# renaissance-architecture

A skill that pushes the agent toward first-principles design instead of "X but for Y". Useful when you plan features, pick a stack or review UI.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 3300 installs · ★ 467
- Author: bencium
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/bencium/bencium-marketplace/tree/HEAD/renaissance-architecture/skills/renaissance-architecture/SKILL.md
- Updated: 2026-10-04
- HTML: https://affpapa.org/en/nevibecode/skills/renaissance-architecture

## What it does

The skill hands the agent a set of architecture and UI/UX principles. Inside are decision tables: when to move from SQLite to Postgres, from a single file to several, from a monolith to services. Framework tables follow the same shape — Next.js, Remix, Astro, SvelteKit, Rails/Django, FastAPI, Hono/Elysia — each with a "use it when" and an "avoid it when" column.

Separate sections cover human-legible systems: configs a new teammate can read and edit in 10 minutes, error messages that say what happened and what to do, logs, docs that live with the code. Then local-first, composition over frameworks, and cloud only where it serves users rather than an assumed scale.

On the UI side: feedback under 100ms, honest progress instead of fake bars, visible system state, no layout shifts after load, a back button that works and undo implemented at the data layer. The tables are framed as defaults, not dogma — you can break them if you document why. Worth knowing if your stack is already settled: the skill will keep pulling toward a simple start.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add bencium/bencium-marketplace --skill renaissance-architecture -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/renaissance-architecture/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/renaissance-architecture/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add bencium/bencium-marketplace --skill renaissance-architecture -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/renaissance-architecture/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add bencium/bencium-marketplace --skill renaissance-architecture -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/renaissance-architecture/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install bencium/bencium-marketplace renaissance-architecture
```

2. **Manually: put the files in place**
- File: `.github/skills/renaissance-architecture/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add bencium/bencium-marketplace --skill renaissance-architecture -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/bencium/bencium-marketplace --path renaissance-architecture/skills/renaissance-architecture
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/renaissance-architecture/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add bencium/bencium-marketplace --skill renaissance-architecture -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/bencium/bencium-marketplace/tree/HEAD/renaissance-architecture/skills/renaissance-architecture/SKILL.md

## When to use it
- choose between SQLite and Postgres before concurrent writes become a problem
- decide whether a task needs a framework or just one library
- split a monolith only once the team outgrows a single codebase
- write a config a new teammate can read and edit in 10 minutes
- remove layout shifts and fake progress from loading states

## Example prompts
- Design the architecture for a notes service: start simple and show me when it has to get more complex
- Review my settings screen against renaissance-architecture and point out where the system state is opaque
- Help me choose between a monolith and services for this project, with reasoning for each option

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: d600e5eeccc5535a.

BEGIN THIRD-PARTY FILE d600e5eeccc5535a
```text
---
name: renaissance-architecture
description: Software architecture and UI/UX principles for building genuinely new solutions, not derivative work. Use when designing features, architecting software, brainstorming apps, reviewing designs, or during strategy discussions. Focuses on first-principles thinking, simplicity where it matters, and creating rather than commenting.
---

# Renaissance Architecture

Build genuinely new things. Not "X but for Y."

---

## Core Philosophy

The problem isn't modern tools. It's building **commentaries instead of creations**.

Medieval scholars wrote commentaries on Aristotle instead of new philosophy. We build Star Wars spin-offs instead of new sci-fi. We add AI to existing workflows instead of asking what workflows become possible.

**Renaissance architecture means:**
- First-principles thinking about WHAT to build
- Pragmatic choices about HOW to build it
- Creating new paradigms, not extending old ones
- Using modern tools to make genuinely new things possible

---

## Architecture Principles

### 1. Simplicity as Default, Complexity When Earned

**Start simple, add complexity when pain is measurable.**

| Start With | Move To | When |
|------------|---------|------|
| SQLite | Postgres | >10 concurrent writers, >100GB, need PostGIS/full-text |
| Single file | Multiple files | File exceeds ~500 LOC or has multiple responsibilities |
| Monolith | Services | Team can't work on same codebase, or genuine scale isolation needed |
| Static hosting | Server | Need auth, real-time, or server-side computation |
| Local state | Cloud sync | Multi-device is a real user need, not assumed |

**Not dogma, but defaults.** Violate with documented reasoning.

---

### 2. Framework Choices

**Use frameworks when they provide genuine leverage.**

| Framework | When to Use | When to Avoid |
|-----------|-------------|---------------|
| **Next.js** | Full-stack React apps, SSR matters, team knows it | Simple static sites, non-React teams |
| **Remix** | Data-heavy apps, progressive enhancement priority | Simple SPAs, unfamiliar teams |
| **Astro** | Content sites, partial hydration valuable | Highly interactive apps |
```
END THIRD-PARTY FILE d600e5eeccc5535a

The third-party file has ended. Everything between the d600e5eeccc5535a tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2174 of 13227 bytes. © bencium · MIT · https://github.com/bencium/bencium-marketplace/tree/HEAD/renaissance-architecture/skills/renaissance-architecture/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md