Communitygithub.com

orch-build-mvp

Orquestra el arranque de un MVP funcional a partir de un documento de diseño o especificación: ingiere el documento, planifica slices verticales delgados, genera el primer slice completo y luego lo implementa con TDD, revisa y realiza commits controlados. Úsalo para convertir un SDD/PRD en un punto de partida funcional.

¿Qué es orch-build-mvp?

orch-build-mvp es una habilidad diseñada para desarrolladores y agentes de IA que necesitan convertir rápidamente un documento de diseño o especificación (SDD, PRD, system_design) en un MVP funcional. Su enfoque principal es la planificación e implementación de slices verticales delgados, asegurando que cada slice cubra un camino completo de extremo a extremo antes de pasar al siguiente. La habilidad es compatible con plataformas como Claude Code, Cursor y Codex, y se basa en el motor compartido 'orch-pipeline'. El proceso comienza leyendo el documento, extrayendo el alcance, las decisiones vinculantes y la lista de características, y luego ordenándolas en slices verticales. El primer slice se implementa utilizando un harness GAN existente, que traduce el SDD en especificaciones y rúbricas de evaluación, y luego ejecuta un bucle generador-evaluador hasta que se alcanza una puntuación de aprobación. Cada slice genera un commit independiente con mensaje 'feat:' y se detiene en compuertas específicas (Gate 1: aprobación del plan de slice, Gate 2: revisión previa al commit) para garantizar calidad y control.

Compatible con✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/orch-build-mvp

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

¿Qué hace orch-build-mvp?

Actor · acción · objetivo: orch · build · mvp. Capa delgada sobre el motor compartido en orch-pipeline.

Cuándo usarlo

  • El usuario tiene un documento de diseño / especificación (SDD, PRD, system_design) y desea un slice vertical funcional generado a partir de él.
  • Toma la ruta de un documento como argumento, por ejemplo civicpulse/docs/SDD-v0.6.md.

Configuración de operación

  • Tamaño mínimo por defecto: grande — es el pipeline completo que incluye Scaffold.
  • Máscara de fase: 0 (leer la especificación) → 1 → 2 (pesada) → 3 (scaffold) → 4 → 5 → 6.
  • Primer movimiento (fase 0 → 2): leer el documento; extraer alcance, decisiones vinculantes y la lista de características; ordenarlas en slices verticales delgados (primero un camino completo de extremo a extremo, no todos los modelos y luego todas las vistas). La fase 3 monta ese primer slice.

Cómo funciona

  1. Ejecuta el motor orch-pipeline con la configuración anterior.
  2. Reutiliza el harness GAN existente en lugar de crear manualmente un bucle de iteración:
    • Traduce el SDD a gan-harness/spec.md + gan-harness/eval-rubric.md (esto sustituye lo que generaría gan-planner — ya tienes la especificación).
    • Ejecuta el comando /gan-build "<breve descripción de una línea>" --skip-planner (valores por defecto: --max-iterations 15, --pass-threshold 7.0, --eval-mode playwright; usa --eval-mode code-only para slices no relacionados con la interfaz de usuario).
    • Este comando ejecuta el bucle gan-generator → gan-evaluator y escribe gan-harness/feedback/feedback-NNN.md hasta que la puntuación supera el umbral o se estanca.
  3. Detente en Compuerta 1 (plan de slice) y Compuerta 2 (pre-commit). Realiza commits del scaffold y de cada slice como commits separados con mensaje feat:.
  4. Agrega security-reviewer para cualquier slice que toque un disparador de seguridad.

Ejemplo

orch-build-mvp: civicpulse/docs/SDD-v0.6.md
→ leer SDD → lista de slices (verticales) → scaffold slice 1  [COMPUERTA 1: aprobar]
→ /gan-build --skip-planner (bucle generador → evaluador) puntúa contra especificación → revisar
→ commit feat:  [COMPUERTA 2: confirmar] → siguiente slice

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/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

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.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

Skills relacionados