automation-strategy
Test Automation Strategy
When to Use This Skill
Use this skill when:
- Automation Strategy tasks - Planning test automation strategies
- Planning or design - Need guidance on ROI analysis, candidate selection, framework evaluation
- Best practices - Want to follow established patterns and standards
Overview
A well-planned test automation strategy maximizes ROI by automating the right tests at the right level. Poor automation choices lead to maintenance burden, flaky tests, and wasted effort.
Automation Quadrant
High Business Value
│
┌──────────────────┼──────────────────┐
│ AUTOMATE │ AUTOMATE │
│ FIRST │ (careful ROI) │
│ (High ROI) │ │
Low ├──────────────────┼──────────────────┤ High
Effort │ AUTOMATE │ CONSIDER │ Effort
│ (Low effort) │ MANUAL │
│ │ (Low ROI) │
└──────────────────┼──────────────────┘
Low Business Value
Selection Criteria Matrix
| Criterion | Weight | Score (1-5) |
|---|---|---|
| Execution Frequency | 25% | 5 = Daily, 1 = Quarterly |
| Business Criticality | 25% | 5 = Revenue-critical, 1 = Rarely used |
| Stability (low change) | 20% | 5 = Never changes, 1 = Weekly |
| Complexity to Automate | 15% | 5 = Trivial, 1 = Very complex |
| Data Availability | 15% | 5 = Static, 1 = Unavailable |
Decision: Score ≥ 4.0: Prioritize | 3.0-3.9: Defer | < 3.0: Keep manual
Good vs Poor Automation Candidates
| Good Candidates | Poor Candidates |
|---|---|
| Smoke/sanity tests | Exploratory testing |
| Regression tests | Usability testing |
| Data-driven tests | One-time tests |
| API contract tests | Rapidly changing features |
| Performance baselines | Visual design validation |
| Security scans | Edge cases rarely executed |
ROI Quick Estimation
| Factor | Multiply Manual Time By |
|---|---|
| Simple UI automation | 3-5x |
| Complex UI automation | 8-15x |
| API automation | 1-2x |
| Database automation | 2-3x |
| Performance tests | 5-10x |
Example: 30 min manual × 1.5 = 45 min API automation. 52 weekly runs = 26 hrs saved. ROI = 3,367%
Anti-Patterns to Avoid
| Anti-Pattern | Problem | Solution |
|---|---|---|
| Sleep/Wait hardcoding | Flaky, slow | Use explicit waits |
| XPath over data-testid | Brittle | Use stable selectors |
| Test interdependence | Order-dependent failures | Isolated test setup |
| Shared mutable state | Race conditions | Fresh state per test |
| Too many E2E tests | Slow pipeline | Push to lower pyramid |
Maintenance Metrics
| Metric | Healthy | Warning | Critical |
|---|---|---|---|
| Pass rate | > 98% | 95-98% | < 95% |
| Flaky test rate | < 2% | 2-5% | > 5% |
| Avg execution time | < 10 min | 10-30 min | > 30 min |
| Maintenance hours/week | < 4 hrs | 4-8 hrs | > 8 hrs |
References
| Reference | Content | When to Load |
|---|---|---|
| automation-strategy-template.md | Full strategy template, framework selection, roadmap | Creating automation strategy |
| automation-patterns.md | Page Object Model, Fluent Builder, Test Fixture | Implementing .NET Playwright tests |
Integration Points
Inputs from:
test-strategy-planningskill → Overall strategytest-pyramid-designskill → Pyramid ratios- Requirements → Coverage targets
Outputs to:
- CI/CD pipeline → Automation integration
- Team training → Framework usage
test-case-designskill → Automatable test designs
Test Scenarios
Scenario 1: Planning automation strategy
Query: "Help me plan a test automation strategy for our e-commerce platform"
Expected: Skill activates, provides strategy template, guides through assessment
Scenario 2: Evaluating automation candidates
Query: "Should I automate this checkout flow test?"
Expected: Skill activates, provides selection criteria matrix, helps calculate ROI
Scenario 3: Implementing patterns
Query: "Show me the Page Object Model pattern in Playwright"
Expected: Skill activates, loads automation-patterns.md reference, provides code examples
Last Updated: 2025-12-28
Version History
- v1.1.0 (2025-12-28): Refactored to progressive disclosure - extracted template/patterns to references/
- v1.0.0 (2025-12-26): Initial release
More from melodic-software/claude-code-plugins
design-thinking
Design Thinking methodology for human-centered innovation. Covers the 5-phase IDEO/Stanford d.school approach (Empathize, Define, Ideate, Prototype, Test) with workshop facilitation and exercise templates.
191plantuml-syntax
Authoritative reference for PlantUML diagram syntax. Provides UML and non-UML diagram types, syntax patterns, examples, and setup guidance for generating accurate PlantUML diagrams.
161system-prompt-engineering
Design effective system prompts for custom agents. Use when creating agent system prompts, defining agent identity and rules, or designing high-impact prompts that shape agent behavior.
141architecture-documentation
Generate architecture documents using templates with diagram integration. Use for creating C4 diagrams, viewpoint documents, and technical overviews.
126data-modeling
Data modeling with Entity-Relationship Diagrams (ERDs), data dictionaries, and conceptual/logical/physical models. Documents data structures, relationships, and attributes.
101resume-optimization
Resume structure, achievement bullet formulas, ATS optimization, and job-targeted tailoring for software engineers. Use when reviewing resumes, crafting achievement bullets, extracting keywords from job descriptions, or tailoring content for specific roles.
93