Art & Design

Up to 99% token savings on AI agent context. Free. Provider-agnostic (Claude, Cursor, Codex, Cline, any MCP agent). 91.62% over 626.8M auditable tokens. Try: nuxs.ai/playground

AI product manager skills for Codex/Claude: brainstorming, product research, PRD workflows, requirements review, and planning handoff.

中英双语 AI 工作流系统，7个协作技能覆盖引导/规划/执行/审计/收尾全生命周期。Bilingual AI workflow system — 7 collaborative skills for project guidance, planning, execution, auditing, and closeout. Claude Code & Codex.

Free, local, open-source 24/7 Cowork app for OpenClaw, Hermes Agent, Claude Code, Codex, OpenCode, Gemini CLI and 20+ more CLI | Customize your assistants | Star if you like it!

Starter kit for agentic WordPress development. CLAUDE.md/AGENTS.md templates, the wordpress-development skill, curated MCP servers, sub-agents, hooks. Companion to WordCamp Portugal 2026.

Twelve Greek gods. One command. A working SaaS. 98 skills + 49 agents + 13 hooks for Claude Code + Codex CLI + Gemini CLI. Cross-CLI persistent memory, zero-interaction full pipeline (design → build → inspect → test → ship).

A multi-agent method for AI-first refinement and build. Ten agents, eleven skills, a constitution your project owns. Runs on Claude Code / Cursor / Codex.

Write your MCP server + lifecycle hooks once, deploy to 29 AI-agent platforms — Claude Code, Codex, Cursor, Gemini, Copilot, OpenCode, Warp, Zed & more — from one defineConnector() API. Renders native config for every host (MCP · hooks · commands · skills) with built-in per-tool token telemetry.

Make your AI agent argue visually. Universal skill pack for Excalidraw diagrams across Claude Code, Cursor, Codex, Gemini CLI, and any MCP-compatible agent.

CI for AI agent skills — lint, safety-audit, and scenario-test SKILL.md skills before you trust them. No Docker required.

Curated list of AI agent skills and global AGENTS.md that I built and use on daily basis.

Foundry. The agent skill that makes any AI coding assistant an expert at building agentic tooling.

Agent skills with opinions: design, motion, artifacts, decisions, and the craft of making skills themselves.

Personal agent skills for Paper-first UI prototyping and design engineering.

PowerShell scaffolder for Claude Code projects. Spin up Terraform/AWS, React + shadcn/ui, or Fastify API projects pre-loaded with their respective claude skills and CLAUDE.md conventions. Bash port welcome.

Claude skill that analyzes images, websites, and Figma files and generates a structured design.md with token system, component inventory, and reconstruction notes.

Open-source Claude skills for GEO, AI discoverability, and developer GTM workflows. Built for developer-focused companies that want their documentation to be found, parsed, and cited by AI systems.

Claude skill: game-feel intelligence - screenshake, hit-stop, easing, particles, squash & stretch with playtested numbers. Same mechanics, 10x the feel.

Claude skill: technical SEO intelligence - meta, Open Graph, JSON-LD structured data, semantic HTML, Core Web Vitals. Every AI-built page ships search-ready.

Claude skill: API design intelligence - REST conventions, RFC 9457 errors, cursor pagination, idempotency keys, signed webhooks. Design APIs like Stripe, not a CRUD generator.

Claude skill: HTML email design intelligence - renders perfectly in Outlook, Gmail, Apple Mail. Bulletproof buttons, dark mode, client quirks for 25+ clients.

Compile raw source material into a persistent, cross-linked Markdown wiki using this OpenClaw agent skill for iterative knowledge base building.

A SentinelOne AI SOC analyst built as Claude Skills, 3 MCP servers (PowerQuery, SDL, Mgmt Console, UAM, Hyperautomation), and a Principal SOC Analyst persona. Threat hunting, alert triage, detections, dashboards, and SOAR from natural language.

Prepare image datasets for LoRA training (Ostris AI Toolkit / Z-Image Turbo): quality checks, captioning (templates / Claude Vision / Florence-2), 20+ validation rules. Agent Skill for Claude Code & Cursor + standalone CLI.