Communitygithub.com

GAN-스타일 하네스

GAN에서 영감을 받은 생성기-평가기 에이전트 하네스로, 고품질 애플리케이션을 자율적으로 구축합니다. Anthropic 기반.

GAN-스타일 하네스란 무엇인가요?

이 스킬은 GAN(생성적 적대 신경망)의 원리를 차용한 멀티 에이전트 하네스로, 생성(Generator)과 평가(Evaluator)를 분리하여 두 에이전트 간의 적대적 피드백 루프를 통해 결과물의 품질을 극대화합니다. Planner, Generator, Evaluator라는 세 가지 에이전트가 단계적으로 협력하며, Planner는 한 줄짜리 프롬프트를 상세한 제품 명세로 확장하고, Generator는 이를 구현하며, Evaluator는 Playwright MCP를 통해 실제 실행 중인 애플리케이션을 테스트하고 엄격한 기준으로 점수를 매깁니다. 이는 단일 에이전트가 자기 평가에서 지나치게 낙관적인 경향을 보이는 문제를 해결하며, 설계 품질, 독창성, 장인 정신, 기능성의 네 가지 기준으로 평가됩니다. Sonnet 모델이 기본이지만 환경 변수를 통해 모델을 업그레이드할 수 있으며, 약 5-15회의 반복을 거쳐 프로덕션 수준의 결과물을 만들어냅니다. 빠른 단일 파일 수정이나 예산이 제한된 작업에는 적합하지 않지만, 'AI 슬롭' 스타일을 피하고 고품질의 완성형 애플리케이션을 원하는 프로젝트에 이상적입니다.

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

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

GAN-스타일 하네스 스킬

장기 실행 애플리케이션 개발을 위한 Anthropic의 하네스 설계에서 영감을 받음 (2026년 3월 24일)

생성과 평가를 분리하여, 단일 에이전트가 달성할 수 있는 것보다 훨씬 뛰어난 품질을 이끌어내는 적대적 피드백 루프를 구축하는 멀티 에이전트 하네스입니다.

핵심 통찰

에이전트가 자신의 작업을 평가하라고 요청받으면 병적으로 낙관적입니다. 평범한 결과물을 칭찬하고, 정당한 문제점들을 스스로 합리화합니다. 하지만 별도의 평가자를 가차 없이 엄격하게 만드는 것은 생성자에게 자기 비판을 가르치는 것보다 훨씬 다루기 쉽습니다.

이는 GAN(생성적 적대 신경망)과 동일한 역학입니다. 생성자는 결과물을 만들고, 평가자는 비판하며, 그 피드백이 다음 반복을 추진합니다.

사용 시기

  • 한 줄짜리 프롬프트로 완전한 애플리케이션 구축
  • 높은 시각적 품질이 필요한 프론트엔드 디자인 작업
  • 단순한 코드가 아닌 실제 작동하는 기능이 필요한 풀스택 프로젝트

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