Communitygithub.com

orch-build-mvp

디자인 또는 명세 문서를 읽고, 얇은 수직 슬라이스로 계획한 후 첫 번째 슬라이스를 스캐폴딩 및 TDD로 구현하고 검토하여 게이트 커밋까지 진행합니다. SDD/PRD를 작동하는 MVP로 전환할 때 사용합니다.

orch-build-mvp란 무엇인가요?

**orch-build-mvp** 스킬은 디자인 문서(SDD, PRD, system_design 등)를 입력으로 받아, 문서를 분석하고 수직 슬라이스(vertical slice)를 계획한 후 첫 번째 슬라이스를 스캐폴딩(scaffolding)하고 TDD 방식으로 구현하여 게이트 커밋(gated commit)하는 전체 파이프라인을 오케스트레이션합니다. 이 스킬은 이미 검증된 `orch-pipeline` 엔진을 기반으로 동작하며, GAN(Generative Adversarial Network) 기반의 반복 빌드 루프(`gan-generator` → `gan-evaluator`)를 재사용하여 코드 생성과 평가를 자동화합니다. 주요 플랫폼(Claude Code, Cursor, Codex 등)에서 사용할 수 있으며, 보안 트리거가 있는 슬라이스에는 `security-reviewer`를 자동으로 추가하여 안전성을 보장합니다. 사용자는 문서 경로 하나만 전달하면 되며, 이후 스캐폴딩, 코드 생성, 테스트, 검토, 커밋까지 대부분 자동화되어 있어 빠른 MVP 프로토타이핑에 이상적입니다.

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

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

orch-build-mvp은(는) 무엇을 하나요?

Actor · action · target: orch · build · mvp. orch-pipeline의 공유 엔진을 감싼 얇은 래퍼(wrapper)입니다.

사용 시점

  • 사용자가 디자인/명세 문서 (SDD, PRD, system_design)를 가지고 있고, 이를 기반으로 작동하는 수직 슬라이스(vertical slice)를 부트스트래핑하려는 경우.
  • 인자로 문서 경로를 받습니다. 예: civicpulse/docs/SDD-v0.6.md

동작 설정

  • 기본 크기 하한: large — 스캐폴드를 포함한 전체 파이프라인입니다.
  • 단계 마스크: 0 (명세 읽기) → 1 → 2 (메인) → 3 (스캐폴드) → 4 → 5 → 6.
  • 첫 번째 움직임 (단계 0 → 2): 문서를 읽고, 범위, 확정된 결정, 기능 목록을 추출한 다음 얇은 수직 슬라이스로 정렬합니다 (첫 번째는 종단간(end-to-end) 경로이며, 모든 모델을 먼저 만들고 모든 뷰를 만드는 방식이 아닙니다). 단계 3에서 첫 번째 슬라이스를 구축합니다.

작동 방식

  1. 위 설정으로 orch-pipeline 엔진을 실행합니다.
  2. 수동 반복 루프 대신 기존 GAN 하네스(harness)를 재사용합니다.
    • SDD를 gan-harness/spec.md + gan-harness/eval-rubric.md로 변환합니다. (이는 gan-planner가 생성할 내용을 대신합니다 — 명세는 이미 있습니다.)
    • /gan-build "<한 줄 요약>" --skip-planner 명령으로 빌드를 시작합니다. (기본값: --max-iterations 15, --pass-threshold 7.0, --eval-mode playwright; UI가 없는 슬라이스의 경우 --eval-mode code-only 사용)
    • 이 명령은 gan-generator → gan-evaluator 루프를 실행하고, 점수가 통과하거나 수렴할 때까지 gan-harness/feedback/feedback-NNN.md를 작성합니다.
  3. 게이트 1 (슬라이스 계획)과 게이트 2 (커밋 전)에서 멈춥니다. 스캐폴드와 각 슬라이스를 별도의 feat: 커밋으로 커밋합니다.
  4. 보안 트리거와 관련된 슬라이스에는 security-reviewer를 추가합니다.

예시

orch-build-mvp: civicpulse/docs/SDD-v0.6.md
→ SDD 읽기 → 슬라이스 목록 (수직) → 슬라이스 1 스캐폴드  [게이트 1: 승인]
→ /gan-build --skip-planner (생성기 → 평가기 루프) 점수와 명세 비교 → 검토
→ feat: 커밋  [게이트 2: 확인] → 다음 슬라이스

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.

관련 스킬