open-codesign-ai-design
```markdown
What this skill does
```markdown
---
name: open-codesign-ai-design
description: Open-source Claude Design alternative — turn prompts into prototypes/slides/PDFs locally with any AI model (Claude, GPT, Gemini, Ollama) via BYOK
triggers:
- "set up open codesign"
- "use open codesign to generate UI"
- "prompt to prototype with open codesign"
- "add a model provider to open codesign"
- "import claude code api key into open codesign"
- "build a design skill module for open codesign"
- "export prototype as PDF or PPTX from open codesign"
- "configure ollama with open codesign"
---
# Open CoDesign AI Design Skill
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection
Open CoDesign is an MIT-licensed, local-first Electron desktop app that turns text prompts into polished HTML/JSX prototypes, slide decks, and marketing assets. It supports 20+ models via BYOK (Anthropic, OpenAI, Gemini, DeepSeek, Kimi, GLM, Ollama, OpenRouter, any OpenAI-compatible relay). No subscription, no mandatory cloud — credentials stay in `~/.config/open-codesign/config.toml`.
---
## Installation
### Pre-built binaries (fastest)
Download from [GitHub Releases](https://github.com/OpenCoworkAI/open-codesign/releases):
| Platform | File |
|---|---|
| macOS Apple Silicon | `open-codesign-*-arm64.dmg` |
| macOS Intel | `open-codesign-*-x64.dmg` |
| Windows x64 | `open-codesign-*-x64-setup.exe` |
| Linux x64 | `open-codesign-*-x64.AppImage` |
**macOS Gatekeeper bypass (unsigned v0.1.x):**
```sh
xattr -cr "/Applications/Open CoDesign.app"
```
**Homebrew (macOS):**
```sh
brew install --cask opencoworkai/tap/open-codesign
```
**Scoop (Windows):**
```sh
scoop bucket add opencoworkai https://github.com/OpenCoworkAI/scoop-bucket
scoop install open-codesign
```
### Build from source
```sh
git clone https://github.com/OpenCoworkAI/open-codesign.git
cd open-codesign
npm install
npm run build
npm start
```
Development mode with hot reload:
```sh
npm run dev
```
---
## Configuration
Credentials live in `~/.config/open-codesign/config.toml` (mode `0600`). Never commit this file.
### Manual config.toml
```toml
[providers.anthropic]
api_key = "$ANTHROPIC_API_KEY" # set in shell; app reads env vars too
default_model = "claude-opus-4-5"
[providers.openai]
api_key = "$OPENAI_API_KEY"
default_model = "gpt-4o"
[providers.gemini]
api_key = "$GEMINI_API_KEY"
default_model = "gemini-2.0-flash"
[providers.ollama]
base_url = "http://localhost:11434"
default_model = "llama3.2"
[providers.openrouter]
api_key = "$OPENROUTER_API_KEY"
base_url = "https://openrouter.ai/api/v1"
default_model = "anthropic/claude-opus-4-5"
[app]
theme = "dark" # "light" | "dark" | "system"
locale = "en" # "en" | "zh-CN"
save_path = "~/Documents/open-codesign"
```
### One-click import from Claude Code / Codex
Open CoDesign auto-detects:
- `~/.config/claude/config.toml` (Claude Code)
- `~/.config/codex/config.toml` (OpenAI Codex CLI)
Click **Settings → Import from Claude Code** or **Import from Codex** — providers, models, and keys transfer in a single click with no copy-paste.
