Art & Design

Lightweight CLI to build self-managing AI agent teams. Define roles, skills & projects in Markdown+YAML — agents run autonomously on a heartbeat schedule, talk to each other via inbox, and delegate tasks. Works with Claude Code, Codex, Gemini, Cursor & more.

Spec-first AI development: describe a feature → AI creates spec + plan + tasks, builds autonomously, syncs to GitHub/JIRA. Domain-expert skills for PM, Architect, Frontend, QA learn your patterns permanently. Claude Code, Codex, Cursor, Copilot & more.

Build, evaluate, and integrate long-term memory for self-evolving agents.

Agent skill for turning product ideas into structured design plans, staged visual drafts, and formal design documents.

Multi-provider AI image generation cookbook: prompt gallery, agentic skill, and CLI for OpenAI gpt-image-2, Google Imagen, Flux, and more. Claude Code plugin + Codex/OpenClaw skill + Python CLI.

Teaches AI coding agents OS platform awareness (Windows vs Linux shell/path) and social restraint around git operations. Saves tokens by preventing wrong-command retries and premature commit prompts.

Rasputin Omnitool: OpenClaw skill bundle with planner/executor/reviewer agent loop and 12 tools (research, browser, sandbox, multimedia). Manus-equivalent agent built from OSS.

Agent skill for system analysis and UML modeling with templates, checklists, traceability, and Mermaid notation guidance

Skill bundle for Claude, Codex, Hermes, OpenClaw, Cursor, Windsurf, and generic agents covering PiAPI (Midjourney, Suno, Kling, Flux, Hailuo, Luma, Hunyuan, Faceswap, Trellis 3D, MMAudio, F5-TTS, Veo 3, Gemini 2.5 Flash Image, Seedance, and the OpenAI-compatible LLM gateway).

Uses knowledge extracted from 10 design books to guide agents in creating intentional UI/UX.

Virtual whiteboard for sketching hand-drawn like diagrams; used as an agent skill for architecture design.

Collection of skills for mobile app icons and multi-platform asset generation using Nano Banana models.

Open-source CLI for generating app icons and assets using the latest vision models.

Codex App Fast/Priority proxy for third-party OpenAI-compatible APIs

Coze Image Generation Tool - 通过 Coze API 生成图片的 OpenClaw Skill

Curated AI agent communities, hubs, reefs, and OpenClaw skills. Poltergeist-built. Agents only. 🦞

OpenClaw skill for web-grounded factual answers with citations and sourced images

Codex skill for building interactive narrative relationship graphs

Codex skill for searching and adapting curated GPT-Image-2 prompt patterns

Codex skill for faithful document-driven interactive HTML slide decks

Image-to-website Codex skill pipeline: design prototypes, generated assets, and working frontend builds from one reference image.

SGoal is a set of Codex skills for turning early project intent into practical planning artifacts.

Codex skill for image generation via configurable compatible image APIs

Personal curated resources for AI agent dev (Claude Code, Codex, Skills, MCP). Doubles as idempotent bootstrap + reference library.