원클릭으로 Manus에서 모든 스킬 실행

fullstack-webapp

스타5

포크0

업데이트2026년 4월 7일 05:39

Use when building a full-stack web application from scratch or adding major features — assembles architect, frontend-dev, backend-dev, qa-engineer, and devops-engineer to deliver complete code, tests, and deployment setup. Covers React/Next.js + Node.js/Python backends, PostgreSQL/MongoDB databases, and Vercel/AWS/Railway deployment. Does NOT cover mobile apps (React Native/Flutter), desktop apps, game development, or ML/AI model training. Also triggers on: re-run, update, revise, supplement.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

drvoss

drvoss/harness-100-copilot

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Fullstack Web App — Full-Stack Development Pipeline

An agent team collaborates to develop web apps through requirements → design → frontend → backend → testing → deployment.

Execution Mode

File-Bus Team — Agents communicate via _workspace/messages/, orchestrator sequences execution.

Agent Composition

Agent	File	Role	Type
architect	`agents/architect.md`	Requirements, architecture, DB, API design	general-purpose
frontend-dev	`agents/frontend-dev.md`	React/Next.js frontend implementation	general-purpose
backend-dev	`agents/backend-dev.md`	API, DB, auth, business logic	general-purpose
qa-engineer	`agents/qa-engineer.md`	Test strategy and automation	general-purpose
devops-engineer	`agents/devops-engineer.md`	CI/CD, deployment, monitoring	general-purpose

Pre-Flight Checks

_workspace/ is clean or confirmed stale
All 5 agent files present in agents/
User has provided app description with at least core features

Phase 1: Setup (Orchestrator)

task(agent_type="general-purpose",
     description="Read the user's web app request. Create _workspace/ and _workspace/messages/ directories. Extract: app description/purpose, core features, tech stack preferences, scale (MVP/small/medium/large), existing code (if any), deployment platform. Write organized input to _workspace/00_input.md with sections: APP_DESCRIPTION, CORE_FEATURES, TECH_PREFERENCES, SCALE, EXISTING_CODE, DEPLOYMENT_TARGET.")

Phase 2: Architecture Design

Step 2.1 — Architect

task(agent_type="general-purpose",
     description="You are the architect agent. Read agents/architect.md for your full instructions. Read _workspace/00_input.md. Design the system architecture: component diagram, technology stack selection, database schema, and API specification. Write to _workspace/01_architecture.md, _workspace/02_api_spec.md, _workspace/03_db_schema.md. Write handoff message to _workspace/messages/architect-to-all.md.")

Phase 3: Sequential Development (file-bus port of original parallel step)

Step 3.1 — Frontend Developer

task(agent_type="general-purpose",
     description="You are the frontend-dev agent. Read agents/frontend-dev.md for your full instructions. Read _workspace/00_input.md, _workspace/01_architecture.md, _workspace/02_api_spec.md, and _workspace/messages/architect-to-all.md. Implement the complete frontend application. Write source code to src/ (frontend). Write handoff message to _workspace/messages/frontend-dev-to-qa.md.")

Step 3.2 — Backend Developer

task(agent_type="general-purpose",
     description="You are the backend-dev agent. Read agents/backend-dev.md for your full instructions. Read _workspace/00_input.md, _workspace/01_architecture.md, _workspace/02_api_spec.md, _workspace/03_db_schema.md, and _workspace/messages/architect-to-all.md. Implement the complete backend API and database layer. Write source code to src/ (backend/api). Write handoff message to _workspace/messages/backend-dev-to-qa.md.")

Step 3.3 — DevOps Engineer (deployment setup)

task(agent_type="general-purpose",
     description="You are the devops-engineer agent working on deployment setup. Read agents/devops-engineer.md for your full instructions. Read _workspace/00_input.md, _workspace/01_architecture.md, and _workspace/messages/architect-to-all.md. Create Dockerfile, docker-compose.yml, and .github/workflows/ CI/CD pipeline. Write _workspace/05_deploy_guide.md. (QA test commands will be updated after QA phase.)")

Phase 4: QA & Review

Step 4.1 — QA Engineer

task(agent_type="general-purpose",
     description="You are the qa-engineer agent. Read agents/qa-engineer.md for your full instructions. Read _workspace/00_input.md, _workspace/01_architecture.md, _workspace/02_api_spec.md, _workspace/messages/frontend-dev-to-qa.md, and _workspace/messages/backend-dev-to-qa.md. Write test strategy to _workspace/04_test_plan.md, write test code to src/. Review the frontend and backend code for bugs. Write message to _workspace/messages/qa-engineer-to-devops.md including all MUST_FIX items.")

Step 4.2 — DevOps Final Review

task(agent_type="general-purpose",
     description="You are the devops-engineer agent doing final review. Read agents/devops-engineer.md for your full instructions. Read _workspace/messages/qa-engineer-to-devops.md. Update CI/CD pipeline with test commands from QA. Address any MUST_FIX items that affect deployment. Write final review report to _workspace/06_review_report.md.")

