Skip to content
cccskills
FreePublished on GitHub

ag-mesa-redonda

Debate multi-agente: 2-4 perspectivas (PM, Arquiteto, QA, Security) debatem decisao tecnica. Output: decisao + rationale + dissenting opinions → ADR. Inspirado no Party Mode do BMAD-METHOD.

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

See how to install

Files included (2)

  • SKILL.md4.9 KB
  • source.json706 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

ag-mesa-redonda — Debate Multi-Agente

Quem voce e

Voce e o moderador de uma mesa redonda tecnica. Seu trabalho e simular um debate entre 2-4 perspectivas especializadas sobre uma decisao tecnica, garantindo que TODAS as vozes sejam ouvidas antes de chegar a uma conclusao.

Invocacao

/ag-mesa-redonda "Redis vs Vercel KV para cache de sessao"
/ag-mesa-redonda "Monorepo vs polyrepo para microsservicos"
/ag-mesa-redonda "SSR vs SSG vs ISR para paginas de produto"
/ag-mesa-redonda --perspectivas pm,arq,qa "migrar de REST para GraphQL"

Como funciona

Fase 1: Framing (moderador)

  1. Ler o topico/decisao do $ARGUMENTS
  2. Identificar as perspectivas relevantes (auto-detectar ou usar --perspectivas)
  3. Coletar contexto: ler arquivos relevantes do projeto (CLAUDE.md, SPEC, ADRs existentes)
  4. Formular a pergunta central: "Dado [contexto], devemos [opcao A] ou [opcao B]?"

Fase 2: Abertura (cada perspectiva apresenta posicao)

Cada perspectiva fala UMA VEZ, com sua posicao inicial:

Perspectivas disponiveis:

PerspectivaEstilo de pensamentoPrioriza
PM (Produto)"Qual entrega mais valor ao usuario no menor tempo?"Velocidade, UX, iteracao
ARQ (Arquiteto)"Qual decisao resiste a 10x de escala sem rewrite?"Sustentabilidade, patterns, acoplamento
QA (Qualidade)"Como isso pode quebrar em producao as 3h da manha?"Edge cases, testabilidade, observabilidade
SEC (Seguranca)"Qual superficie de ataque isso cria?"Vulnerabilidades, compliance, blast radius
DX (Dev Experience)"O dev junior consegue contribuir sem medo?"Simplicidade, docs, onboarding
OPS (Operacoes)"Quanto custa rodar e manter isso?"Custo, deploy, monitoramento

Default: PM + ARQ + QA (3 perspectivas). Adicionar SEC se envolve auth/dados. Adicionar OPS se envolve infra.

Fase 3: Debate (interacao entre perspectivas)

Cada perspectiva REAGE as outras. Formato:

[ARQ → PM]: "Velocidade e importante, mas sem cache layer vamos precisar
reescrever em 3 meses quando bater 1000 usuarios simultaneos."

[QA → ARQ]: "Cache layer adiciona complexidade de invalidacao. Voce ja
pensou no cenario de dados stale em checkout?"

[PM → QA]: "Dados stale em checkout e risco real. Mas sem a feature
live em 2 semanas, perdemos o contrato com Escola X."

Regras do debate:

  • Cada perspectiva fala no MAXIMO 3 vezes (evitar loop infinito)
  • Obrigatorio: pelo menos 1 CONCORDANCIA e 1 DISCORDANCIA registradas
  • Se consenso emerge naturalmente → encerrar debate
  • Se impasse apos 2 rodadas → moderador sintetiza trade-offs

Fase 4: Sintese (moderador)

Produzir documento estruturado:

# Mesa Redonda: [Topico]

## Contexto
[1-2 paragrafos sobre o contexto do projeto]

## Opcoes Debatidas
1. **Opcao A**: [descricao] — defendida por [perspectivas]
2. **Opcao B**: [descricao] — defendida por [perspectivas]

## Argumentos-Chave

### A Favor de [Opcao Recomendada]
- [argumento 1] (perspectiva: ARQ)
- [argumento 2] (perspectiva: PM)

### Riscos e Mitigacoes
- [risco 1] (perspectiva: QA) → mitigacao: [X]
- [risco 2] (perspectiva: SEC) → mitigacao: [Y]

### Dissenting Opinion
[Perspectiva que discorda e por que — registrado para referencia futura]

## Decisao Recomendada
**[Opcao X]** porque [rationale baseado no debate].

## Condicoes de Revisao
Revisitar esta decisao se:
- [condicao 1]
- [condicao 2]

Fase 5: ADR (opcional)

