subagent-dev

2
0
Source

Execute implementation plans using fresh subagents per task with two-stage review (spec compliance + code quality). Use when executing multi-task plans with independent work units. Enhances ralph-loop methodology.

Install

mkdir -p .claude/skills/subagent-dev && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8083" && unzip -o skill.zip -d .claude/skills/subagent-dev && rm skill.zip

Installs to .claude/skills/subagent-dev

About this skill

Subagent-Driven Development

구현 계획을 서브에이전트 단위로 실행, 2단계 리뷰.

ralph-loop와의 관계

이 스킬은 ralph-loop의 "서브에이전트로 1태스크씩" 원칙을 강화한다:

  • ralph-loop = 전체 프로세스 (specs → plan → implement → test)
  • subagent-dev = implement 단계의 실행 패턴

프로세스

계획 읽기 → 태스크 전체 추출
  ↓
[태스크마다 반복]
  1. 구현 서브에이전트 디스패치 (태스크 전문 + 맥락)
     ├─ 질문 있으면? → 답변 후 재디스패치
     └─ 구현 + 테스트 + 커밋 + 셀프리뷰
  2. 스펙 검증 서브에이전트 디스패치
     ├─ 스펙 불일치? → 구현자가 수정 → 재검증
     └─ 통과
  3. 코드 품질 리뷰 서브에이전트 디스패치
     ├─ 품질 이슈? → 구현자가 수정 → 재리뷰
     └─ 승인
  4. 태스크 완료 표시
  ↓
전체 완료 → 최종 코드 리뷰 → 브랜치 마무리

2단계 리뷰의 핵심

Stage 1: 스펙 검증

  • 코드가 요구사항과 일치하는가?
  • 빠진 기능은? 추가된 불필요 기능은?
  • 스펙에 명시된 모든 항목이 구현됐는가?

Stage 2: 코드 품질

  • 중복 코드? 네이밍? 타입 커버리지?
  • 에러 처리? 엣지 케이스?
  • 성능 이슈? 보안 이슈?

왜 2단계?

  • 스펙 검증 = "맞는 것을 만들었는가?" (What)
  • 코드 품질 = "잘 만들었는가?" (How)
  • 하나의 리뷰에 합치면 둘 다 놓치기 쉬움

서브에이전트 프롬프트 구조

구현자 프롬프트

## 태스크
[계획에서 추출한 태스크 전문]

## 맥락
[관련 파일, 아키텍처, 제약 조건]

## 제약
- 이 태스크 범위만 수정
- TDD: 테스트 먼저, 구현 후
- 커밋 메시지 작성
- 셀프리뷰 결과 포함

## 출력
- 구현 요약
- 테스트 결과
- 셀프리뷰 발견사항

스펙 리뷰어 프롬프트

## 원본 스펙
[태스크 요구사항 전문]

## 검증 대상
[구현된 코드의 git diff 또는 파일 목록]

## 체크리스트
- 모든 요구사항 구현됐는가?
- 불필요한 추가 기능은?
- 엣지 케이스 처리?

장점

  • 신선한 컨텍스트: 태스크별 새 서브에이전트 = 오염 없음
  • 품질 게이트: 2단계 리뷰로 이중 검증
  • 속도: 컨트롤러가 태스크 맥락을 사전 준비
  • 질문 가능: 서브에이전트가 모호한 점을 질문

비용

  • 태스크당 3회 서브에이전트 (구현 + 스펙리뷰 + 품질리뷰)
  • 컨트롤러의 준비 작업 필요
  • 리뷰 루프 시 추가 호출

결론: 비용 대비 품질 이득이 크다. 특히 중요한 기능 구현 시 필수.

fivem

openclaw

Fix, create, or validate FiveM server resources for QBCore/ESX (config.lua, fxmanifest.lua, items, housing/furniture, scripts, MLOs). Use when asked to debug resource errors, convert ESX↔QB, update fxmanifest versions, add items, or source scripts from GitHub. Also use for SSH key generation for SFTP access.

575388

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

802305

research-paper-writer

openclaw

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

85172

keyword-research

openclaw

Discovers high-value keywords with search intent analysis, difficulty assessment, and content opportunity mapping. Essential for starting any SEO or GEO content strategy.

464118

html-to-ppt

openclaw

Convert HTML/Markdown to PowerPoint presentations using Marp

36494

weread

openclaw

WeChat Reading (微信读书) CLI tool for fetching notes and highlights. Use when: (1) user asks about weread/微信读书 notes or highlights, (2) fetching today's or recent reading notes, (3) exporting book highlights, (4) managing reading bookshelf, (5) any task involving reading notes from WeChat Reading.

12186

You might also like

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

3,2062,749

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

4,2481,829

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

2,2211,672

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

2,3601,518

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

2,6651,279

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

2,0721,001