AGENT SKILL

nexu-io--open-design

Alternative mã nguồn mở cho Claude Design — filesystem of design skills, 150 brand-grade DESIGN.md systems, 261 plugins. Chạy trên 21+ agent CLI qua MCP server.

License 许可
Apache-2.0
最近更新
2026-11-14
Stars
★ 13
Forks
2

01 前言 Front Matter

name
nexu-io--open-design
description
Alternative mã nguồn mở cho Claude Design — filesystem of design skills, 150 brand-grade DESIGN.md systems, 261 plugins. Chạy trên 21+ agent CLI qua MCP server.
allowed-tools
Bash, Read, Write
user-invocable
true

03 SKILL.md 正文

Open Design là platform thiết kế agent-native: agent đọc DESIGN.md files như một design system và tạo ra prototype HTML, pitch deck, motion graphic, dashboard — tất cả từ 1 brief.

Install

# Desktop app (recommended) — auto-detect agent CLIs
# macOS / Windows: download từ https://open-design.ai

# CLI
curl -fsSL https://open-design.ai/install.sh -o /tmp/open-design-install.sh
# Inspect first: head -40 /tmp/open-design-install.sh — then run if safe:
sh /tmp/open-design-install.sh claude-code
# Hoặc: cursor, copilot, hermes, opencode, kimi...

Slash Commands

od skill list              # xem 100+ skills
od skill search dashboard  # tìm skill theo keyword
od skill apply landing-page --design minimal-saas

od plugin list             # 261 plugins
od plugin install figma-to-react

od design-system list      # 150 brand systems

Artifact Types (từ 1 brief)

/design landing-page brief="SaaS product for developers"
→ HTML prototype (web/mobile/desktop)
→ Live dashboard với editable params
→ Pitch deck (PPTX/PDF export)
→ Motion graphic (HTML→MP4 via HyperFrames)
→ Generated images/video

DESIGN.md Format

# Brand: YamTam Engine

## Colors
primary: #6366f1
background: #0f0f0f
text: #e2e8f0

## Typography
heading: "ui-sans-serif", weight 700
body: "ui-sans-serif", size 16px, line-height 1.5

## Components
button: rounded-lg, px-4 py-2, bg-primary
card: bg-zinc-900, border border-zinc-800, rounded-xl p-6

REST API (local daemon)

GET  /api/skills            — skill registry
GET  /api/plugins           — marketplace
GET  /api/design-systems    — brand catalog
POST /api/chat (SSE)        — streaming artifact generation
GET  /api/artifacts/lint    — validate artifact

Stack

  • Frontend: Next.js 16 + React 18
  • Backend: Node 24, Express, SSE, SQLite
  • Desktop: Electron
  • Storage: .od/ directory
  • MCP server: tools for any MCP-compatible agent

Khi Nào Dùng

  • Tạo prototype nhanh từ brief
  • Generate pitch deck từ mô tả sản phẩm
  • Cần design system portable (DESIGN.md) cho team
  • Thay thế Figma cho AI-first workflow

Source

https://github.com/nexu-io/open-design · Apache-2.0

04 同仓库更多 Skills

Horonomos-laps
Horonomos-laps/Yana-AI

openai--sentry--sentry

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

ito-basket-compare

Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

implementing-network-traffic-baselining

Build network traffic baselines from NetFlow/IPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly/daily traffic pattern profiling

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

detecting-evasion-techniques-in-endpoint-logs

Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

implementing-microsegmentation-with-guardicore

Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.

★ 13
Horonomos-laps
Horonomos-laps/Yana-AI

ramdisk-tmpfs-patterns

暂无简介

★ 13