Havuz

A Codex skill that keeps human outcomes and creative intent ahead of overengineering.

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

Screenplay breakdown & AI prompt-pack studio — import a script, get scenes, elements, bibles, shot lists & a timeline, then export self-exec

Reusable AI prompt and project brief system for cinematic scroll-driven 2.5D websites.

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

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

Drama Skills, Claude Code ve Codex gibi Agent ortamlarında AI kısa drama üretimini senaryodan storyboard, prompt, üretim ve kurguya kadar dosya tabanlı bir iş akışıyla destekliyor.

Neden yükseliyor · 73 günde 2288 yıldıza ulaşmış ve son 28 günde 75 commit almış; AI video ve kısa drama iş akışlarına yönelik ilgi dikkat çekmiş olabilir. Yükselişin kesin nedeni verilerden bilinmiyor. Commitlerin tek yazardan gelmesi, yüksek commit temposunun bağımsız katkı çeşitliliği anlamına gelmediğini gösteriyor.

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one set

小优AIGC（抖音小优与AIGC的奇妙冒险）的 AI 摄影剧组 skill —— 电影摄影级生图提示词生成器，可装入 Claude Code / Codex / Hermes

东方文化编辑海报 v2 Codex skill：Image 2 出图、中文标题精炼、真实文化物证、A/B/C 三联测试

Offline prompt engineering manager for Windows

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.

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

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

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,

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.

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

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

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

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

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.

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

Claude skill for generating and beautifying resumes — 11 print-ready HTML templates, structured data pipeline, three entry flows (beautify /

Claude skill for behavioral interview prep — mine real experiences, structure them with STAR/CAR, and build a reusable bilingual story bank.

codex-keysmith, Codex talimatlarını yerel yapılandırmaya önizleme, onay, doğrulama ve geri alma adımlarıyla kuran bir Python CLI aracıdır.

Neden yükseliyor · 92 günde 4601 yıldıza ulaşması belirgin ilgiye işaret ediyor; son 28 gündeki 34 commit geliştirme faaliyetinin sürdüğünü gösterse de bunların yalnızca 2 farklı yazardan gelmesi katkı çeşitliliğinin sınırlı olduğuna işaret ediyor.

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

Best Prompt Engineering Tools for 2026 AI Workflow Optimization

Top 10 Claude Prompt Optimization Frameworks 2026

Proven 2026 Multi-Agent AI Review System – Verdict-Driven Quality Control

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

Turn dry expert topics into high-engagement content with 7+2 journalistic angle types. An AI skill for any LLM, any niche, any language.

🔍 Reverse engineer any codebase into a build prompt — architecture breakdown, ASCII blueprint, and AI-ready reconstruction prompt

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

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

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

个人 IP 图解创作器：用你的 IP 形象，生成专属内容图解。

AI skill for rewriting machine-generated text to sound human-written across 9 languages - 5-stage pipeline: cleanup → specificity → tone → r

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