跳到正文
cccskills
免费在 GitHub 公开

feat-review

Use when the user wants a code review of an explicit range or set of files — correctness, security, performance, conventions, tests — with stable findings (CR-nnn, BLOCKER..INFO) and rule citations — 'revisar os últimos commits', 'code review da feature X', 'review base..HEAD'. Plans a REPORT-mode review (no code changes, no commit). Do NOT use to fix code (feat-feature / feat-quick), to write tests (feat-test) or for UI/UX design critique.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(2)

  • SKILL.md3.1 KB
  • agents/openai.yaml184 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Review plan

Plan type review — always executed in REPORT mode: findings only, no code change, no commit. The review contract (scope, finding fields, severities, dimensions, verdict) is references/review.md; read it before planning.

Procedure

  1. Language — resolve lang (references/language.md).
  2. Fix the scope — resolve the argument into an explicit BASE..TARGET range:
    • a feature slug → base_commit from its progress.md/plan.done.md to HEAD;
    • "last N commits" → HEAD~N..HEAD; a branch → $(git merge-base main <branch>)..<branch>;
    • paths only → the range that last touched them, confirmed with the human. Record (audit on): sh "<plugin-root>/scripts/audit-log.sh" event review "" scope <base>..<target>. Build the package: sh "<plugin-root>/scripts/review_package.sh" <base> <target> .planning/feat/features/{slug}/review [-- <paths>]. Exit 2/3 (bad or empty range) → stop and ask; never widen the scope silently.
  3. Method — follow references/pwdevia-method.md with plan_type: review:
    • Persona: senior code reviewer for the stack in context/architecture.md.
    • §3 lists the package files, the project instructions file, context/conventions.md, context/concerns.md and, when reviewing a feature, its plan.md.
    • §4 lists ONLY .planning/feat/features/{slug}/review.md (rendered from templates/review-report.md) — this is what puts the executor in REPORT mode. Do not name it report.md: some runtimes refuse subagent writes to report-like names.
    • §5: every finding has id, severity, path:line, rule citation, evidence and suggestion; the five dimensions are covered; lint/test commands run on the target and recorded.
  4. After execution, when the verdict is CHANGES_REQUESTED, offer to turn the report's fix scope into a fix plan (feat-feature or feat-quick), citing the report in §3.

Prohibitions

  • Never fix code in a review plan, and never list project files in §4.
  • Never skip the security dimension.
  • Never rate a cosmetic issue above LOW, or a finding without a rule citation above LOW.
  • Never move HEAD in the working checkout — use a temporary worktree to inspect other states.

Language: resolve lang per references/language.md before any human-facing output. Safety: never read or expose .env* (except .env.example/.template/.sample), keys, certificates or credentials — references/safety.md. Paths references/, scripts/, templates/, schemas/ are relative to the plugin root (references/runtime.md).

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

ai-infra

免费

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".

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

alt-text

免费

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.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

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.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

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.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

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".

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

查看 pwdev-solucoes 的全部技能

报告此技能的问题