Skip to content
cccskills
FreePublished on GitHub

flow-review

Review a code diff or explicit file set through independent correctness and QA lenses. Use when the user asks for a code review, test-coverage assessment, pre-merge audit, or review gate in a PWDEV Flow workflow.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md2.2 KB
  • agents/openai.yaml194 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Review code and test evidence

Read collaboration, artifacts, and safety before reviewing.

Review is read-only. Do not implement fixes unless the user separately requests changes.

Establish the contract

  1. Resolve the scope from an explicit file list, diff range, active Flow state, or working-tree diff.
  2. Read applicable AGENTS.md, the relevant acceptance criteria, quality rules, and prohibitions.
  3. If scope is ambiguous, inspect safely and state the bounded scope used.

Correctness lens

  • Read the complete diff, not only a summary.
  • Check behavior, error paths, boundary cases, security, concurrency, data integrity, compatibility, conventions, and unnecessary complexity.
  • Report only actionable findings with severity, file, tight line range, consequence, and concrete remediation.
  • Use inline code comments when the runtime supports them.

QA lens

  • Map each acceptance criterion and changed behavior to existing tests.
  • Run the relevant test commands when safe and non-mutating beyond normal local build artifacts.
  • Identify untested failure paths and explain the smallest valuable missing test.
  • Distinguish environmental failures from product failures.

Run the two lenses sequentially by default. Use separate collaborating workers only when the user explicitly requests delegation or parallel agent work, following collaboration.

Verdict

Use the worst applicable result:

  • APPROVED: no critical or major finding and evidence is adequate;
  • CHANGES_REQUESTED: at least one major finding or material test gap;
  • BLOCKED: scope, evidence, or environment prevents a responsible review.

Return findings first, ordered by severity, followed by assumptions, test evidence, and verdict. Persist a report only when the user requested it or this is an active Flow phase with artifact persistence already authorized.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Accessibility auditing and remediation skill for Vue 3 + Reka UI. Use when reviewing components, verifying WCAG 2.1 AA, fixing ARIA issues, or validating keyboard navigation in Reka UI components.

The English summary is being prepared. Showing the original description.

pwdev-solucoes/pwdev-claude-marketplace3Updated Oct 15, 2026

Infraestrutura para IA — GPU, servidores MCP, gateway de LLM, pipeline de inferência, custo de token, cache semântico e observabilidade de modelo. Use quando o usuário disser "GPU", "MCP server", "LLM", "inferência", "modelo", "gateway de IA", "custo de token", "rate limit da API de IA", "self-host de modelo".

The English summary is being prepared. Showing the original description.

pwdev-solucoes/pwdev-claude-marketplace3Updated Oct 15, 2026

Escreve texto alternativo e descrição de imagem para peças de rede social. Use quando o usuário disser "alt text", "texto alternativo", "descrição da imagem", "acessibilidade da peça", "descrever para leitor de tela", ou automaticamente antes de qualquer publicação. Obrigatório em todas as peças — em carrossel, um por slide.

The English summary is being prepared. Showing the original description.

pwdev-solucoes/pwdev-claude-marketplace3Updated Oct 15, 2026

Organiza, compara e seleciona entre as variações geradas, e publica a grade de comparação como Artifact para aprovação do time. Use quando o usuário disser "qual dessas", "comparar as variações", "escolher a melhor", "mostrar as opções", "montar grade de aprovação", ou após qualquer lote de geração. Selecionar é trabalho, não detalhe.

The English summary is being prepared. Showing the original description.

pwdev-solucoes/pwdev-claude-marketplace3Updated Oct 15, 2026

Aumenta resolução e qualidade de imagem via Freepik/Magnific, ou orienta o processo manual quando não há chave. Use quando o usuário disser "upscale", "melhorar a resolução", "a imagem está pixelada", "Magnific", "Freepik", "aumentar a imagem", "imagem pequena demais". Gasta crédito — exige confirmação.

The English summary is being prepared. Showing the original description.

pwdev-solucoes/pwdev-claude-marketplace3Updated Oct 15, 2026

CI/CD e automação — GitHub Actions, Terraform, OpenTofu, Ansible, n8n. Use quando o usuário disser "pipeline", "CI/CD", "GitHub Actions", "workflow", "terraform", "ansible", "n8n", "automatizar", "deploy automático", "IaC".

The English summary is being prepared. Showing the original description.

pwdev-solucoes/pwdev-claude-marketplace3Updated Oct 15, 2026

See all skills by pwdev-solucoes

Report a problem with this skill