files
| File | Purpose |
|---|---|
scripts/test_suite_generator.py | Jest + RTL stub generator |
scripts/coverage_analyzer.py | Coverage gap analyzer and CI gate |
scripts/e2e_test_scaffolder.py | Playwright scaffolder for Next.js routes |
assets/sample_components/Button.tsx | Component with a typed props interface for the generator |
assets/sample_app/app/ | Two-route Next.js App Router tree for the scaffolder |
assets/sample_lcov.info | LCOV report with an under-tested payment file (strict gate exits 1 at 80) |
references/*.md | Workflows, CLI reference, strategies, automation patterns, best practices |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |