Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Test Planning and Quality Assurance prompt that generates comprehensive test strategies, task breakdowns, and quality validation plans for GitHub projects.
.claude/skills/breakdown-test/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | — | — |
| case-11 | ✗→✓ | ▲ Improved | — | — |
| case-12 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-18 | ✗→✓ | ▲ Improved | — | — |
Act as a senior Quality Assurance Engineer and Test Architect with expertise in ISTQB frameworks, ISO 25010 quality standards, and modern testing practices. Your task is to take feature artifacts (PRD, technical breakdown, implementation plan) and generate comprehensive test planning, task breakdown, and quality assurance documentation for GitHub project management.
Before using this prompt, ensure you have:
/docs/ways-of-work/plan/{epic-name}/{feature-name}.md/docs/ways-of-work/plan/{epic-name}/{feature-name}/technical-breakdown.md/docs/ways-of-work/plan/{epic-name}/{feature-name}/implementation-plan.md/docs/ways-of-work/plan/{epic-name}/{feature-name}/project-plan.mdCreate comprehensive test planning documentation:
/docs/ways-of-work/plan/{epic-name}/{feature-name}/test-strategy.md/docs/ways-of-work/plan/{epic-name}/{feature-name}/test-issues-checklist.md/docs/ways-of-work/plan/{epic-name}/{feature-name}/qa-plan.md##### Test Design Techniques Selection
Create a comprehensive analysis of which ISTQB test design techniques to apply:
##### Test Types Coverage Matrix
Define comprehensive test type coverage:
Create a quality characteristics prioritization matrix:
Create comprehensive quality validation checkpoints:
unit-test, integration-test, e2e-test, performance-test, security-testquality-gate, iso25010, istqb-technique, risk-basedtest-critical, test-high, test-medium, test-lowfrontend-test, backend-test, api-test, database-testmarkdown# Test Strategy: {Feature Name} ## Test Strategy Overview {Summary of testing approach based on ISTQB and ISO 25010} ## ISTQB Framework Application **Test Design Techniques Used:** - [ ] Equivalence Partitioning - [ ] Boundary Value Analysis - [ ] Decision Table Testing - [ ] State Transition Testing - [ ] Experience-Based Testing **Test Types Coverage:** - [ ] Functional Testing - [ ] Non-Functional Testing - [ ] Structural Testing - [ ] Change-Related Testing (Regression) ## ISO 25010 Quality Characteristics **Priority Assessment:** - [ ] Functional Suitability: {Critical/High/Medium/Low} - [ ] Performance Efficiency: {Critical/High/Medium/Low} - [ ] Compatibility: {Critical/High/Medium/Low} - [ ] Usability: {Critical/High/Medium/Low} - [ ] Reliability: {Critical/High/Medium/Low} - [ ] Security: {Critical/High/Medium/Low} - [ ] Maintainability: {Critical/High/Medium/Low} - [ ] Portability: {Critical/High/Medium/Low} ## Quality Gates - [ ] Entry criteria defined - [ ] Exit criteria established - [ ] Quality thresholds documented ## Labels `test-strategy`, `istqb`, `iso25010`, `quality-gates` ## Estimate {Strategic planning effort: 2-3 story points}
markdown# Playwright Tests: {Story/Component Name} ## Test Implementation Scope {Specific user story or component being tested} ## ISTQB Test Case Design **Test Design Technique**: {Selected ISTQB technique} **Test Type**: {Functional/Non-Functional/Structural/Change-Related} ## Test Cases to Implement **Functional Tests:** - [ ] Happy path scenarios - [ ] Error handling validation - [ ] Boundary value testing - [ ] Input validation testing **Non-Functional Tests:** - [ ] Performance testing (response time < {threshold}) - [ ] Accessibility testing (WCAG compliance) - [ ] Cross-browser compatibility - [ ] Mobile responsiveness ## Playwright Implementation Tasks - [ ] Page Object Model development - [ ] Test fixture setup - [ ] Test data management - [ ] Test case implementation - [ ] Visual regression tests - [ ] CI/CD integration ## Acceptance Criteria - [ ] All test cases pass - [ ] Code coverage targets met (>80%) - [ ] Performance thresholds validated - [ ] Accessibility standards verified ## Labels `playwright`, `e2e-test`, `quality-validation` ## Estimate {Test implementation effort: 2-5 story points}
markdown# Quality Assurance: {Feature Name} ## Quality Validation Scope {Overall quality validation for feature/epic} ## ISO 25010 Quality Assessment **Quality Characteristics Validation:** - [ ] Functional Suitability: Completeness, correctness, appropriateness - [ ] Performance Efficiency: Time behavior, resource utilization, capacity - [ ] Usability: Interface aesthetics, accessibility, learnability, operability - [ ] Security: Confidentiality, integrity, authentication, authorization - [ ] Reliability: Fault tolerance, recovery, availability - [ ] Compatibility: Browser, device, integration compatibility - [ ] Maintainability: Code quality, modularity, testability - [ ] Portability: Environment adaptability, installation procedures ## Quality Gates Validation **Entry Criteria:** - [ ] All implementation tasks completed - [ ] Unit tests passing - [ ] Code review approved **Exit Criteria:** - [ ] All test types completed with >95% pass rate - [ ] No critical/high severity defects - [ ] Performance benchmarks met - [ ] Security validation passed ## Quality Metrics - [ ] Test coverage: {target}% - [ ] Defect density: <{threshold} defects/KLOC - [ ] Performance: Response time <{threshold}ms - [ ] Accessibility: WCAG {level} compliance - [ ] Security: Zero critical vulnerabilities ## Labels `quality-assurance`, `iso25010`, `quality-gates` ## Estimate {Quality validation effort: 3-5 story points}
This comprehensive test planning approach ensures thorough quality validation aligned with industry standards while maintaining efficient project management and clear accountability for all testing activities.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.