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".
88
85%
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 skill description that clearly defines its purpose as a final reviewer before deployment, lists concrete validation actions, and provides an extensive set of natural trigger terms in Portuguese. It explicitly addresses both what the skill does and when to use it, with minimal risk of conflicting with other skills due to its specific focus on the final deploy gate.
| 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' (explicit 'Use quando' clause plus a dedicated 'Trigger em' list with specific phrases). | 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 | Occupies a clear niche as a final pre-deploy review/gate skill, distinct from general code review or individual QA/security skills. The trigger terms like 'gate de deploy', 'aprovação', 'checklist final' are highly specific to this final validation step. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%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 comprehensive checklists and clear workflow sequencing including feedback loops and escalation paths. Its main weakness is the lack of executable verification commands — the checklists tell Claude *what* to check but not *how* to programmatically verify each item. There's also some redundancy between the Responsabilidades section and the detailed checklists that follow.
Suggestions
Add concrete verification commands for checklist items where possible (e.g., `npx tsc --noEmit` for TypeScript checks, `npm audit --audit-level=high` for security, `npx eslint . --quiet` for code quality)
Remove or merge the 'Responsabilidades' section into the checklist since it largely duplicates the same information in less actionable form
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy (e.g., 'Quando Usar'/'Quando Nao Usar' sections that are somewhat obvious, and the 'Responsabilidades' section largely duplicates what the checklist already covers). The checklists themselves are valuable and earn their tokens, but the overall document could be tightened by ~20-30%. | 2 / 3 |
Actionability | The checklists are concrete and specific (e.g., 'Nenhum console.log no código', 'npm audit sem HIGH/CRITICAL'), which is good. However, there are no executable commands or code examples for how to actually verify these items — no specific CLI commands, no scripts to run, no tool invocations. The guidance is specific about *what* to check but vague about *how* to check it programmatically. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced: receive → execute checklist → mark OK/FAIL → approve/reject → generate report. The rejection workflow includes explicit feedback loops (reject → orchestrator → responsible skill → fix → back to reviewer), a max retry count (3 cycles), and escalation path. Validation checkpoints are explicit throughout. | 3 / 3 |
Progressive Disclosure | The skill appropriately references external files (templates/review.md, templates/rejection.md, templates/commit-trailers.md, policies/*, GLOBAL.md) without inlining their content. References are one level deep and clearly signaled. The main content is well-organized with clear section headers for different checklist domains. | 3 / 3 |
Total | 10 / 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
e9f6648
- 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.