Art & Design

Installable cli-creator agent skill for designing and auditing Python CLI tools.

Get into Builder Mode — an AI-native startup factory and OS you point Claude Code (or Cursor/Codex/Windsurf) at.

Design generation and iteration in canvas-based environments

Comprehensive frontend design patterns and visual polish guidance

Reusable Codex skills for practical Domain-Driven Design work.

own your agent skills — vet, sign & pin every skill & MCP server before it runs. The supply-chain gate for AI agents (pairs with warden's runtime firewall). Part of Own Your Stack.

This is a Claude skill designed to assist all members of the Dycos team.

Codex skills for Web/UI design, planning, implementation, acceptance review, and website prompts

Your AI digital clone — learns who you are, acts on your behalf, remembers everything. Persistent vector memory, multi-agent teams, 60+ skills, smart model routing. Self-hosted, encrypted, multi-provider (Claude/Ollama/OpenRouter). Deploy to Slack, Discord, Telegram, WhatsApp & more in minutes.

입력 자료를 17개 모드로 라우팅해 전문가급 한국어 HTML을 만드는 단일 통합 스킬 adaptive-html-final 쇼케이스 — 8-테마·비주얼 프로파일(위젯·도식·자동)·무 JS·자기방어 게이트 159 | Showcase of adaptive-html-final: a single skill routing inputs into 17 modes to generate expert-grade Korean HTML — 8 themes, visual profiles (widget·diagram·auto), zero-JS, 159 self-defending gates

Reusable skills for AI coding agents (Claude Code, Codex, Forge) covering paper review, commit triage, GPU rentals, reference search, research logs, image-prompt composition, and more.

Agent skills for building Boogy services — design, data modeling, auth, jobs, MCP/REST, and platform limits

Research-grounded Agent Skills for coding agents: DX review, test strategy, and agent-readiness heuristics. Install via npx skills add Thulr/informed-skills.

Two summonable advisory panels for Claude: an 18-persona Advisory Board (strategy, philosophy, persuasion, science) and a Code Team (the people building Claude Code + Matt Pocock). One plugin for Claude Code, two skill zips for chat and Cowork.

Rust low-latency Solana arbitrage execution skill for the Solana AI Kit: Yellowstone gRPC ingestion, simulate-first Jito bundles, tx landing, risk/kill-switch. MIT.

Practical Solana/Anchor security audit workflow skill for the Solana AI Kit (static + manual + dynamic + report); fills the official seed. MIT.

Deterministic, risk-governed multi-agent trading engine for US equities. A strategy swarm proposes orders; an independent risk guardian has final say. Paper mode by default, gated live Robinhood MCP execution.

A context-preserving Git/GitHub safety skill for AI coding agents.

Multi-skill umbrella for Claude Code: analytic-workbench, spec-driven-dev, splunk-platform, wise-scraper, design2spec, and more

自己整理的Codex Skill

A Codex skill for STM32 embedded C architecture guidance: CubeMX + HAL layering, BSP/Driver/Module/App boundaries, RTOS/OSAL design, Bootloader/IAP, Git workflow, and C style.

Clean up, organize and index any markdown knowledge base (Obsidian/PARA) with Karpathy's 3-layer LLM-wiki method. Works as an AI agent skill or standalone Python.

Audit AI context files (AGENTS.md, memory.md) for freshness and token cost. Zero deps, works as CLI, GitHub Action and Claude Code skill

Open-source brand skills that turn an idea into a real brand — name, identity, voice & brand book — without leaving your AI agent. Works in Claude Code, Cursor & 70+ agents.