Communitygithub.com

orch-build-mvp

Orquestra a inicialização de um MVP funcional a partir de um documento de design ou especificação — ingira o documento, planeje fatias verticais finas, construa a primeira fatia de ponta a ponta e, em seguida, implemente com TDD, revise e faça commit controlado. Use para transformar um SDD/PRD em um ponto de partida funcional.

O que é orch-build-mvp?

Esta skill orquestra a transformação de um documento de design ou especificação (como SDD, PRD ou system_design) em um MVP funcional através de fatias verticais planejadas. Ela atua como um wrapper sobre o mecanismo compartilhado em `orch-pipeline`, lendo o documento de especificação, extraindo escopo, decisões vinculadas e lista de funcionalidades, e ordenando-as em fatias verticais finas — priorizando um caminho de ponta a ponta completo em vez de construir todos os modelos primeiro. A skill utiliza o harness GAN existente para o loop de geração e avaliação, traduzindo o SDD em especificações e rubricas de avaliação, e acionando o comando `/gan-build` com o modo apropriado (Playwright para slices de UI, code-only para outros). O processo para em dois portões principais: Gate 1 (aprovação do plano de fatias) e Gate 2 (confirmação pré-commit), garantindo que cada fatia seja commitada separadamente como `feat:` e que uma revisão de segurança seja adicionada quando necessário. É ideal para transformar rapidamente documentos de design em um MVP executável.

Funciona com✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/tree/main/skills/orch-build-mvp

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

O que orch-build-mvp faz?

Ator · ação · alvo: orch · build · mvp. Wrapper fino sobre o mecanismo compartilhado em orch-pipeline.

Quando usar

  • O usuário possui um documento de design / especificação (SDD, PRD, system_design) e deseja uma fatia vertical funcional inicializada a partir dele.
  • Recebe o caminho do documento como argumento, ex.: civicpulse/docs/SDD-v0.6.md.

Configurações de operação

  • Tamanho mínimo padrão: grande — este é o pipeline completo, incluindo Scaffold.
  • Máscara de fase: 0 (ler a especificação) → 1 → 2 (pesado) → 3 (scaffold) → 4 → 5 → 6.
  • Primeira movimentação (fase 0 → 2): ler o documento; extrair escopo, decisões vinculadas e a lista de funcionalidades; ordená-las em fatias verticais finas (um caminho de ponta a ponta primeiro, não todos-modelos-depois-todas-visões). A fase 3 monta essa primeira fatia.

Como funciona

  1. Execute o mecanismo orch-pipeline com as configurações acima.
  2. Reutilize o harness GAN existente em vez de criar manualmente um loop de iteração:
    • Traduza o SDD para gan-harness/spec.md + gan-harness/eval-rubric.md (isso substitui o que o gan-planner geraria — você já tem a especificação).
    • Conduza a construção com /gan-build "<resumo de uma linha>" --skip-planner (padrões: --max-iterations 15, --pass-threshold 7.0, --eval-mode playwright; use --eval-mode code-only para fatias não-UI).
    • Esse comando executa o loop gan-generator → gan-evaluator e escreve gan-harness/feedback/feedback-NNN.md até que a pontuação passe ou estabilize.
  3. Pare no Gate 1 (plano de fatias) e Gate 2 (pré-commit). Faça commit do scaffold e de cada fatia como commits feat: separados.
  4. Adicione security-reviewer para qualquer fatia que toque em um gatilho de segurança.

Exemplo

orch-build-mvp: civicpulse/docs/SDD-v0.6.md
→ ler SDD → lista de fatias (vertical) → fatia scaffold 1  [GATE 1: aprovar]
→ /gan-build --skip-planner (loop gerador → avaliador) pontua vs especificação → revisar
→ commit feat:  [GATE 2: confirmar] → próxima fatia

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

Habilidades Relacionadas