Havuz

⚡ TidyFactor Architecture Ecosystem , AI-Native Web Architecture, Design Systems & Agent Skills .

🎬 TipAI Cinema Skills — AI视频创作Skill模块。剧本→分镜→提示词→表情控制，可加载的AI创作工作流。

能力库 (Capability) — one-stop visual management of DSH Skills & MCP: on-demand MCP loading, in-session hot reload, and SKILL/MCP descriptions

把微信公众号文章批量抓取并导入 IMA 知识库的自动化技能 (WeChat official-account article crawler → IMA knowledge base, MIT)

SKILL: Claude FABLE 5 spanking Claude OPUS 4.8. Orchestrator-worker cost model for Claude Code: the expensive model reads and judges, Opus 4

加密环境文件操作 MCP 工具。当 Node.js 是加密软件白名单进程时，通过 fs 模块自动解密读写文件明文，替代 AI Agent 内置文件工具，适用于任何支持 MCP 协议的 Agent。

Access your Maccabi health records using a CLI, MCP, or SDK

Hi-LLM，嗨大模型导航，围绕 AI 工具、网站与开发者资源建立可持续维护的内容目录。访客可以按分类浏览、关键词搜索、查看热门排行和收藏感兴趣的内容；管理员则可维护分类、站点信息、展示状态与推荐内容。

A benchmarking suite for Agent Skills (SKILL.md files) that measures whether a skill actually improves LLM output quality, and by how much.

The recursive self-improvement loop for your skills (including itself) — runs a retro after every session and turns corrections into permane

Ready to use design system for cool UI/UX with no extra slop

CLI, MCP server, and Skill for safe local Codex session audit, cleanup, restore, and verification.

CDP-powered perf CLI: goes beyond Lighthouse scores, builds causal degradation graphs. Tells you why it's slow, not just that it is.

AI Agent skill for TI MSPM0 (G3507/G3519/L1306): SysConfig validation, board-aware pin safety for LCKFB Tianmengxing/Dimengxing/Dizhengxing,

Claude Code skill that scans an iOS project and auto-generates a copyable App Store Connect submission report.

Help your AI-generated interfaces escape the generic — agent skills for product-specific UI

A Codex skill that turns 'do everything' into safe scope, defaults, memory, and AI observability.

Telegram bot development skill for Claude Code and OpenCode: checks the live Bot API docs and the installed library (aiogram, grammY, python

个人A股/港股盯盘智能副驾 - 信息驱动、人在回路、非量化、非自动下单。基于WorkBuddy平台的Skill。全网同名：WaterCMY 感谢相遇，感谢关注！学习学习再学习 实践-反思-总结-持续进化 CN No.1

麦麦省钱助手 —— 基于麦当劳 MCP 的点餐成本优化 Skill。算出当前门店最省钱的点餐方案，并主动提示凑单陷阱。

M-CODE WRAPPED · 麦当劳数据全景报告 + 个人年报 + 方言播报

One desktop for all your AI coding Agent — Claude Code, Codex CLI & Gemini CLI. Auto-detect, one-click install, unified chat, file explorer,

An Enterprise-Grade Full-Stack RBAC Permission Management System Built with Go + React

把老板蒸馏成 AI Skill — PUA检测(10大厂流派) · 反击教练(三档话术) · 画饼鉴定 · 证据收集 · 劳动法速查 · 翻车模拟(互动文字游戏) · 汇报优化 · 老板心理预测。整活的外壳，认真保护打工人的内核。

麦当劳 MCP 技能：待评价清单、好评兑礼进度、发票报销门槛凑单、单次抽奖确认。99 项测试，非官方产品。

基于麦当劳 MCP 的权益精算 Skill——按档口与账户权益实时核价，算清这顿值不值、这张卡值不值，一次确认完成点单

Double-check before you ship: grill the requirements, test the implementation, prove the delivery. An engineering-discipline bundle for Deep

A Claude Code skill that consolidates scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at th

macOS & Windows Codex Desktop 梦幻换肤 Skill｜由世事宜AI免费提供

先议后行——AI 协作变更任务的议行分离机制 skill（DeepSeek Harness）

"Does this actually work with my agent?" An open, versioned registry of AI-agent artifacts: skills, plugins, MCP servers, models, etc. with

Distill your bros. The ones who make you laugh until you can't breathe. The ones who say stupid things that somehow make sense. Online or of

No more guessing. No more panic after a bad patch. No encoding surprises. A protocol for safer, smarter updates — the bigger your codebase,

A pure open-source coding agent developed by AI

麦当劳自助管家 McButler — 基于麦当劳 MCP 的点单参谋：每日推荐 / 套餐健康体检 / 门店全成本比价 / 团餐智能配餐 / 麦险分信用评级 / 麦门小剧场。麦当劳 1024 程序员节参赛作品。

Say "¥35, not spicy, no ice" → one answer + a copyable order card. Official calculate-price only. Zero-dependency MCP skill. 麦当劳点餐 Skill.

麦当劳配餐决策 Skill｜1881 种搭配里算出三档最优解，并告诉你为什么不是另外那些。控卡、忌口、拼单 max-min 公平分配；LLM 不参与算钱，每个数字可追溯。

A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedi

麦有谱：同样的麦当劳，不同的吃法。基于麦当劳 MCP 的组合吃法 Skill 与交互演示。

麦麦预算餐：基于麦当劳 MCP 的真实核价、预算比较与餐品替换 Skill

Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, synthetic users, quant surveys, p

GhostWriter reduces API costs and improves AI debugging accuracy by ensuring the AI remains focused only on the logic relevant to the failur