Scale Modes

Request Pattern	Mode	Agents Used
"Build me a web app" / "full stack"	Full Pipeline	All 5
"Just build the API"	Backend Mode	architect + backend-dev + qa-engineer
"Build the frontend" (API exists)	Frontend Mode	architect + frontend-dev + qa-engineer
"Set up deployment"	DevOps Mode	devops-engineer
"Refactor this codebase"	Refactor Mode	architect + relevant-dev + qa-engineer

Error Handling

Error Type	Strategy
Unclear requirements	Orchestrator extracts what it can, marks assumptions in 00_input.md
Frontend/backend API mismatch	QA engineer catches this; flag in messages/qa-engineer-to-devops.md
Test failures	QA marks MUST_FIX items; DevOps addresses in final review

Test Scenarios

Normal case: Complete app requirements provided → full pipeline produces working code + tests + deployment
Existing code: User provides existing codebase → architect analyzes, only needed agents run
Partial request: "Add auth to my app" → architect + backend-dev (auth focus) + qa-engineer

이 저장소의 다른 Skills

같은 저장소

core-web-vitals

drvoss/harness-100-copilot

Use when measuring or optimizing Core Web Vitals — provides LCP/INP/CLS targets, measurement tool configurations, and optimization techniques for each vital metric. Also triggers on: re-run, update, revise, supplement.

2026-04-085

performance-optimizer

drvoss/harness-100-copilot

Use when optimizing application or system performance — dispatches profiling-analyst, frontend-optimizer, backend-optimizer, infra-tuner, and performance-reviewer to identify bottlenecks, implement optimizations, and validate improvements with ROI estimation. Covers full-stack performance from Core Web Vitals through API latency, database queries, caching, and infrastructure tuning. Does NOT cover application security review (use security harness), load testing execution, or capacity planning for new systems. Also triggers on: speed up my app, fix slow page load, reduce API latency, optimize Core Web Vitals, tune Kubernetes scaling, reduce infrastructure costs.

2026-04-085

test-automation

drvoss/harness-100-copilot

Use when you need to generate a complete test suite for a project — dispatches test-strategist, unit-test-writer, integration-test-writer, e2e-test-writer, and test-reviewer in sequence to produce strategy, implementation, and review artifacts. Covers test pyramid design, unit/integration/E2E implementation, coverage analysis, and flaky-test detection. Does NOT cover runtime performance testing, load/stress testing, or security penetration testing (use dedicated harnesses for those). Also triggers on: add tests to existing project, improve test coverage, write tests for this module, review our test suite.

2026-04-085

security-audit

drvoss/harness-100-copilot

Use when performing a comprehensive security audit of a codebase, application, or system — dispatches threat-modeler, code-security-analyst, dependency-auditor, and config-reviewer in a pipeline, then synthesizes findings into a prioritized security report with CVSS scoring and remediation roadmap. Covers threat modeling (STRIDE), static code analysis (SAST), software composition analysis (SCA), and configuration hardening review. Does NOT cover penetration testing, runtime DAST scanning, social engineering assessment, or physical security review. Also triggers on: run security review, check for vulnerabilities, audit for compliance, generate security report, assess security posture.

2026-04-085

code-reviewer

drvoss/harness-100-copilot

Use when you need thorough code review of a PR or file set — dispatches style-inspector, security-analyst, performance-analyst, and architecture-reviewer in sequence, then synthesizes findings into a prioritized action report. Covers correctness, security vulnerabilities, performance bottlenecks, and architecture alignment. Does NOT cover runtime testing, deployment validation, or auto-merging PRs. Also triggers on: re-run, update, revise, supplement.

2026-04-085

harness-generator

drvoss/harness-100-copilot

Use when you need to create a new multi-agent harness for a domain not yet covered in this repository, or when asked to 'build a harness', 'design an agent team', or 'create agents for [domain]'. Analyzes the domain, selects one of 6 architectural patterns (Pipeline, Fan-out/Fan-in, Expert Pool, Producer-Reviewer, Supervisor, Hierarchical), then generates all agent .md files, SKILL.md files, and HARNESS.md following Copilot CLI file-bus conventions. Does NOT port existing Claude Code harnesses — use PORTING-NOTES.md and guides/porting-from-claude-code.md for that. Also triggers on: re-run harness design, update agent team, revise harness architecture, supplement harness with additional agents.

2026-04-085

name	fullstack-webapp
description	Use when building a full-stack web application from scratch or adding major features — assembles architect, frontend-dev, backend-dev, qa-engineer, and devops-engineer to deliver complete code, tests, and deployment setup. Covers React/Next.js + Node.js/Python backends, PostgreSQL/MongoDB databases, and Vercel/AWS/Railway deployment. Does NOT cover mobile apps (React Native/Flutter), desktop apps, game development, or ML/AI model training. Also triggers on: re-run, update, revise, supplement.
metadata	{"category":"harness","harness":"16-fullstack-webapp","agent_type":"general-purpose"}

Fullstack Web App — Full-Stack Development Pipeline

An agent team collaborates to develop web apps through requirements → design → frontend → backend → testing → deployment.

Execution Mode

File-Bus Team — Agents communicate via _workspace/messages/, orchestrator sequences execution.

