Art & Design

Self-hosted image bed on Cloudflare Workers + R2 with built-in MCP server for AI agents

Gateway-only Railway image for Hermes Agent with Nous + OpenAI Codex OAuth bootstrap

Community MCP vision bridge for Xiaomi MiMo Vision, enabling image understanding for text-only LLM agents.

Nano Banana Edit — Claude Code skill bridging the Gemini Image API for in-flow image retouching. Shared workspace tool used by /visual-prompt (BIG) and other skills.

Agentic Workflow System — single binary with embedded Studio UI, MCP server, REST API, and React dashboard

The Ultimate PARA Vault & SDD Agent Stack 2026: Smart Orchestrator With 7 Design Skills & 5 Plugins

Headless Claude Code in a Docker container. Base image for ephemeral one-shots, persistent agents, and the missions toolkit. Published as ladder99/clawborrator-worker.

Convert DOCX and PDF to clean Markdown with AI image descriptions for AI agents and Claude Projects

Open-source desktop AI agent client with MCP, tools, multi-provider support, design workflows, and image workflows.

Self-service management portal for OpenClaw — dashboard, agents, channels, skills, plugins, chat, and ops in one UI. Vue 3 + Fastify.

Claude Code marketplace: `design` plugin (canvas-first HTML/JSX iteration, Cmd+Click element edits, chained UX/DS critique) + `flow` plugin (agentic workflow loop, `.ai/` second-brain workspace) + `mdcc` CLI.

Index of @shaharsha's published Claude Code skills - gdoc-sync, gslides-sync, presentation-generator, brand-system, brand-assets, image-generation, prompt-engineer, namecheap-domains. Each skill lives in its own repo.

Curated list of papers, frameworks, benchmarks, and applications for multimodal AI agents (LLMs, text-to-image, speech, world models, etc.) on mobile and edge devices.

A self-contained, zero-build visual simulation of five AI agents that discover tasks, build skills, trade knowledge with one another, deliberate to agree on a shared goal, and produce value together. There is no install step, no backend, and no network access. The whole thing is plain HTML/CSS/JavaScript with a deterministic, seeded engine.

OpenCode configuration pack for rldyour AI CLI workflows: local plugins, MCP/LSP, permissions, commands, agents, browser/design, and security.

DevOps / SRE / cloud / platform-engineering skills for Claude Code — cloud-agnostic and IaC-agnostic by design.

Local Figma MCP server with no REST rate limits, no metered tool-call quotas, and a verification loop. Drop-in alternative to Figma's Dev Mode MCP and Framelink for Claude Code, Cursor, Windsurf — works on every plan including Free.

Local-first PR review helper — drives claude or codex agents under a browser UI, ships findings to GitHub via gh.

Claude Code plugin marketplace for rldyour SDLC flows: MCP/LSP, Serena memory, security review, browser/design workflows, and reviewer agents.

Self-hosted, no-auth, multi-pane terminal canvas for AI CLI agents (Claude, Codex, Gemini, Cursor, Grok, Aider) over PTY+WebSocket.

WeChat Article Pipeline Skill 是一个面向 Codex 与 AI Agent 的微信公众号内容生产 Skill，支持文章优化、配图规划、HTML/Markdown 排版，并可自动创建公众号草稿，实现半自动化发布流程。 A WeChat article production skill for Codex and AI agents, supporting article refinement, image planning, HTML/Markdown formatting, and automatic WeChat draft creation for publishing workflows.

Custom skills, agents, and hooks for Claude Code. 38 skills (dev, Android, image, game dev), 10 specialized agents, 5 hooks. TDD, debugging, token optimization, game dev workflow with Godot 4. Written from scratch, zero dependencies.

天巧星 MSPM0G3519 开发板的 AI 编程助手 skill。支持 Claude Code、Codex、OpenCode 等 CLI Agent。一句话创建完整 CCS 工程 — 自动适配引脚、时钟树、外设配置，并通过 SysConfig CLI + gmake 一键编译验证。内置 OLED ▎ UI 框架、IMU、WS2812、无线串口等板载外设驱动。

Generative AI projects in Java with Spring Boot and Quarkus: agents, RAG, memory, MCP (server/client), tools and LangChain orchestration with GPT, Claude and Ollama, plus image generation/analysis and voice pipelines (speech-to-text and text-to-speech)