CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable gate playbook with explicit validation checkpoints and a real rejection feedback loop. Its main weakness is a verbatim duplicated section and some redundancy between the checklists and the Regras list that inflates the token budget.

Suggestions

Remove the verbatim-duplicated 'Constituicao como rubric primario' block (the section appears twice consecutively) to recover tokens and remove ambiguity about which copy is authoritative.

De-duplicate the 'Regras' list against the checklist sections: the 'NUNCA aprovar com findings críticos de segurança / sem testes / sem documentação' rules already appear in the Segurança, Testes, and Documentação checklists.

Mark which referenced files (policies/*.md, templates/*.md, personas/code-reviewer.md) are kit-level vs. bundled so a reader can tell which paths are guaranteed present without inspecting the surrounding kit.

DimensionReasoningScore

Conciseness

Mostly lean checklists and rules that assume Claude's competence, but the 'Constituicao como rubric primario' section is duplicated verbatim (appearing twice) and the 'Regras' section re-states items already covered in the security/test/docs checklists — clear tightening opportunities beyond a minor trim.

3 / 5

Actionability

Concrete, specific guidance throughout: checklists with measurable thresholds ('Cobertura >= 80%', 'npm audit sem HIGH/CRITICAL'), a numbered review flow, a rejection taxonomy ('codigo | teste | seguranca | documentacao | performance'), and named commands/MCP tools ('/diff-impact', 'devkit_suggest_trailers').

4 / 5

Workflow Clarity

Clear sequenced Fluxo de Review (1-7) with explicit OK/FAIL checkpoints and APPROVED/REJECTED decision, plus a rejection feedback loop ('Reviewer rejeita -> Orquestrador -> skill corrige -> Volta pro Reviewer') with a max-3-cycle cap and escalation — matching the explicit-validation-plus-feedback-loop anchor.

5 / 5

Progressive Disclosure

Well-organized sections with one-level-deep, backtick-signaled references to external materials (policies/*.md, templates/*.md, personas/code-reviewer.md), but the duplicated section and references to kit-level files not present in this bundle leave minor organization/verifiability gaps.

4 / 5

Total

16

/

20

Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it states concrete capabilities and pairs them with an explicit 'Use quando' clause plus a rich list of natural trigger phrases. The only weakness is mild overlap risk with adjacent review skills that the description does not disambiguate.

DimensionReasoningScore

Specificity

Lists multiple 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' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (validação completa, checar qualidade, confirmar segurança/QA/documentação, gerar relatório) and 'when' ('Use quando precisar validar...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes a broad set of natural trigger phrases users would say — 'review final', 'aprovação', 'rejeição', 'gate de deploy', 'checklist final', 'aprovar deploy', 'pode deployar', 'pronto pra produção', 'validar entrega', 'última verificação' — with synonyms and casual variations.

5 / 5

Distinctiveness Conflict Risk

Clear niche as a final deploy gate ('Reviewer Final', 'gate de deploy'), but broad terms like 'validação' and 'review' carry minor overlap risk with related review skills (e.g. the in-flight doubt-driven review referenced in the body), which is not disambiguated in the description itself.

4 / 5

Total

19

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
felvieira/claude-skills-fv
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.