sdd-design
Skill0 starsChanged 54 days agoMITView on GitHub
Use after a requirements doc is approved to design the technical plan. Auto-use when the user approves requirements and says "plano", "plan", "design", "como vamos fazer", or asks to move an approved spec toward implementation. Converts approved requirements into design.md; refuses to run if not yet approved.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- GabrielaStark/starktheir own version, first seen Nov 1, 2026
- svg153/skillstheir own version, first seen Nov 1, 2026
- PedroMosquera/squadaitheir own version, first seen Oct 13, 2026
- luanmorenommaciel/agentspectheir own version, first seen Oct 8, 2026
- pchemguy/Skill-SDD-Managertheir own version, first seen Oct 6, 2026
- GabrielaStark/SDDtheir own version, first seen May 25, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- luanmorenommaciel/agentspec★ 256same name
- PedroMosquera/squadai★ 10same name
- GabrielaStark/SDD★ 1same name
- GabrielaStark/stark★ 1same name
- Maicololiveras/praxisgenai-agent-orchestrator★ 1same name
- svg153/skills★ 1same name
- callingcard1973/claude-skills★ 0same name
- pchemguy/Skill-SDD-Manager★ 0same 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.
- sdd-acceptanceSkill
- sdd-analyzeSkill
- sdd-backlogSkill
- sdd-constitutionSkill
- sdd-deliverySkill
- sdd-discoverySkill
- sdd-reportSkill
- sdd-requirementsSkill
- sdd-stateSkill
The file
Files
sdd-design
Converte um requirements.md aprovado em specs/<NNN>-<slug>/design.md.
Pré-condição
- O
requirements.mddo mesmo<NNN>-<slug>deve estarStatus: approved. - Se estiver
awaiting_approval/draft→ parar e pedir a aprovação antes (não planejar).
Passos
- Ler
requirements.md, aconstitution.md, oarchitecture.mde as convenções/guidelines do próprio projeto (CONTRIBUTING, guia de estilo, config de lint/format, padrões do código existente). - Preencher a partir de
${CLAUDE_PLUGIN_ROOT}/sdd/templates/design.md: estratégia técnica (1 recomendação, não catálogo), impacto por arquivo, dependências, riscos+mitigação, ordem de execução, validação planejada (como cada CA será provado), e a branch de trabalho (feat|fix|chore/<slug>). - Garantir que a estratégia respeita a
constitution.md— citar quais princípios guiam a escolha. - Preencher a Estratégia de testes (nível + casos de borda/erro por CA) — ver
test-strategy. - Citar as guidelines relevantes de
${CLAUDE_PLUGIN_ROOT}/sdd/guidelines/e onde importam (tdd,test-strategy,solid,defensive-programming,rich-domain,dry,kiss,yagni,clean-code,error-handling,secure-by-default,code-review). As guidelines do sdd-kit são uma base; as guidelines/convenções do próprio projeto têm precedência — onde conflitarem, o projeto vence. - Gravar
design.mdcomStatus: ready.
Regras
- A "Validação planejada" é a base do
sdd-acceptance— cada critério de aceite mapeado a uma prova. - Não incluir trabalho fora do escopo dos requisitos. Se surgir necessidade nova, volta pra
sdd-requirements. - Próximo passo natural:
sdd-backlog.
Estado (lock)
- Respeitar o protocolo do
sdd-state: lerstate.mdantes de agir; se outra feature estiverin_progress, parar e avisar. Ao iniciar/fechar esta etapa, atualizar o bloco LOCK e o histórico.
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
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.

