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

sdd-requirements

Skill0 starsChanged 54 days agoMITView on GitHub

Auto-use when the user wants a new feature, product/behavior change, API or contract change, or says anything like "quero", "preciso", "vamos fazer", "feature", "spec", "nova tela", "novo endpoint" — even without naming this skill. Turns a story/description/ticket/code into a versioned requirements doc, then STOPS for human approval before any design or code.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. GabrielaStark/SDD★ 1same name
    2. GabrielaStark/stark★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

Create a free account to mount
Files
SKILL.md

sdd-requirements

Transforma demanda (história, descrição, ticket, bug, código) em specs/<NNN>-<slug>/requirements.md.

Passos

  1. Ler constitution.md (princípios que a feature herda) e architecture.md se existirem. Se o repo for novo/desconhecido e isso ajudar, sugerir sdd-constitution e/ou sdd-discovery antes.
  2. Definir <slug> (kebab curto do título) e <NNN>: varrer specs/, pegar o maior número existente + 1, com 3 dígitos (001, 002…). Criar a pasta specs/<NNN>-<slug>/.
  3. Preencher a partir de ${CLAUDE_PLUGIN_ROOT}/sdd/templates/requirements.md: problema, escopo (dentro/fora), requisitos em notação EARS, critérios de aceite (Dado/Quando/Então), premissas, dúvidas, rastreabilidade.
  4. Clarify: varrer o documento por ambiguidade e fazer as perguntas de decisão humana que faltarem — não preencher dúvida crítica com achismo. Repetir até não restar ambiguidade bloqueante.
  5. Rodar o checklist de qualidade do rodapé do template (EARS sem ambiguidade, todo CA verificável, escopo-fora preenchido, nada contra a constitution.md, zero detalhe de implementação).
  6. Gravar requirements.md com Status: awaiting_approval.

Gate (obrigatório)

  • Resumir em 5–10 linhas + critérios e pedir aprovação humana explícita.
  • NÃO gerar design, NÃO criar branch, NÃO codar neste turno.
  • Só após um "aprovado"/"segue"/"implementa" do humano, mudar Status: approved e seguir para sdd-design.

Regras

  • Critério de aceite tem que ser verificável (vira teste/evidência lá no sdd-acceptance).
  • Escopo "fora" explícito evita creep.
  • Se a demanda já tem número/slug (retomada), atualizar o documento existente em vez de duplicar.

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