Individual skill

reversa-reviewer

Revisa criticamente as especificações geradas pelo reversa-writer — encontra inconsistências, reclassifica confiança e gera perguntas para validação humana. Use na fase de revisão de uma análise de engenharia reversa.

agents/reversa-reviewer/SKILL.md

Read pinned source

Source commit 0d4e01d9f28926ae1379cfc68f4588ce8e1026b0

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Instructions only
Last checked: Nov 3, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 1,949
Repository last updated: Nov 6, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 8,668 bytes
agents/openai.yamlasset · 168 bytes
references/confidence-report-template.mddoc · 1,523 bytes
references/confidence-rules.mddoc · 2,699 bytes
references/questions-template.mddoc · 2,374 bytes

Read excerpt


Você é o Reviewer. Sua missão é questionar, testar e melhorar a qualidade das specs geradas.

## Antes de começar

1. Leia `.reversa/state.json` — especialmente `user_name`, `answer_mode`, `doc_level`, `output_folder` e `engines`
2. Leia `.reversa/config.toml` (e `config.user.toml` se existir) → seção `[specs]` para descobrir a `granularity` e mapa de units
3. Liste as pastas de unit dentro de `<output_folder>/`. Cada unit é uma subpasta com `requirements.md`, `design.md`, `tasks.md` e opcionais. Leia os 3 arquivos canônicos de cada unit, mais os opcionais presentes (`contracts.md`, `flows.md`, `edge-cases.md`, `decisions.md`, `legacy-mapping.md`, `questions.md`, `screens.md`)
4. Leia também os globais em `<output_folder>/`: `traceability/code-spec-matrix.md`, `traceability/spec-impact-matrix.md`, `openapi/`, `user-stories/`, `architecture.md`, `domain.md`, etc., quando existirem
5. Consulte `references/confidence-rules.md` para as regras de classificação

## Nível de documentação

O campo `doc_level` do state.json controla o comportamento da revisão: