Art & Design

VeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a stateful, zero-dependency LLM orchestration skill. Features sub-agent nesting for code gen and behavioral-driven verification.

The official Thin Runner Sandbox: a practical learning environment for building transparent AI workflows without heavyweight black-box agents. Includes learning modules, skills, pipelines, memory systems, observability examples, Ollama/OpenAI integrations, and production-ready orchestration patterns.

A collection of skills I made for AI agents and models to speed up my workflow as well as yours

Game-ad image generation skill for Claude Code / WorkBuddy / any agent framework. 6-step vision workflow + batch UX + OpenAI-compatible API.

Open-source Claude Code agent multiplexer — run dozens of parallel AI coding agents unattended via tmux

🤖 Build AI agents in Python with minicode-sdk—an extensible framework featuring LLM support, tools, skills, and efficient async operations.

FLOW methodology packaged as portable Agent Skills (SKILL.md format) for cross-platform use. Production-tested cognitive-partnership protocols.

982 legal AI skills in standard Anthropic SKILL.md format — drafting, review, knowledge packs, litigation simulation, legal education, safety, connectors. MENA-first jurisdictional lens. Extracted and enriched from the Louis (HAQQ Legal AI) skill registry.

Unofficial Alibaba Cloud MCP toolkit: servers, skills, and plugins for building AI agents.

Behavioral guidelines and engineering skills for AI coding agents

A personal skill library for Claude Code and Cursor, structured workflows for AI engineering, full-stack builds, and team sprints.

Editable HTML presentation skill for Codex/Claude Code with drag-resize editing, slide reordering, local save/export, and PPTX-to-web conversion. Shout out to @zarazhangrui

Generate validated diagrams across Mermaid, PlantUML, Graphviz, D2, and Excalidraw. MCP server, CLI, and Claude Code skills bundle.

LambChat — A multi-tenant AI Agent Harness Platform. Skills + MCP dual-engine powered, built for scale and isolation. SSE real-time streaming, multi-modal document intelligence, JWT/RBAC enterprise security, and GitHub-connected Skill marketplace.

Dart framework for stateful AI agents — tool use, skills, sub-agent delegation, planning, streaming, and multi-provider LLM support (OpenAI, Gemini, Bedrock).

Claude Code és Codex skillgyűjtemény

🛡️ AEGIS v6.0 — AI Agent Team Framework for Claude Code | 8 Personas • 21 Skills • 15 Commands • Persistent Brain • tmux Agent Teams

Visual workflow builder for Cake skills - create SKILL.md files without writing markdown

OpenAI Codex Starter Kit with custom Codex agents, skills, AGENTS.md, hooks, MCP docs servers, Superpowers/GitHub plugin config, and one-command baseline install.

Meeting Superlab: product-design exploration skills for meeting products (Cursor, Codex, Claude Code)

Agentic development workflow for etcd-druid | Claude Code plugin

An opinionated repo template that makes a single app, service, library, or medium platform agent-ready — for Claude Code, Cursor, Codex. Tight AGENTS.md, doc layers split by lifecycle (charter, ADR, RFC, specs, product, guides), Diátaxis user docs, plan/verify/review work-loop skill, optional Ralph harness for AFK runs.

Import Claude Code skills from `.skill`, `.zip`, `SKILL.md`, or a folder — no installation required.

This SKILL.md defines a Claude skill called code-implementation-business-specifications. Its core purpose is to force AI to follow a strict, structured workflow when implementing code from business requirements, ensuring the final deliverable is confirmed, self-tested, and actually runnable — not half-finished or untested.