Havuz

HEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), rever

The most frequently used agent skills of Wade Foster, CEO of Zapier

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party cal

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

Global instructions for coding agents: evidence, parallelization, validation, all in one AGENTS.md / CLAUDE.md

Agent Skills lifecycle toolkit: mine repeated coding-agent workflows, audit and personalize skills, and generalize personal skills for publi

Make Opus 4.8 (or any Claude model) work like Claude Fable 5 — a Claude Code skill + guard hooks (plan gate, model ceiling, per-task enforce

The most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using C

情圣 · Claude Code 中文恋爱教练技能 · 微信/探探/Soul/Bumble/青藤之恋聊天截图分析 · 高情商回复生成 · 7阶段关系推进

A muted, poetic paper-poster Agent Skill for low-saturation zine-style image generation.

这个skill旨在让GPT说话像人，改善防御性回复，不套安慰模板，说大白话。与同类skill对比，说人话的能力排名第一（Codex skill，附盲评对比）

CLAUDE.md / AGENTS.md 规则模板：放进项目根目录，让 Claude Code、Codex、Cursor 少返工（附前后对比）｜Drop-in rules for AI coding agents

Goal-based planning and proof gate for AI coding agents

Multi-agent engineering framework: evidence packs, runtime validation, task decomposition, cross-window worker execution, and CI artifact ve

DeepSeek Harness 官方通道破甲预设 · complete:true 整段替换 · 自带工具说明书 · 不改宿主 · 升级不丢

Production-grade vibe coding framework with specs, architecture, AI agents, testing, security, code review, CI/CD, and battle-tested workflo

电商主图与详情页视觉策划、参考反推和生产级生图提示词 Skill

EXSALA HERMES MOD - streamlined execution profile + skill pack for Hermes Agent

把你的网易云歌单与听歌排行变成一份深度自我画像 —— 支持 Windows / macOS 的本地数据采集与 AI 画像分析 Skill

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.

让 AI 主动记错题、自我迭代的协作机制 · A framework that makes your AI reflect on its own mistakes and stop repeating them

An AI roleplay chat platform with the most advanced prompting system

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

AI-driven intelligent clipboard turns scattered content across applications into a searchable, editable AI context. It features a clean, ele

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

An open Agent Skill for extracting poster design systems and transferring them to original poster concepts.

ChatGPT 与 Codex 的可验证工作流、断点交接、网页增强和本地工具

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

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

One-stop shop for AI skills and agents. Search 110K+ community skills, install and track them declaratively, and deploy across all major AI

Seedance.skill — 白模驱动的 AI 视频工作台。白模参考视频与提示词出自同一份 scene.json，渲染前做几何体检，还能从一张照片反解出白模。Control AI video with clay renders — and a prompt that can'

Personality layer for coding agents. Same code, different voice: yo / dawg / mafa / off.

DeepSeek V4 特化思维链引导规范：we need to 句式，任意 agent 客户端可接入（纯提示词层）

Rational engineering system prompt for Codex and LLMs — focused on accuracy, software engineering, AI, security research, bug bounty, and re

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

Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.

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

An ongoing, collaborative meta-analysis about Human-AI-Interactions. We aggregate data and knowledge to build a non-abrasive, user-friendly

ASD-STE100 (Simplified Technical English, Issue 9) for Claude Code: /asd mod with an STE pane, agent skill, and linter. Inspired by Karpathy

🐴 Prompt-first harness engineering for safer AI coding agent workflows.

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

✨ Stunning glassmorphism UI for Stable Diffusion and Anima prompt engineering. Intelligent conflict-free composition, live preview, NSFW saf

讓 AI 用台灣人的繁體中文講話，並把已寫好的文字清掉 AI 味。Claude Code、claude.ai、ChatGPT Codex 與一般聊天都能用。

게임 기획 실무에서 바로 쓰는 AI·클로드 코드 활용법 — 한국어판 원고 (CC BY-NC-SA 4.0 · 부크크 ISBN 979-11-12-21479-9)

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

Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development

Find and repair substance defects in AI-assisted prose, code, docs, and agent output. Reports defects, never authorship. Structural tests ov

AI Agent 面试知识库：覆盖 LLM、Prompt、RAG、MCP、Tool Use、Agent 架构、Multi-Agent、LangGraph、Claude Code、Codex CLI、工程化评估、安全与源码解析。

小liu破甲 - Codex CLI jailbreak prompt and one-click deploy tool. 基于CTF框架的Codex破甲提示词与一键部署工具