reviewer
Skill do Reviewer Final para validação completa antes do deploy. Use quando precisar validar que todos os passos do pipeline foram executados, checar qualidade de código, confirmar segurança, confirmar QA, confirmar documentação, ou gerar relatório de aprovação/rejeição. Trigger em: "review final", "reviewer", "aprovação", "rejeição", "validação final", "gate de deploy", "checklist final", "aprovar deploy", "pode deployar", "pronto pra produção", "validar entrega", "review completo", "última verificação".
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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, well-crafted skill description that clearly defines its purpose as a final reviewer/validation gate before deployment. It excels in all dimensions by listing concrete actions, providing extensive natural trigger terms, explicitly stating both what it does and when to use it, and occupying a distinct niche. The only minor note is that it's in Portuguese, which is appropriate if the skill ecosystem targets Portuguese-speaking users.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: validating pipeline steps, checking code quality, confirming security, confirming QA, confirming documentation, and generating approval/rejection reports. | 3 / 3 |
Completeness | Clearly answers both 'what' (validate pipeline steps, check code quality, confirm security/QA/documentation, generate approval/rejection report) and 'when' with an explicit 'Use quando' clause and a dedicated 'Trigger em' list. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms in Portuguese including 'review final', 'aprovação', 'rejeição', 'gate de deploy', 'pode deployar', 'pronto pra produção', 'validar entrega', and many more variations users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche as a final pre-deploy validation/gate skill. The specific triggers like 'gate de deploy', 'aprovação', 'checklist final', and 'pode deployar' are unlikely to conflict with other skills such as general code review or testing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured review gate skill with highly actionable checklists, clear workflow sequencing with feedback loops and escalation paths, and good progressive disclosure to external templates and policies. The main weakness is moderate verbosity — some sections like 'Quando Usar/Não Usar' and 'Entradas/Saídas Esperadas' could be trimmed, and there's some repetition in referencing templates and policies across multiple sections. The anti-rationalization table is a strong addition that adds practical value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some sections that could be tightened — 'Quando Usar/Não Usar' and 'Entradas/Saídas Esperadas' sections add moderate value but are somewhat verbose. The checklists themselves are well-structured and earn their tokens, but the overall document is long with some redundancy (e.g., repeated references to templates and policies). | 2 / 3 |
Actionability | The checklists are highly concrete and specific — each item is a verifiable yes/no check (e.g., 'npm audit sem HIGH/CRITICAL', 'Cobertura >= 80%', 'Nenhum console.log no código'). The rejection workflow specifies exactly what must be included (responsible skill, specific file/line, classification). The flow is copy-paste usable as a review process. | 3 / 3 |
Workflow Clarity | The review flow is clearly sequenced (receive → checklist → mark OK/FAIL → approve/reject → report). The rejection workflow includes explicit feedback loops (Reviewer rejects → Orchestrator → responsible skill → fix → back to Reviewer), a max retry limit (3 cycles), and escalation path. Validation checkpoints are embedded throughout the checklists. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately and at one level deep: templates (review.md, rejection.md), policies (execution.md, handoffs.md, etc.), and personas (code-reviewer.md). The main content stays focused on the review process while pointing to detailed resources for specific concerns. Navigation is clearly signaled. | 3 / 3 |
Total | 11 / 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
d87ad31
- 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.