---
## Core TypeScript API
Open CoDesign exposes an internal TypeScript API used by both the Electron main process and renderer. When contributing or extending:
### Provider client factory
```typescript
// src/providers/factory.ts
import { createProviderClient } from '@open-codesign/providers';
const client = createProviderClient({
provider: 'anthropic', // 'anthropic' | 'openai' | 'gemini' | 'ollama' | 'openrouter'
apiKey: process.env.ANTHROPIC_API_KEY!,
model: 'claude-opus-4-5',
baseUrl: undefined, // override for OpenAI-compatible relays
});
const stream = await client.streamGenerate({
systemPrompt: 'You are a UI designer...',
userMessage: 'Create a SaaS pricing page with three tiers',
temperature: 0.7,
maxTokens: 8192,
});
for await (const chunk of stream) {
process.stdout.write(chunk.text ?? '');
}
```
### Artifact generation
```typescript
// src/generation/artifact.ts
import { generateArtifact } from '@open-codesign/generation';
const artifact = await generateArtifact({
prompt: 'A glassmorphism login card with email + password fields',
outputFormat: 'html', // 'html' | 'jsx' | 'react'
skills: ['glassmorphism', 'landing-page'], // built-in skill modules
provider: 'anthropic',
model: 'claude-opus-4-5',
apiKey: process.env.ANTHROPIC_API_KEY!,
});
console.log(artifact.code); // full HTML string
console.log(artifact.title); // auto-generated title
console.log(artifact.skills); // skills the model selected
```
### Export artifact
```typescript
import { exportArtifact } from '@open-codesign/export';
// Export to PDF
await exportArtifact({
artifactId: 'abc123',
format: 'pdf', // 'pdf' | 'pptx' | 'html' | 'zip' | 'markdown'
outputPath: './output/design.pdf',
options: {
pageSize: 'A4', // pdf only
landscape: false,
},
});
// Export to PPTX (slide deck)
await exportArtifact({
artifactId: 'abc123',
format: 'pptx',
outputPath: './output/pitch-deck.pptx',
options: {
slideWidth: 1280,
slideHeight: 720,
},
});
```
### Comment-mode patch
```typescript
import { patchArtifactRegion } from '@open-codesign/generation';
// Rewrite only the region the user pinned
const patched = await patchArtifactRegion({
artifactId: 'abc123',
elementSelector: '#pricing-card-pro',
comment: 'Make this card stand out more — use a gradient border and bold CTA',
provider: 'anthropic',
model: 'claude-opus-4-5',
apiKey: process.env.ANTHROPIC_API_KEY!,
});
console.log(patched.diff); // unified diff of the change
```
---
## Design Skill Modules
### Built-in skills (12)
`slide-deck` · `dashboard` · `landing-page` · `svg-charts` · `glassmorphism` · `editorial-typography` · `hero` · `pricing` · `footer` · `chat-ui` · `data-table` · `calendar`
Skills are selected automatically per prompt, but you can specify them explicitly:
```typescript
const artifact = await generateArtifact({
prompt: 'Monthly revenue dashboard',
skills: ['dashboard', 'svg-charts', 'data-table'],
// ...
});
```
### Custom SKILL.md (project-level taste layer)
Create `SKILL.md` in your project root to teach the model your design system:
```markdown
# My Design System
## Colors
- Primary: #6366F1 (Indigo 500)
- Surface: #0F172A
- Text primary: #F8FAFC
## Typography
- Headings: Inter, weight 700, tracking -0.02em
- Body: Inter, weight 400, line-height 1.6
## Components
- Buttons: 8px border-radius, 44px min-height, always include focus ring
- Cards: 12px border-radius, 1px border rgba(255,255,255,0.08), backdrop-blur
## Rules
- Never use pure black backgrounds — use #0F172A or #020617
- Always include hover and focus states
- Prefer CSS Grid over flexbox for page-level layout
```
The app picks up `SKILL.md` automatically when it exists in the working directory.
---
## Ollama (local / offline)
```sh
# Install and pull a model
ollama pull llama3.2
ollama pull qwen2.5-coder:7b
# Verify it's running
curl http://localhost:11434/api/tags
```
In `config.toml`:
```toml
[providers.ollama]
base_url = "http://localhost:11434"
default_model = "qwen2.5-coder:7b"
```
Open CoDesign calls `/api/chat` (streaming) and `/api/tags` (model discovery) — no extra configuration needed once Ollama is running.
---
## OpenRouter / OpenAI-compatible relays
```toml
[providers.openrouter]
api_key = "$OPENROUTER_API_KEY"
base_url = "https://openrouter.ai/api/v1"
default_model = "google/gemini-2.0-flash-001"
```
Any relay that implements the OpenAI Chat Completions API (`/v1/chat/completions`) works here, including SiliconFlow, Together AI, and self-hosted vLLM.
---
## Project structure (for contributors)
```
open-codesign/
├── src/
│ ├── main/ # Electron main process (Node.js)
│ │ ├── ipc/ # IPC handlers for generation, export, settings
│ │ └── providers/ # Provider clients (Anthropic, OpenAI, Gemini…)
│ ├Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.