richfrem

Garden Structure Designer — AI skill for Claude Code

AI community

Self-improving AI-agent plugin for garden-structure design, combining guided intake, deterministic geometry, CAD-style drawings, validation gates, shop blueprints, and builder-ready documentation.

How to install Garden Structure Designer

This entry records only its repository, not the path inside it, so there is no exact command to give. Open richfrem/garden-structure-designer and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Garden Structure Designer does

Self-improving AI-agent plugin for garden-structure design, combining guided intake, deterministic geometry, CAD-style drawings, validation gates, shop blueprints, and builder-ready documentation. Intention you would use this designer with something like github copilot + vs code, claude code or antigravity or similar.

Alternatives in AI

  • Startup Canvas — Generate Startup Canvas combining Product Strategy and Business Model 7.8k ★
  • Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
  • Gtm Engineer Skills — Claude Code skill for improving website AEO (AI Engine Optimization) and GEO (Generative Engine Optimization) 761 ★

README

Garden Structure Designer

**AI-native multi-agent design pipeline that converts colloquial descriptions of garden structures into professional-grade structural construction PDF packages.**

[![Platform: Agentic OS](https://img.shields.io/badge/Platform-Agentic%20OS-blue.svg)](https://github.com/richfrem/agent-plugins-skills) [![Python 3.11+](https://img.shields.io/badge/Python-3.11%2B-brightgreen.svg)](https://www.python.org/)


🏗️ What It Does

`garden-structure-designer` acts as your personal master timber framer. It conducts an interactive interview to understand your vision (*"a 14ft hexagonal cedar gazebo with steep roof and decorative knee braces in Victoria, BC"*), resolves regional building codes, solves exact 3D geometry and compound miters through deterministic Python engines, generates 8 dimensioned architectural SVG sheets, runs adversarial physics and drawing QA, and compiles a comprehensive PDF package complete with cut-lists and step-by-step assembly guides.

flowchart TD
    User([👤 User Request]) -->|Plain-English Description| ID[🎯 interactive-designer Agent]
    ID -->|Progressive Interview & Spec Normalization| Struct[context/staging/structure.json]
    Struct -->|Canonical Staging Bus| DO[⚙️ design-orchestrator Agent]
    DO --> Stages[Stages 0–8: Deterministic Math, CAD Translator, Drawings & QA]
    Stages --> PDF([📄 outputs/pergola_plan.pdf Construction Package])

🚪 Quick Start

For End Users & Clients

Start your design journey by talking to the **`interactive-designer`** agent:

*"I want to design a 14ft hexagonal cedar gazebo with steep roof, decorative knee braces, and sonotube footings in Victoria, BC."*

The agent guides the conversation with progressive disclosure, normalizes specifications, and hands off execution to the backend orchestrator.

For Developers & Automated Workflows

If you already have a structured design specification in `context/staging/structure.json`:

# Regenerat