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
Quality
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 well-crafted skill description that excels across all dimensions. It clearly defines the skill's purpose as a final deployment validation gate, lists specific validation actions, and provides comprehensive trigger terms in Portuguese. The explicit 'Use quando' and 'Trigger em' sections make it highly actionable for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'validar que todos os passos do pipeline foram executados', 'checar qualidade de código', 'confirmar segurança', 'confirmar QA', 'confirmar documentação', 'gerar relatório de aprovação/rejeição'. | 3 / 3 |
Completeness | Clearly answers both what (validate pipeline steps, check code quality, confirm security/QA/documentation, generate approval/rejection report) AND when with explicit 'Use quando' clause and comprehensive 'Trigger em' list. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say in Portuguese: 'review final', 'aprovação', 'rejeição', 'pode deployar', 'pronto pra produção', 'validar entrega', 'última verificação' - these are natural phrases developers would use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche as a final deployment gate/reviewer skill with distinct triggers like 'gate de deploy', 'checklist final', 'aprovar deploy' that are specific to pre-deployment validation and unlikely to conflict with 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 strong skill with excellent actionability and workflow clarity. The comprehensive checklists provide concrete validation criteria, and the rejection workflow includes proper feedback loops with escalation paths. Minor verbosity in some sections and slight redundancy in checklist items prevent a perfect conciseness score, but overall the skill is well-designed for its gate-keeping purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy - the checklist items repeat concepts that could be consolidated, and some sections like 'Quando Usar/Nao Usar' could be tighter. The governance references add overhead but serve a purpose. | 2 / 3 |
Actionability | Highly actionable with concrete checklists, specific validation criteria (e.g., 'Cobertura >= 80%', 'npm audit sem HIGH/CRITICAL'), clear workflow steps, and explicit rules. The checklist format makes it copy-paste ready for validation. | 3 / 3 |
Workflow Clarity | Excellent workflow clarity with explicit sequencing (6-step review flow), clear rejection workflow with feedback loops (Reviewer → Orquestrador → skill → Reviewer), validation checkpoints, and a maximum retry limit (3 cycles) with escalation path. | 3 / 3 |
Progressive Disclosure | Well-structured with clear references to external templates (templates/review.md, templates/rejection.md) and policies. Content is appropriately organized into sections with the main skill file serving as an actionable overview pointing to supporting materials. | 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.
524725e
Table of Contents
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.