KS
Killer-Skills

architecture-designer — how to use architecture-designer how to use architecture-designer, what is architecture-designer, architecture-designer alternative, architecture-designer setup guide, transform project requirements into architecture, ADR documentation best practices, technical architecture design with AI

v1.0.0
GitHub

About this Skill

Ideal for Technical Agents needing to transform project requirements into concrete architectural decisions with ADR documentation. architecture-designer is a skill that helps define technical architecture by transforming project requirements into concrete decisions with ADR documentation

Features

Triggers architecture design with commands like 'Help me define the architecture' or '/architecture'
Requires 'docs/project.md' to exist with project definition
Creates an architecture overview in 'docs'
Suggests project interview if 'docs/project.md' does not exist
Supports ADR documentation for technical architecture decisions

# Core Topics

edumesones edumesones
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
36
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add edumesones/azure--demo/architecture-designer

Agent Capability Analysis

The architecture-designer MCP Server by edumesones is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use architecture-designer, what is architecture-designer, architecture-designer alternative.

Ideal Agent Persona

Ideal for Technical Agents needing to transform project requirements into concrete architectural decisions with ADR documentation.

Core Value

Empowers agents to create architecture overviews in documentation files, utilizing ADR documentation and generating concrete architectural decisions from project requirements, leveraging triggers like 'Help me define the architecture' and integrating with existing project definitions in 'docs/project.md' files.

Capabilities Granted for architecture-designer MCP Server

Defining technical architecture for new projects
Generating architecture overviews in documentation
Creating ADR documentation for project requirements

! Prerequisites & Limits

  • Requires existing project definition in 'docs/project.md'
  • Specific to project architecture design
Project
SKILL.md
3.1 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Architecture Designer (Fase 0)

Transform project requirements into concrete architectural decisions with proper ADR documentation.

Triggers

  • "Help me define the architecture"
  • "Define architecture"
  • "Let's design the architecture"
  • "Help me with technical architecture"
  • /architecture

Prerequisites

  • docs/project.md should exist with project definition
  • If not exists, suggest: "Let's first interview about the project"

Purpose

Create:

  1. Architecture overview in docs/architecture/_index.md
  2. ADRs (Architecture Decision Records) in docs/decisions/
  3. Technical foundation for feature development

Process

1. Read Project Context

bash
1# Read project definition 2cat docs/project.md 3 4# Check existing architecture docs 5ls -la docs/architecture/ 2>/dev/null 6ls -la docs/decisions/ 2>/dev/null

2. Identify Key Decisions

Based on project.md, identify decisions needed:

CategoryTypical Decisions
Language/RuntimePython, Node, Go, Rust
FrameworkFastAPI, Django, Express, Next.js
DatabasePostgreSQL, MongoDB, SQLite, Redis
AuthenticationJWT, OAuth, Session, API Keys
HostingAWS, GCP, Azure, Vercel, Self-hosted
API StyleREST, GraphQL, gRPC
FrontendReact, Vue, Gradio, CLI
CachingRedis, Memcached, In-memory
Queue/AsyncCelery, RQ, SQS, None
MonitoringCloudWatch, Datadog, Prometheus

3. Interview for Each Decision

For each major decision, ask:

"For [CATEGORY], I see a few options:

A) [Option A] - [Pros: X, Y] [Cons: Z]
B) [Option B] - [Pros: X, Y] [Cons: Z]
C) [Option C] - [Pros: X, Y] [Cons: Z]

Based on your project (MVP timeline, team size, scale needs),
I'd recommend [X] because [reason].

What's your preference?"

4. Create ADRs

For each decision, create docs/decisions/ADR-NNN-title.md

5. Create Architecture Overview

Update docs/architecture/_index.md with:

  • System diagram
  • Tech stack table linking to ADRs
  • Project structure
  • Key patterns

6. Interview Rules

ARCHITECTURE INTERVIEW RULES

1. Always provide options with trade-offs
   Never ask "what database?" - ask "PostgreSQL or MongoDB? Here's why..."

2. Make recommendations based on project context
   "Given your MVP timeline, I recommend X"

3. Create ADR immediately after each decision
   Don't wait until the end

4. Challenge over-engineering
   "Do you really need Kubernetes for MVP? ECS is simpler."

5. Document the WHY, not just the WHAT
   Future you will thank present you

7. Completion Check

Before ending, verify:

  • All major categories have decisions
  • Each decision has an ADR
  • Architecture overview exists
  • Project structure is defined
  • No conflicting decisions

8. Handoff

When complete:

Architecture defined. Created:
- docs/architecture/_index.md (overview)
- docs/decisions/ADR-001-*.md through ADR-00N-*.md

Next step:
"Define MVP features" -> Creates feature folders ready for implementation

Or: "Let's start with the first feature"

Related Skills

Looking for an alternative to architecture-designer or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication