Havuz

Token-efficient Windows file discovery for Codex and AI agents using voidtools Everything (es.exe)

A comprehensive Codex skill for Runpod: Serverless workers, Pods, Flash, Public Endpoints, runpodctl, MCP, Python SDK, REST, GraphQL, storag

Adaptive GPT-5.6 Sol, Terra, and Luna routing skill for Codex

Codex skill that disables Responses Lite model mapping to restore hosted Web Search through OpenAI-compatible gateways.

Photo Decode / 解图 (PhotoDecode) — AI skill for visual analysis, image decoding, source-adaptive reconstruction, color palettes and key visua

Turn photos into 16:9 transparent PNG retro gouache journaling material collections with Codex.

Make your coding agent justify architecture with real sources before it builds.

剪影群像风格 Skill v1：正负形互补纸艺双联画，锁定原人物像素｜理智画

📸 上传一张照片，生成影棚级职业照/证件照 — 11种风格 + 海马体级美颜，Claude Code / Codex / OpenClaw skill

Codex使用自定义api如中转站时的图像生成skill

Agents config for development

Local CLI-first bridge for bidirectional Claude Code and Codex review loops.

A Codex Skill that turns one reference image into a safe, one-click Dream Skin theme.

Codex skill and local toolkit for tracking Hong Kong rental listings

A self-correcting system of nested engineering loops: plan & execute repo work; safely implement audit findings; design greenfield & improve

开源微信公众号排版 Skill / AI 视觉主编：让 Agent 将主题、资料或 Markdown 转成 12 套可切换主题的微信兼容文章，支持 AI 配图、手机预览、富文本复制和公众号草稿箱发布。Open-source AI agent skill for Markdown

Flight search and booking Skill for AI agents. Automatically installs the atlas-flight CLI.

Agent skill for generating and verifying AGENTS.md files for coding agents.

Turn complete knowledge into final-only Xiaohongshu educational carousels with consistent characters and deterministic Chinese typesetting.

Claude as subagents in Codex — scoped workers, resumable sessions, git-ignored logs.

Most AI will tell you your startup idea is brilliant. This one researches it properly and scores it out of 100. The two ideas I have put

Quality-first Codex skill for verified delegation across native subagents and Codex/Claude CLI workers.

An open-source companion repo for Agentique.io: a free community hub for discovering, sharing, and reusing trusted AI agent resources.

Claude Code/Codex skills, evals, harnesses/context tools, and learning resources that make it easy to build with Jev, TypeSafe's System One

Codex Skill for choosing and coordinating the smallest safe Agent setup.

视频复刻大师：将参考视频拆解为完整剧本、原片关键帧图文故事板与 Seedance 2.5 自包含提示词，支持标准与深度分析模式。

Material 3 & Expressive UI skill for Android and Web: adaptive layouts, accessibility, forms, loading states, and restrained design without

加密环境文件操作 MCP 工具。当 Node.js 是加密软件白名单进程时，通过 fs 模块自动解密读写文件明文，替代 AI Agent 内置文件工具，适用于任何支持 MCP 协议的 Agent。

Agent skills for SolidJS 2.0 — write, migrate, and review solid-js 2.x code without React/1.x reflexes

一张照片变成 8 张趣味贴纸：可揭下下载，也可贴上 Mac 桌面 · Turn one photo into 8 playful stickers to download or pin on your Mac desktop.

软件著作权申请材料生成 Skill｜Generate standardized software copyright registration materials with AI.

Turn long AI conversations into reusable domain knowledge across sessions

Ready to use design system for cool UI/UX with no extra slop

CLI, MCP server, and Skill for safe local Codex session audit, cleanup, restore, and verification.

GEO-first SEO toolkit for Codex. Audit websites for AI search visibility across ChatGPT, Perplexity, Gemini, Google AI Overviews, and Bing

A provider-agnostic Codex skill and Python toolkit for cleanly redrawing AI-degraded images while preserving composition.

A Codex skill that turns 'do everything' into safe scope, defaults, memory, and AI observability.

Autonomous AI agent loop that keeps working through your project while you keep planning what comes next.

Remove unrequested caveats, faux rigor, invented metrics, and AI formatting residue from academic writing.

将简单设定扩写成中国式宏大场景故事、连续分镜与成对图片视频提示词的 Codex Skill

A Codex Skill for Seedance 2.5 long-form, multimodal, extension, editing, green-screen, white-model, and audio prompts.

Agentic video editing engine/skill/plugin

Let Codex test multiple fixes in isolated worktrees, compare evidence, and apply only the safest proven solution.让 Codex 不再盲改代码，而是并行测试多个方案，用