Agent Composition

Agent	File	Role	Type
architect	`agents/architect.md`	Requirements, architecture, DB, API design	general-purpose
frontend-dev	`agents/frontend-dev.md`	React/Next.js frontend implementation	general-purpose
backend-dev	`agents/backend-dev.md`	API, DB, auth, business logic	general-purpose
qa-engineer	`agents/qa-engineer.md`	Test strategy and automation	general-purpose
devops-engineer	`agents/devops-engineer.md`	CI/CD, deployment, monitoring	general-purpose

Pre-Flight Checks

_workspace/ is clean or confirmed stale
All 5 agent files present in agents/
User has provided app description with at least core features

Phase 1: Setup (Orchestrator)

task(agent_type="general-purpose",
     description="Read the user's web app request. Create _workspace/ and _workspace/messages/ directories. Extract: app description/purpose, core features, tech stack preferences, scale (MVP/small/medium/large), existing code (if any), deployment platform. Write organized input to _workspace/00_input.md with sections: APP_DESCRIPTION, CORE_FEATURES, TECH_PREFERENCES, SCALE, EXISTING_CODE, DEPLOYMENT_TARGET.")

Phase 2: Architecture Design

Step 2.1 — Architect

task(agent_type="general-purpose",
     description="You are the architect agent. Read agents/architect.md for your full instructions. Read _workspace/00_input.md. Design the system architecture: component diagram, technology stack selection, database schema, and API specification. Write to _workspace/01_architecture.md, _workspace/02_api_spec.md, _workspace/03_db_schema.md. Write handoff message to _workspace/messages/architect-to-all.md.")

Phase 3: Sequential Development (file-bus port of original parallel step)

Step 3.1 — Frontend Developer

task(agent_type="general-purpose",
     description="You are the frontend-dev agent. Read agents/frontend-dev.md for your full instructions. Read _workspace/00_input.md, _workspace/01_architecture.md, _workspace/02_api_spec.md, and _workspace/messages/architect-to-all.md. Implement the complete frontend application. Write source code to src/ (frontend). Write handoff message to _workspace/messages/frontend-dev-to-qa.md.")

Step 3.2 — Backend Developer

task(agent_type="general-purpose",
     description="You are the backend-dev agent. Read agents/backend-dev.md for your full instructions. Read _workspace/00_input.md, _workspace/01_architecture.md, _workspace/02_api_spec.md, _workspace/03_db_schema.md, and _workspace/messages/architect-to-all.md. Implement the complete backend API and database layer. Write source code to src/ (backend/api). Write handoff message to _workspace/messages/backend-dev-to-qa.md.")

Step 3.3 — DevOps Engineer (deployment setup)

task(agent_type="general-purpose",
     description="You are the devops-engineer agent working on deployment setup. Read agents/devops-engineer.md for your full instructions. Read _workspace/00_input.md, _workspace/01_architecture.md, and _workspace/messages/architect-to-all.md. Create Dockerfile, docker-compose.yml, and .github/workflows/ CI/CD pipeline. Write _workspace/05_deploy_guide.md. (QA test commands will be updated after QA phase.)")

Phase 4: QA & Review

Step 4.1 — QA Engineer

task(agent_type="general-purpose",
     description="You are the qa-engineer agent. Read agents/qa-engineer.md for your full instructions. Read _workspace/00_input.md, _workspace/01_architecture.md, _workspace/02_api_spec.md, _workspace/messages/frontend-dev-to-qa.md, and _workspace/messages/backend-dev-to-qa.md. Write test strategy to _workspace/04_test_plan.md, write test code to src/. Review the frontend and backend code for bugs. Write message to _workspace/messages/qa-engineer-to-devops.md including all MUST_FIX items.")

Step 4.2 — DevOps Final Review

task(agent_type="general-purpose",
     description="You are the devops-engineer agent doing final review. Read agents/devops-engineer.md for your full instructions. Read _workspace/messages/qa-engineer-to-devops.md. Update CI/CD pipeline with test commands from QA. Address any MUST_FIX items that affect deployment. Write final review report to _workspace/06_review_report.md.")

Scale Modes

Request Pattern	Mode	Agents Used
"Build me a web app" / "full stack"	Full Pipeline	All 5
"Just build the API"	Backend Mode	architect + backend-dev + qa-engineer
"Build the frontend" (API exists)	Frontend Mode	architect + frontend-dev + qa-engineer
"Set up deployment"	DevOps Mode	devops-engineer
"Refactor this codebase"	Refactor Mode	architect + relevant-dev + qa-engineer

Error Handling

Error Type	Strategy
Unclear requirements	Orchestrator extracts what it can, marks assumptions in 00_input.md
Frontend/backend API mismatch	QA engineer catches this; flag in messages/qa-engineer-to-devops.md
Test failures	QA marks MUST_FIX items; DevOps addresses in final review

Test Scenarios

Normal case: Complete app requirements provided → full pipeline produces working code + tests + deployment
Existing code: User provides existing codebase → architect analyzes, only needed agents run
Partial request: "Add auth to my app" → architect + backend-dev (auth focus) + qa-engineer