Havuz

江南 × 烽火戏诸侯文风蒸馏 Agent Skills（Claude Code/Codex/Cursor/Trae/Antigravity 通用）｜1465万字语料实证 + 自动风格审计 + 独立盲测 95/100·A

Offline prompt engineering manager for Windows

A full prompt-writing studio in a single ComfyUI node - AI editing, style targeting, prompt browsing, and wireless prompt injection, powered

Metis is a coding agent that boosts AI/LLM coding performance by 50% QQ群: 801193315

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

Quality-per-token GPT-5.6 Sol, Terra, and Luna model router for Codex, Work, CLI, and subagents.

fluent-korean, Claude Code ve diğer LLM'lerin daha açık ve doğal Korece üretmesini hedefleyen bir output-style eklentisidir.

Neden yükseliyor · 79 günde 1339 yıldız, projeye belirgin ilgi olduğunu gösteriyor. Korece üreten coding agent'larının dil kalitesi somut bir kullanım sorununa karşılık geliyor; ancak son 28 günde commit ve farklı yazar yok. Bu veriler ilginin nedenini veya devam eden benimsemeyi tek başına doğrulamıyor.

Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex / Gemini / Hermes)

AI Prompt工作流库（自用分享）：详情页制作工作流、电商、TikTok、中泰本地化翻译、AI 生图、视频分镜与自动化

Prompt builder for Krea-2 in ComfyUI. Fill structured fields and get flowing prose in the format the model expects, not a keyword list.

Public, source-cited Fable 5, Mythos, Claude Code, and agent-operations second brain. Not affiliated with Anthropic.

The Regression Testing Framework for AI Agents. Replay · Evaluate · Assert · Catch Regressions — in CI. Like Jest for your AI layer.

speak-human-tw, Traditional Chinese metinlerdeki AI yazım kalıplarını işaretleyip Taiwan kullanımına göre düzeltme önerileri sunan bir agent skill’idir.

Neden yükseliyor · 81 günlük bir repoda 1000 yıldıza ve son 28 günde 26 commit’e ulaşmış; Traditional Chinese ve Taiwan yerelleştirmesine odaklanan, kurulumu kolay agent skill’lerine yönelik ilgiden yararlanıyor olabilir. Ancak commit’lerin tamamı tek yazardan geldiği için bu aktivite topluluk katkısı olarak yorumlanmamalı; yükselişin kesin nedeni mevcut verilerden anlaşılamıyor.

🎬 Director-grade Seedance 2.0 prompt OS for OpenClaw + Hermes agents — 28 skills, T2V/I2V/V2V/FLF2V, multi-clip sequences, zh/ja/ko support,

AI 人生设计师 — 基于斯坦福 Life Design Lab 方法论的 Claude Code Skill，通过深度对话帮你设计人生

A deterministic, zero-dependency prompt-pruning layer for long-running LLM conversations — expires stale tool state, collapses duplicate con

Reusable UI/UX design skills for AI coding agents — Codex, Claude Code, ZCode, and more.

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

中文 9 段式人像提示词创作体系 · 可直接出图的模板/风格预设/千条级批量生成器 · 覆盖全身照与上半身中景照 · 适配 ComfyUI/Krea2/GPT Image 2 · 无强制约束，创作自由

Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.

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

免费书：游戏策划实务即用的 AI·Claude Code 活用法 —— 没有一个数字是编造的。全文免费（CC BY-NC-SA）。韩语纸质原版（ISBN 979-11-12-21479-9）的简体中文版。

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

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

Vibe Coding 轻量项目实验室：Web 应用、桌面工具、Prompt 资料库与 Codex Skills

The Agency — a roster of 200+ specialist AI agent personas (engineering, design, marketing, sales, security, GIS, game-dev & more) for Claud

Frontier model solution tracing, then made the prompting skills

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

Codex / WorkBuddy 短剧带货 Skill：salpx 生成分镜首帧，salpx Wan 3.0 直出 2–30 秒视频（多图/视频/音频参考、原生音轨、口型同步），支持美国市场本地化与剧本保真。

A practical Generative AI engineering lab exploring LLM foundations, tokenization, deployment strategies, and real-world AI system design.

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

OpenCode agent configuration — a read-only orchestrator delegates to 6 specialized subagents. Expert model plans, fast models execute. Isola

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

A juicy token compression algorithm. Compress upto 95% of tokens without any loss. Free & Opensource

AI Storyboard Director v5.2: open-source director-grade AIGC storyboard skill for turning scripts into executable cinematic shot chains.

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

Generate verification-focused operating prompts for AI agents.

Agent skill: your AI coding logs as a gamified character sheet — Claude Code, Codex, OpenCode, Gemini, Copilot. 74 achievements, fixed-scale

High-performance computer vision implementation featuring real-time image segmentation matrices, dynamic alpha-channel compositing, and auto

Principal-PM-level product-teardown skill — reverse-engineer any product as a system and render a bilingual (EN + ZH) HTML report with a pro

Growth Marketing OS | Mahmoud Omar — open-source AI marketing prompts, Claude skills, agents & growth playbooks (EN + AR)

A skill library that teaches Claude Opus the working disciplines of Claude Fable 5. Move the checkpoints, not the capacity.

Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the ro

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

Hypertaks = "A founder who owns a library of more than 1,400 books, knows exactly which book to consult for this issue, and has a strict SOP

Claude Code skill: turn raw requirements, engineering PRDs (incl. Feishu docs), or competitor analysis into a concise, coding-agent-ready PR

12 agent skills for AI-driven software development — a gated idea-to-ship pipeline: 7w3 design, build-ready specs, executable architecture,

Methodology + templates for a trustworthy, traceable, self-growing AI data-analyst agent: metrics-first, independent read-only validation, a

Free anti-AI-slop system prompt & skill that makes ChatGPT, Claude, Gemini, Grok & Kimi write like a human. Bans AI tells (delve, tapestry,