qa-testing
Skill do QA Engineer para testes unitarios, integracao e E2E. Use quando precisar escrever testes, validar regressao, revisar cobertura, configurar estrategia de QA, ou evidenciar qualidade antes de release. Trigger em: "teste", "test", "QA", "Playwright", "Vitest", "Jest", "E2E", "coverage", "mock", "fixture", "regressao", "teste de integracao", "testing library".
76
67%
Does it follow best practices?
Impact
85%
1.16xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/05-qa-testing/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope (QA testing across unit, integration, and E2E), provides explicit trigger guidance with a comprehensive list of natural keywords in both Portuguese and English, and clearly answers both what the skill does and when to use it. The description is concise, uses third-person voice appropriately, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: writing tests, validating regression, reviewing coverage, configuring QA strategy, and evidencing quality before release. Also specifies test types: unit, integration, and E2E. | 3 / 3 |
Completeness | Clearly answers both 'what' (QA Engineer skill for unit, integration, and E2E tests) and 'when' (explicit 'Use quando' clause with specific trigger scenarios like writing tests, validating regression, reviewing coverage, configuring QA strategy, and pre-release quality checks). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say, including both Portuguese and English variants ('teste', 'test', 'QA', 'Playwright', 'Vitest', 'Jest', 'E2E', 'coverage', 'mock', 'fixture', 'regressao', 'teste de integracao', 'testing library'). These are terms users would naturally use when requesting QA-related help. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche around QA/testing with highly specific trigger terms like 'Playwright', 'Vitest', 'Jest', 'E2E', 'coverage', 'mock', 'fixture'. These are unlikely to conflict with non-testing skills, making it very distinguishable. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill attempts to cover a broad QA scope but suffers from verbosity and insufficient actionability. The mutation testing section, while informative, dominates the skill and explains concepts Claude already understands. The core QA responsibilities lack concrete, executable examples — there are no sample unit tests, integration tests, or E2E test patterns despite these being the primary purpose of the skill.
Suggestions
Move the mutation testing tools table and detailed explanation to a separate reference file (e.g., docs/mutation-testing.md) and keep only a brief trigger condition + link in the main skill.
Add 2-3 concrete, executable test examples for the core responsibilities: a unit test for a hook/util, a component test, and an E2E test skeleton using the mentioned frameworks (Vitest/Jest/Playwright).
Remove or drastically shorten explanatory content Claude already knows (what coverage means, why tests matter, what mutation testing is) and replace with terse decision rules.
Define a clear numbered workflow for a complete QA pass with explicit validation checkpoints (e.g., 'run tests → check coverage threshold → if below X, stop and report → run mutation if above 60%').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is very verbose at ~200+ lines. It explains concepts Claude already knows (what mutation testing is, what coverage means, what PDF-like analogies are), includes lengthy tables of tools per language that could be a reference file, and has significant padding like the 'Anti-Rationalization' table and philosophical explanations about why tests matter. The mutation testing section alone is disproportionately long for a QA skill overview. | 1 / 3 |
Actionability | There is one concrete code example (SQLite WAL cleanup pattern) and a semi-concrete mutation testing workflow, but most guidance is abstract ('escrever testes unitarios para hooks, stores e utils', 'cobrir caminho feliz'). No executable test examples are provided for the core responsibilities (unit, integration, E2E). The mutation testing workflow uses numbered steps but lacks executable commands beyond `npx stryker run`. | 2 / 3 |
Workflow Clarity | The mutation testing workflow has a reasonable sequence but lacks explicit validation checkpoints and error recovery loops. The main QA workflow is implicit — there's a checklist but no clear step-by-step process for how to execute a QA pass. The handoff section lists deliverables but doesn't sequence the overall QA process with validation gates. | 2 / 3 |
Progressive Disclosure | References to external files exist (personas/test-engineer.md, docs/skill-guides/qa-testing.md, various policies), which is good. However, the skill itself is monolithic with too much inline content that should be in referenced files (the entire mutation testing tools table, the anti-rationalization table). The mutation testing section alone could be its own reference document, keeping the SKILL.md leaner. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- felvieira/claude-skills-fv
- Commit
7577622
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.