Havuz

Universal AI Agent Swarm & MCP Plugin with 178 specialized skills and 8 autonomous subagents for Antigravity, Claude Code, Cursor, Windsurf,

Research-backed agent skills and tools for premium image, video, audio, voice, and generative media production across AI coding assistants.

FALSIFY · 证伪 — 先证伪，再决定。A portable reasoning kernel: evidence layering, falsifiers, and a tamper-evident forecast ledger for any AI agent.

Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, les

365 free AI marketing skills (zh-TW/en) for ChatGPT, Claude, Gemini, Claude Code & Cursor — copywriting, ads budget, margin, CRM, email. 365

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

三个 skill 画论文图：fig-analyze 看材料，fig-draw 先看 6 种风格再出图。交付后询问要不要做成可编辑 PPT，同意后 fig-pptx 才做。npx skills add Azhi-ss/academic-figure-skills

许愿特化器 · Wish Specializer — DSH 插件：让模型更出色地，不误解你的意思地，完成你的“愿望”。在短提示词+自带的Wish预设（PTC也可以）+重度的情况下，可以起到巨大的表现增益

DeepSeek-Harness (DSH) 插件：✨ 提示词一键增强（5 模式·模型链·记忆链）+ 💬 语音输入增强（热键·说完自动停·口水词清理·语音纠错）

DSH PUA — 为 DeepSeek Harness 提供 PUA 任务推进、角色风味、验收循环和运行状态卡片 · PUA task persistence, personas, verification loops, and live status cards for De

Antigravity 破甲工程：二进制提示词补丁 / 规则技能 / 生命周期钩子 / IDE 等长补丁 / 模型后端改道

Ready-to-use Grok Bot profiles with focused outcomes, explicit approval boundaries, and separate specification, implementation, and verifica

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。

Community edition of RepoPrompt: a native macOS context engineering app for AI coding agents, with an MCP CLI.

138 bilingual AI marketing skills (69 VN + 69 Global) for Claude Code, OpenCode, Codex, VS Code. Four role SOP packs — content, design, perf

Expert-thinking AGENTS.md profiles that teach AI agents to reason like senior scientists and engineers.

大师.skill — 输入行业，自动调研 6 轨[行业大佬 / 工具地图 / 工作流 / 知识正典 / 信息源 / 术语标准] → 提炼为可运行的行业 Master OS skill；装到任意 Claude Code / OpenClaw / Codex / Hermes age

Claude Code skill & open-source wisdom companion (v6.6.0, Apache 2.0) for CLI, IDE, and web chat. One lens per turn, local SQLite vault, 350

面向电商视觉生产的 Agent 技能库：26 个可组合的 skill.md，覆盖平铺图 → 模特上身 → 裂变套图 → 详情页 → 主图视频 → 投前质检 → 平台合规校验。不锁后端，dLazy / OpenAI / Gemini / fal / Replicate / 火山方舟

11 Claude skills for SEO: page audits, linkbuilding, article writing, E-E-A-T audits, semantic gap analysis, link building. Methodology from

Convert GitHub profiles and repositories into clean, LLM-friendly Markdown. Features profile README ingestion, repository lists, and PAT sup

AI-KIT is a practical starter kit for development: ChatGPT/Codex, Claude, DeepSeek, KIMI, and other coding agents. It provides reusable proj

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

AI video prompt cheat sheet & Claude Skill: cinematic camera angles, camera movement, lighting, composition, color grading for Veo 3, Kling,

Claude skill & plugin: turn Claude (or any LLM) into an MBB-grade management consultant. Case-interview coaching, strategy frameworks, marke

Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.

ASD-STE100 Simplified Technical English as a plugin for Claude Code, Codex & coding agents — clearer, unambiguous LLM output

Mutation testing for your LLM evals — degrade the system under test and check whether your evals would actually catch a regression.

ComfyUI nodes for MOSS-Image: storyboard grids, layout editor, face swap, plus a generic LLM prompt node (caption / expand / edit / compile)

21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a

Air traffic control discipline for agent output. Written for a reader with ADHD.

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any sc

For those who struggle with how Claude speaks to them. No more essays. No more slogans, metaphors, "it's not X, it's Y". This plugin makes C

Prompt enhancement plugin for the DeepSeek Harness web GUI: one-click rewrite of the composer draft into a structured prompt, with preview,

Photo Revival, Codex için günlük fotoğrafları bol beyaz alanlı, küçük ve el çizimi hissi veren illüstrasyonlara dönüştürmeye yönelik bir skill sunuyor.

Neden yükseliyor · 57 günde 574 yıldız alması hızlı görünürlük kazandığını gösteriyor; ancak son 28 günde 2 commit ve 1 farklı yazar olması, yıldızların aktif geliştirme veya geniş katkıcı topluluğuyla desteklendiğine dair güçlü kanıt sunmuyor.

By a 12-year product manager who builds 0-to-1: takes a beginner from a vague idea to a buildable plan, then guides the build (GitHub basics

用Agent自动生成小红书爆款封面

Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin

Premiere-inspired PySide6 director studio for MiniMax H3 Ref2VA with AI shot planning, semantic media enrichment, timeline prompt reconcilia

🎓 Claude Code skill — AI prompt library for academic paper writing, polishing, reviewing, translating and submitting to SCI/IEEE/Nature/TRO

Generate project-based guidance and interview Q&A docs with STAR speaking scripts. 基于真实项目生成导学与面经（含第一人称 STAR 法则口播答案）

19 套可直接生图的视觉风格 Skills，为 gpt-image-2 编写。把文章、主题、产品或已有视觉资产编译成完整提示词。/ 19 visual-style prompt skills for gpt-image-2.

58 个跨境电商 · DTC 品牌出海 AI 技能库:Amazon 运营、SEO/GEO、广告归因、财务、联盟、红人、线下零售、VOC、众筹。事实均标来源与日期,内置证据闸——数据不足时说「数据不足」,而不是编一个数字。| 58 skills for cross-border e

DeepSeek Harness plugin: DietrichGebert/ponytail lazy senior mode & 7-rung ladder port, 6 skills with bilingual descriptions & per-skill tog

1407 张 AI 服装参考图 · 纯静态图库，支持手动上传、自定义分类与 DeepSeek 提示词生成

An Agent Skill that turns raw text into production-ready, designer-grade posters in 20 visual styles. Supports Claude Code and Codex.

图片/中文描述 → 英文绘图提示词（DeepSeek API）· Windows 零依赖单文件小工具 / Chinese(or image)-to-English image prompt translator

vibecode-pro-max-kit, AI coding agents için planlama, uygulama ve kontrol aşamalarını bir araya getiren, projeye eklenen spec-driven bir geliştirme iş akışı kitidir.

Neden yükseliyor · 124 günlük yaşında 1138 yıldız almış olması belirgin ilgiye işaret ediyor; kapsamlı agent iş akışı ve tek komutla kurulum vaadi bu ilgiyi açıklayabilir. Ancak yıldızlar kullanım kanıtı değil; son 28 günde commit ve farklı yazar verisi sıfır olduğundan ivmenin sürüp sürmediği bilinmiyor.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history,

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts