Art & Design

Agent-agnostic skill for breaking retry loops and capturing verified workflow lessons.

Static performance audit skill for Claude Code & Cursor — finds N+1 queries, missing indexes, and O(n²) code in NestJS/Next.js/Prisma/Postgres apps

>

Codex skill for generating DataDance-style web pages with DataDance shell and Yuanli components

Ian Xiaohei illustration Codex skill

Recently updated agent-skill-related GitHub repository: pluginagentmarketplace/custom-plugin-linux.

Codex skill for creating Xiaohongshu experience-sharing image note packs

a codex skill for accumulating the frontend design and apply it on your own project

🚀 Feishu/Lark Docs、Sheet、Bitable <-> Markdown | AI Agent-friendly knowledge base exporter and writer with OAuth 2.0, CLI, TUI & Claude Skills support - 飞书文档 <写入/导出> Markdown | AI Agent 友好型导出-写入工具

Drop a hotel booking screenshot, get a ready-to-send upgrade ask. A Claude Skill for elite travelers. 丢一张订单截屏,拿到一封可直接发送的升房请求。

Codex skill package for industrial ecommerce product image set planning, generation QA, and review workflows.

Agent skill that generates edge-case test suites for Sui Move functions. Produces boundary, arithmetic, access-control, and state-machine tests from function signatures and module context.

Recently updated agent-skill-related GitHub repository: ForceInjection/domain-driven-design-skills.

Codex skill and portable CLI for server-side Obsidian agent vaults

Battle-tested skills for Claude Code and other coding agents — distilled from a real production automation setup

AI coding agent skill for turning hidden unknowns into actionable knowns before implementation.

A collection of Agent Skills for serving machine-learning models, from API backend to frontend.

Codex skill for using and troubleshooting AI Blackhole Studio online panorama director.

Self-hosted Vedic astrology engine with Swiss Ephemeris calculations, SVG chart rendering, offline interpretation, and Codex/Claude skill integration.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving every branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or explicitly says \"grill me.\"

Red-Green-Refactor TDD. NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST. Blocks AI test-cheating (writing tests AFTER implementation). Use when implementing any feature or bugfix.

name: caido-mode

Industry Research Framework: an agent-agnostic framework for source-backed industry research and publishable writing

Glyph is a workbench for composing the forms intelligence takes today — and discovering the language it will speak tomorrow.