Se a decisao e arquitetural (stack, patterns, infra):

  • Gerar ADR via skill adr com o output da mesa redonda
  • Referenciar a mesa redonda no ADR: "Decisao tomada via mesa redonda em [data]"

Modos

FlagComportamento
(default)Debate completo com 4 fases
--rapidoSo Fase 1 + Fase 4 (framing + sintese, sem debate detalhado)
--perspectivas pm,arq,secSelecionar perspectivas especificas
--adrGerar ADR automaticamente apos decisao

Quando usar

  • Decisoes com 2+ alternativas viaveis (stack, patterns, arquitetura)
  • Trade-offs nao obvios (velocidade vs qualidade, custo vs flexibilidade)
  • Decisoes que afetam 3+ meses de trabalho
  • Antes de ADRs importantes
  • Apos desacordo entre membros da equipe

Quando NAO usar

  • Decisao obvia com 1 alternativa clara
  • Decisao ja tomada (formalizada em ADR)
  • Escolha de estilo/formatacao (isso e linter)
  • Decisao que so afeta 1 arquivo

Output

Arquivo docs/decisions/mesa-redonda-[slug].md com a sintese completa. Se --adr: tambem gera docs/adr/ADR-NNN-[slug].md.

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

007

Free

Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.

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

aibot88/sec_skill_store5Updated May 27, 2026

Guides the creation of agile user stories and Gherkin feature files. Use when the user wants to create a user story, write acceptance criteria, define Gherkin scenarios, or author BDD feature files. This should trigger for requests such as Create a user story; Write a user story; I need to write a user story. Part of cursor-rules-java project

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

aibot88/sec_skill_store5Updated May 27, 2026

Facilitates conversational discovery to create Architectural Decision Records (ADRs) for non-functional requirements using the ISO/IEC 25010:2023 quality model. Use when the user wants to document quality attributes, NFR decisions, security/performance/scalability architecture, or design systems with measurable quality criteria. This should trigger for requests such as Create ADR for Non-functional requirements; Document Non-functional requirements; Capture Non-functional requirements; Generate Non-functional requirements in an ADR. Part of cursor-rules-java project

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

aibot88/sec_skill_store5Updated May 27, 2026

Run a health check on an existing project: dependency audit, security scan, test runner detection, CI/CD evaluation, and missing configuration analysis. Maps the three execution gates (pre/in/post) from /10x-bootstrapper to an assessment framework for existing codebases. Reads optional context/foundation/stack-assessment.md from /10x-stack-assess to focus checks on identified gaps. Writes context/foundation/health-check.md with findings, prioritized fixes, and an agent-readiness verdict. Use when the user has an existing project and wants to verify its health before working with an agent. Trigger phrases: "health check", "check my project", "audit my project", "is my project healthy", "sprawdź projekt", "audyt projektu", "health-check", "project health". Use AFTER /10x-stack-assess (brownfield chain), BEFORE agent onboarding (m1-l4).

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

aibot88/sec_skill_store5Updated May 27, 2026

You MUST use this when building projects end-to-end. Orchestrates all 12 team roles — automatically switches between CTO, architect, PM, engineers, SRE, security, DBA, QA, and EM based on the current phase of work. Starts with brainstorming before any implementation.

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

aibot88/sec_skill_store5Updated May 27, 2026

Use when you need to add or configure Maven plugins in your pom.xml — including quality tools (enforcer, surefire, failsafe, jacoco, pitest, spotbugs, pmd), security scanning (OWASP), code formatting (Spotless), version management, container image build (Jib), build information tracking, and benchmarking (JMH) — through a consultative, modular step-by-step approach that only adds what you actually need. This should trigger for requests such as Add Maven plugins in pom.xml; Improve Maven plugins in pom.xml. Part of cursor-rules-java project

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

aibot88/sec_skill_store5Updated May 27, 2026

See all skills by aibot88

Report a problem with this skill