agentleFS
Sign inStart free
duviolinduviolin/sdd-kit/skills/sdd-analyze/SKILL.md

sdd-analyze

Skill0 starsChanged 54 days agoMITView on GitHub

Use to cross-check consistency across requirements, design and tasks before implementing. Auto-use when tasks.md is ready, or the user says "analisa", "analyze", "checa consistência", "revisa antes de codar". A cheap gate that blocks delivery if artifacts disagree. Reports findings; does not write code.

The file

Create a free account to mount
Files
SKILL.md

sdd-analyze

Gate de consistência entre requirements.md, design.md e tasks.md de specs/<NNN>-<slug>/, antes de gastar execução em sdd-delivery. Não escreve código nem novos artefatos — reporta.

Pré-condição

  • Existir tasks.md para o <NNN>-<slug>.

Passos

  1. Ler constitution.md (se houver), requirements.md, design.md e tasks.md.
  2. Checar cobertura e coerência:
    • Requisito → design: todo requisito tem tratamento no design?
    • CA → task: todo critério de aceite tem ao menos uma task que o prova? Nada órfão.
    • Task → origem: toda task rastreia a um passo do design / requisito? Nada inventado.
    • Escopo: nada no design/tasks está no "Fora (explicitamente)" dos requisitos.
    • Constitution: design e tasks respeitam os princípios do projeto?
    • Contradições: dependências de task coerentes; ordem viável; sem conflito entre artefatos.
  3. Emitir veredito: consistente ou inconsistente com a lista exata do que corrigir.

Regras

  • Inconsistente → parar. Corrigir na skill de origem (sdd-requirements/sdd-design/ sdd-backlog) antes de implementar. Não seguir para sdd-delivery com o gate vermelho.
  • Consistente → liberar sdd-delivery.

Estado (lock)

  • Respeitar o protocolo do sdd-state: ler state.md antes de agir; se outra feature estiver in_progress, parar e avisar. Ao iniciar/fechar esta etapa, atualizar o bloco LOCK e o histórico.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free