Art & Design

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

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.

Image generation skill for Claude Code, Codex CLI, OpenCode, Cursor and 50+ AI coding agents. Two backends (OpenAI API or codex CLI signed in to ChatGPT subscription), three modes (generate, edit, compose up to 16 references), six production recipes for gpt-image-2.

A codebase for building AI agents and custom skills using Claude Code and MCP server.

Self-hosted web UI for running Claude Code agents (with optional Codex support). Multi-session chat, voice, skills, social media, telephony.

A collection of Claude Code skills for evaluating LLM applications end-to-end: prompts, RAG pipelines, tool calls, and agents. Built for prompt engineers, AI builders, and teams who want a repeatable loop of "edit → eval → see scores → improve" instead of vibes-based iteration.

Vibecoding webapp starter pack — AGENTS.md substrate + 17 agent skills (init/build/ship/maintain) for Claude Code & Codex

bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15+ other agents.

Agentic QE Fleet is an open-source AI-powered QA/QE platform designed for use with Coding Agents (works best with Claude Code) featuring specialized agents and skills to support testing activities for a product at any stage of the SDLC. Free to use, fork, build, and contribute. Based on the Agentic QE Framework created by Dragan Spiridonov.

Webhook integration skills for AI coding agents (Claude Code, Cursor, Copilot). Step-by-step guidance for setting up webhook receivers, signature verification, and event handling for Stripe, Shopify, GitHub, and more. Built on the Agent Skills specification.

A comprehensive reference for building and organizing AI agent skills across Claude Code, KiloCode, OpenClaw, and OpenAI Codex. Covers SKILL.md specifications, folder structures, mode-scoped skills, agent orchestration, and self-hosted model configuration.

A governance runtime for AI agents, built on Linux kernel security primitives.

PersonalClone is a Hermes memory plugin that builds a local user persona from conversation history and injects it back into Hermes for personalized context.

CyBroLog: executable compact accountability language for multi-agent coordination

Build project-specific coding rules for AI assistants with base, language, and framework layers to keep generated code clean and consistent

A practical methodology for mapping business processes and designing safe, measurable AI-agent automation pilots.

codex docs

🤖 Build and optimize an AI trading agent using JavaScript for efficient and intelligent trading decisions on financial markets.

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

🖼️ Generate and edit images using text with the Opencode Antigravity Image plugin, supporting multiple variations and consistent character rendering.

My docker image for Hermes Agent sandbox runtime