Automated summary
Conducts a deep code review by dispatching four parallel specialized agents (code quality, security, test quality, and architectural consequences) and consolidates findings into a structured report.
Strengths
- Covers four distinct review dimensions simultaneously
- Identifies conflicting opinions between reviewers
- Produces a structured report with severity classification
Limitations
- Requires high context length and may be resource-intensive
- May produce conflicting recommendations that need manual resolution
- Dependent on the quality of each individual agent's analysis
Use for large or critical pull requests where thorough review is needed across multiple dimensions.
Avoid for small, simple changes where a single-pass review is sufficient.
Security analysis
SafeThe skill orchestrates a code review using read-only tools (Read, Grep, Glob) and git diff via Bash, dispatching analysis agents that do not perform any destructive or exfiltrating actions. No risky operations are present.
No concerns found
How this analysis is madeExamples
/review-deep src/component.ts/review-deep/review-deep src/name: review-deep description: Code review paralelo com múltiplos agentes especializados. argument-hint: "[arquivo ou diretório]" user-invocable: true allowed-tools: Read, Grep, Glob, Bash, Agent model: opus effort: high context: fork
Review Deep — Code Review Paralelo Multi-Agente
Review profundo com 4 revisores paralelos: $ARGUMENTS
Escopo
Se argumento fornecido
Revisar: $ARGUMENTS
Se nenhum argumento
git diff --name-only HEAD
git diff --cached --name-only
Processo
Fase 1 — Preparação
- Identificar arquivos a revisar
- Ler cada arquivo para entender contexto
- Montar briefing: arquivos, propósito, stack
Fase 2 — Dispatch paralelo (4 agentes)
Despachar TODOS em paralelo:
Revisor 1 — Code Quality (backend/frontend)
- Correção lógica, edge cases, tipos
- Legibilidade, naming, SRP, dead code
- Padrões do projeto
Revisor 2 — Security (security)
- OWASP Top 10, input validation, injection
- Secrets, auth, headers, deps vulneráveis
Revisor 3 — Test Quality (backend/frontend)
- Cobertura: happy path + edge cases
- Nomes descritivos, AAA, mocks vs integração
Revisor 4 — Consequences (architect)
- Impacto em dependentes
- Breaking changes não documentados
- Efeitos cascata, compatibilidade
Fase 3 — Consolidação
- Coletar findings dos 4 revisores
- Remover duplicatas
- Marcar conflitos: "⚠️ Conflito" se revisores discordam
- Classificar por severidade
Fase 4 — Relatório
## Review Deep — Relatório Consolidado
### Revisores
| Revisor | Findings | Críticos | Importantes |
|---------|----------|----------|-------------|
### 🔴 Crítico (bloqueia merge)
- **[Revisor]** [arquivo:linha] Descrição
- Impacto: [...]
- Fix: [...]
### 🟡 Importante (deve corrigir)
### 🔵 Sugestão
### ⚠️ Conflitos entre revisores
- [Revisor A] diz X vs [Revisor B] diz Y
### ✅ Pontos positivos
## Veredicto: PASS | FAIL | NEEDS DISCUSSION
**Confiança: X/5**
Quando usar
/review= 1 pass sequencial, rápido, mudanças pequenas/review-deep= 4 agentes paralelos, PRs grandes ou críticos
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/review-deep-parallel-multi-agent-code-review-mrwakb6v/download' --output '.skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v/SKILL.md.part' && mv '.skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v/SKILL.md.part' '.skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Read, Grep, Glob, Bash, Agent
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v/SKILL.md' && test -s '.skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/review-deep' && cp -R '.skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v' '.claude/skills/review-deep'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v'openskills read 'review-deep-parallel-multi-agent-code-review-mrwakb6v'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/review-deep-parallel-multi-agent-code-review-mrwakb6v/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.