Havuz

A constitution generator for autonomous, agent-run projects: an interview-driven meta system prompt (and installable skill) that scaffolds a

互动小说 skill · 你选，它写｜选项驱动的互动小说 AI 创作规范，装进 AI 助手就能玩，无需部署。interactive fiction for AI agents, choice-driven storytelling

Install once, talk to your agent. ThinkWiki turns documents and notes into a local Markdown wiki with inbox review, content knowledge graph,

Hermes Agent plugin & skill for Twitter search, monitoring, follower exports & X actions. Not affiliated with X Corp.

用于构建Smartisan OS风格UI的Agent Skill

Behavioral-discipline skill turning an AI agent into a methodical, non-robotic bug-bounty & pentest hunter - 42 always-on rules: scope, cove

Intraday gold-futures trading assistant — Al Brooks Price Action + SMC + Order Flow + Volume Profile. Auto-ingests live bars via TradingView

救驾（救驾study / jiujia study）：给留学生的 Canvas / Moodle 学习手帐——盯 deadline、排本周该学什么、按状态给建议。Agent Skill，在 Claude Code、Codex 里说「帮我从 GitHub 安装救驾」就能装。

Automate your real iPhone from Safari with a $2 ESP32. No Mac, no APP, and no jailbreak. Local conversations, your choice of AI, and communi

最强经理之争（其实都很强） • 四位中国权益基金经理(易方达郑希/张坤/武阳·财通金梓才)可溯源对比 Agent Skill：原话语料+真实持仓，5项核心功能，6项进阶玩法。仅研究学习辅助，不构成任何投资建议。

Baseline-aware modern CSS Agent Skill: small SKILL.md router + on-demand references. Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCo

Universal long-term project memory for AI coding agents — Claude Code, Cursor, Windsurf, Cline + 4 more. TDD rules, code graph, spec-driven

曾仕强 AI Agent Skill，基于曾仕强书籍，电视节目及公开演讲等材料构建的大模型知识库 Skill 资源库。完整收录中国式管理全集 23 册、易经、周易、道德经、论语、财神文化、大易管理、三国智慧、家风家庭教育等人情世故与国学管理文本，全部整理为标准化 Markdown

AI-powered personalized IELTS corpus distillation — install-only skill (zero-backend Agent loop) + runnable backend with QMD-RAG. 7-stage pi

Agentic game development for building games with AI Agents. Run one session per seat: art, gameplay, narrative, QA, audio, tech all in 1 spo

面向 Z-Image、Qwen-Image 2.1 与 MiniMax H3 的短剧制作 Skill：角色与场景提示词、图片确认、15秒分镜及按需 A/B 机位。

AI 原生·单文件 HTML 演示 Skill：7 套锚定公认设计体系的视觉人格，好看（WCAG/间距/32 维审计）与诚实（反伪造）都由机器强制，零依赖。 | AI-native single-file HTML presentation skill — 7 design-sy

Excalidraw MCP server with real vendor-icon search & insertion (AWS/Azure/GCP/OCI/Kubernetes) for AI-built architecture diagrams — live canv

Audit and rewrite your README so readers can bail fast — an Art of README agent skill

AI-agent skill for creating, auditing, and maintaining Penpot design systems, prototypes, tokens, and design-to-code workflows via the offic

Build smarter. Work superior. An opinionated rule set for AI coding agents to create original interfaces, compelling content, and production

Agent skill that removes slop, jargon, and AI writing tells from any text. "The gun is not smoking; it's an honest footgun — that will be lo

Evidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.

Agent-agnostic Markdown skill for Xiaohongshu topic planning, trend matching, scoring, and risk review. No code dependencies.

Hermes port of Karpathy-inspired LLM coding guidelines — SKILL.md + examples.

DevLabs™ Free, open source and local-first. A multi-agent harness that works with the AI subscriptions you already pay for. It turns the ter

How do I check brand visibility in AI? open-geo measures whether your brand shows up in ChatGPT, Google AI Overview, Claude, Gemini, Yandex

帮助用户从零写出高质量 PRD，或评估/改进/增量更新已有需求文档。本技能按三视角（用户 / 商业 / 技术）完成诊断，分 **概念版** 与 **落地版** 写入工作区，并系统补全交互状态、数据规范、文案与关键页线框等细节，使文档可直接用于研发实现或 AI 生成代码。

Make generic UI look consistent. No hardcoding, no ignoring your design system. Spec for AI-native design systems: tokens, slots and rules a

Open platform for running Managed Agents at scale

Tailwind CSS v4 plugin: nested elements get the correct concentric corner radius automatically.

AI agent skill for creating cinematic product launch videos with Remotion

Automate AliExpress product listing — 1688 sourcing → Dianxiaomi ERP → AliExpress publish. AI browser automation for cross-border e-commerce

把一张图片逆推成生成提示词（Image to Prompt）：中英双语重建提示词 + 风格标签 + 结构化 JSON prompt，零依赖校验脚本 | Forensic image-to-prompt reconstruction. AGPL-3.0 · Commercial u

🎭 Know yourself as a developer. One command → AI analyzes your coding history → beautiful personality portrait + persona skill. Works with C

Research Software Engineering skills for AI coding agents

A decision protocol for AI agents — critical thinking, evidence verification, and structured review. Less confident advice, more testable de

Names your startup, product or side project, then proves you can actually use it. Checks the domain registry, trademark, GitHub, npm, app st

Your personal GitHub registry for AI Agent Skills. One repo. EVERY agent. EVERY device. Loaded on demand — Zero startup bloat.

A lively Capybara Lulu desktop pet for Codex, with smooth expressive animation, task-aware reactions, 16-direction gaze, and complete source

An AI agent skill for turning characters, products, and everyday objects into themed sticker packs.

AI-driven Roblox R6/R15 animation skill for Codex and Claude, using authentic Blender rigs, audited keyframing, Roblox export, and verified

温病派大师吴鞠通（1758-1836）中医 Agent Skill。基于《温病条辨》《医医病书》《吴鞠通医案》359 案、《温热经纬》吴氏按语蒸馏。三焦辨证·卫气营血·22 温病方剂·9 诊断公式·凉开三宝·白虎四禁·湿温三禁。与倪海厦 skill 合参互补。TCM Wu Jut

Chart a project from a loose idea, then navigate it ticket by ticket on GitHub Issues.

Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review,

Turn Markdown into paste-ready, inline-styled HTML for WeChat Official Account. 10 themes, deterministic validation, placeholder support.

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it te

Xueqiu (雪球) stock data CLI for AI agents — 30 commands for A-shares, HK, US stocks & funds

AI agent skill (Claude Code / Codex) that turns your product into a cinematic promo video: 152 shot recipe cards, 209 style variants, tuned

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.