Havuz

A complete engineering team in one folder: 26 specialist agents, 20 workflow skills, orchestrated workflows and quality gates.

Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.

Local context engine for AI coding agents. Routes tasks to relevant files, tests, rules, and skills, supports prompt caching, and builds com

风插 2.0 — DSH 推理语域锚定预设：两个 agent preset（风插标准/风插 PTC）在 runtime-context 快照头尾各注入一次形式化约束，使推理以第一人称复数展开。定性=硬指令约束（非吸引子）；未证明能力提升，未证明无负面作用。Apache-2.0

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

Focused agent skills for thinking and creating · 清晰思考，自由创作。Explore qc-alchemy through 10 visual transformations.

Agent Skill for generating deployable system prompts for AI agents

Plain-English legal writing skill for AI agents (Claude Code, Codex, Antigravity). For lawyers, paralegals, and in-house counsel: audits and

Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude C

Token-compression skill. An adaptation of caveman — short common words, trust context, say just enough, be laconic.

Claw is a local-first AI control plane that runs powerful open models on your machine and connects to top LLM providers. It intelligently ro

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

A Claude Code plugin marketplace that turns a personal engineering workflow into one-click superpowers — forge sharp PRDs from any raw input

Your AI coding harness, ported to every client you use. Capture Claude Code (or Codex) rules, hooks, skills, subagents, commands and MCP ser

A structured knowledge base for large language model technologies, covering LLMs, Agents, RAG, model training, evaluation methodologies, and

Deterministic causality engine for AI roleplay.

Make AI agents aim higher without losing control: a Claude Code skill with two bars per task, a cheap gate check before expensive work, and

Teaching image models to think in manga pages, not illustration grids.

A lightweight pre-coding check for Codex, Claude, Cursor, Antigravity, Gemini, and Grok: look up what you can, and ask only when an unresolv

小红书图文笔记 Agent Skill，支持看图理解、主动提问、智能选题、实时热梗搜索、标题正文、标签评论钩子和风险检查。

Strip AI writing tells at two layers: surface (Wikipedia Signs of AI writing) + narrative (StoryScope, arXiv:2604.03136). A model-agnostic L

Arming AI with Marxist methodology for deep structural analysis

LLM应用&Agent开发面试题全集：21个专题、380+道题、41000+行、覆盖Python/FastAPI/LangChain/CICD

One person, one bot team: supervisor + specialist Grok Bot teams with copy-ready prompts for 8 personas · 一个人，一支 Bot 团队

20 production-ready AI prompts optimized for n8n workflows. Copy-paste system prompts with model recommendations, cost estimates, and integr

Translate judgments, workflows, system states, and metaphors in articles into clean, hand-drawn, absurd, and minimalist body illustrations S

🧠 布洛陀·五层记忆系统 v2.2.10 · 一包多平台：WorkBuddy·Qoder CN·ZCode·Hermes·Zwork(AutoClaw) 全自动｜豆包办公 一步粘贴｜LobsterAI 适配收尾中暂不推荐｜Trae Work/千问/TeleAgent 适配层保留待

ComfyUI custom nodes: anime character styling console (clothing / pose / expression / scene slots) with a cross-plugin tag arbiter. Zero thi

⚗️ Experimental — A markdown brain that gives your AI coding tools judgment and rigor: sharp defaults, real decisions, and the discipline to

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）

UI Design Agent Kit: prompt kit for a UI/UX agent with spring physics, tool routing, design contract, and evidence-based verification.

Local-first tool that strips emails, secrets, paths, and other identifying content out of your prompts before they reach a cloud LLM — and r

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

Open-source AI prompt engineering workspace — production-ready Next.js SaaS with conversational refinement, multi-engine targeting (ChatGPT,

AI music prompt nodes for ComfyUI — 73 style presets plus song analysis for MiniMax Music 3 and YuE2. Runs on CPU.

Reverse-engineer how you think, talk, and make decisions — then turn it into a stress-tested AI System Prompt. Works on any LLM. Full pipeli

Open-source visual ontology and constraint engine for inspectable reference-guided image generation. Try Virtual Try-On and Cosplay in the P

Prompt-first Codex skill for authorized URL and screenshot web clone prompts.

Build AI agents using the same architecture patterns as Claude Code. Skill + 6 examples + runnable Python code. No framework.

Verdict-first output for AI coding agents. Tiny prompt + installer for Claude Code, Codex, Gemini, Cursor, opencode, and 30+ agents.

Plan, build, review, and ship to the real world. Full opinionated harness with built-in Project Management and DevSecOps to code and maintai

AI ruleset to build or improve CV that interviews you step by step, works for any market, and self-audits each draft

18+ only｜文生图提示词教学站：figure-photo / youth-seduction / erotic 三线导演台 · 维度体系 · 写法规则 · 组合图库。含露骨提示词文本，禁止未成年；不随仓库分发图片。Adult-oriented text-to-image p

Generate, compare, and edit images in Claude Code using your Codex subscription. Background jobs, parallel drafts, and lean context. No imag

Postmodernist critique skill for Claude and Codex. Pressure-test AI-generated strategy and marketing slop. Debug reality.

AI Novel Diagnosis Desk：一站式 AI 网文诊断工作台，可自动解析小说文本，生成小说人物关系图谱，诊断读者流失原因，并输出可执行的智能改稿 Prompt。

An agent skill that reads a photo the way Sherlock Holmes reads a stranger (福尔摩斯): observe first, deduce second, every conclusion cites its

为 DeepSeek Harness 设计的破限插件：卸掉宿主的提示词限制和审批拦截，让助手照你说的做，不半路拒绝、不反复请示。补丁逐条可选，随时还原原版。 A jailbreak plugin for DeepSeek Harness: it strips the host's

花 4 個月慢慢一步一步調整到可以自動化去防 AI Slop 的機制，包括：CLAUDE.md 跟 Hook 之間的設定跟腳本，目的就是幫助整個系統在運作的時候減少 AI Slop。

A system prompt against AI sycophancy, backed by 42 sources on why models tend to agree with you.