Havuz

The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas an

A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-tea

Jailbreak system prompt. One file, one speaker, no second-guessing. Paste it as the system prompt on any provider.

241 evaluated academic Claude/agent skills across 18 research domains — bioinformatics, cheminformatics, data science, databases, clinical,

PROS 05｜初五整理维护的14项公关、研究与知识维护Skill，包含方法、参考、模板与脚本；基于真实材料形成有证据边界的判断与交付。

Reference-first Codex workflow for edit planning, keyframe approval, and MiniMax H3 prompts.

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit)

Agent Skills von LOGIN zur freien Nutzung - SKILL.md-Format fuer Claude Code, Claude-App und API

Complete game production workflow for Claude Code — 27 skills from concept to shipped build. Design review, prototype planning, game feel di

Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario

跨 Agent、多语言面试准备 Skill | Codex · WorkBuddy · Claude | JD analysis, tailored answers, role practice & adaptive mock interviews

AI short-drama story architecture, Studio routing, model-aware shot timelines, continuity, validation, and resumable workflows for Codex and

简明技术中文 / Simplified Technical Chinese: a controlled language for Chinese technical writing, modelled on ASD-STE100. 40 rules, a one-meaning-

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: an

Make Claude Opus, Sonnet, GPT, or Gemini produce work close to what Claude Fable 5 would ship. 21 craft standards written and audited by the

AI Skills That Actually Do Things — 中文優先的 Claude Code / Codex agent skills 合集 · Reusable bilingual skills for any LLM workflow

Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.

Markdown that steers an LLM is code. Genesis is the architectural layer for designing multi-agent, multi-skill systems -- with named pattern

Real-world AI workflows for creators.

Biblioteca de Motion apenasdouglas: 24 efeitos de animação com o nome em português e o termo pra pedir pra IA. Receitas pra canal dark, tema

赛博人物库 · 把中国互联网最有辨识度的人物蒸馏成 AI Skill / Claude Code Skill / LLM character distillation

Practical AI playbooks for engineering leaders to improve delivery, decision-making, and team productivity with real workflows, prompts, and

You ship with AI. Now sell with it. Enterprise sales methodology for the AI era — refined inside AWS. Free Claude skill, 60-second install.

Turn Claude Code into a senior software architect that orchestrates a team of specialist agents and audits itself. An 8-phase skill with TDD

Research-backed prompting toolkit for Claude. System prompts, CLAUDE.md configs, and templates grounded in Anthropic's 2026 emotion vectors

Battle-tested model-dispatch doctrine for Claude Code — portable ops rules that let Sonnet/Haiku reliably run projects. Iterated in real dep

Craft is a Claude Code plugin that asks you the product questions and works out the technical ones. Features get planned, built, and tested,

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

Harness-enforced AI business research skill for Claude Code and Codex Desktop

An AI prompt-skill that turns 20 cognitive biases into high-converting marketing copy. Includes playbooks for ads, landing pages, email sequ

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

Supervising whether AI really promotes cross-platform skills in research programs

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

obra/superpowers extended — 14→24 skills, 6 GadaaLabs engineering improvements, override infrastructure, one-command install

多模态检索实战：意图识别、Prompt 工程、Qwen LoRA、EmbeddingGemma 2 与 InfoNCE 对比学习。含真实演示、自有数据接入、训练评测及 RAG 检索组件学习指南。

Platform-agnostic AI agent: one Full-Stack Software Engineer brain, compiled into ready-to-paste adapters for ChatGPT, Claude, Copilot, Gemi

AI Web Solutions and Python Automation Projects by Krish Sharma 2026

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

Get it right the first prompt. A free Claude skill that rewrites your prompt into an optimized format, audits 35 credit-waste patterns, and

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

Portable fresh-agent QA loop prompt for finding bugs without biased self-checks / 通用自动 QA 循环 SKILL

OmniAiLab AI Director｜影视级全流程 AI 导演 Skill，也是会引导你做判断的决策系统：先定作品形态，再让你指定导演／摄影机／布光／美学（或交给它判断），从剧本解析到成片交付。An end-to-end AI directing Skill that gu

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

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemin

A curated collection of Claude Fable 5 system prompts for developers and researchers. Discover more advanced prompt engineering tools at Moe

A production-grade control layer that sits between your application logic and any LLM — input validation, schema enforcement, circuit breaki

53 retro HTML/CSS UI themes for AI-assisted frontend development. Windows 95, CRT, vaporwave, DOS, arcade, mainframe, and more.

Orquestrador de 5 agentes IA especializados para analise 360 de features com Claude Code. 1 comando, 5 perspectivas, 1 relatorio executivo.

200 web animation examples with copy-ready AI prompts + MotionLens: turn any site's animation into a prompt. React, TypeScript, Framer Motio