Havuz

说人话｜中文优先的去 AI 味改写 skill：保事实、分场景、改完可直接发。Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT — removes AI tone, preserves f

Codex için ölçülebilir hedefler üzerinde kod değişikliği, doğrulama, iyileştirmeyi tutma veya geri alma döngüsünü yürüten bir otomasyon aracıdır.

Neden yükseliyor · 197 günde 2734 yıldıza ulaşması dikkat çekici bir ilgi göstergesi. Codex'i sürekli ve ölçülebilir kod deneylerine bağlaması, autoresearch yaklaşımının geliştirici araçlarına uygulanmasına denk geliyor. Ancak son 28 günlük commit ve yazar verileri ölçülmediği için ilginin güncel geliştirme faaliyetiyle desteklenip desteklenmediği bilinmiyor.

Say "¥35, not spicy, no ice" → one answer + a copyable order card. Official calculate-price only. Zero-dependency MCP skill. 麦当劳点餐 Skill.

README design skill for Claude Code & Codex. 帮你把 GitHub README 做得好看又好懂。

麦当劳 MCP 技能：待评价清单、好评兑礼进度、发票报销门槛凑单、单次抽奖确认。99 项测试，非官方产品。

帮你点麦当劳最省的 Skill：自动叠加优惠券、积分和门店活动，实时核价算出最省付法｜基于麦当劳中国 MCP

AI design system scanner + mcp server. Scores repos 0-100, writes fix prompts. 30K+ npm downloads.

Quicksilver, toplu sınıflandırma ve arama işlerini Jev modeline devrederek Claude Code'un daha az token kullanmasını amaçlayan bir skill ve plugin'dir.

Neden yükseliyor · README, 12 görevlik benchmark'ta token kullanımında medyan %82 azalma ve bazı görevlerde hız artışı iddia ediyor; ölçülebilir tasarruf vaadi dikkat çekici. Ancak bu sonuçlar repo'nun kendi benchmark'ına dayanıyor ve bağımsız olarak doğrulanmış değil. Proje yalnızca 2 günlük olduğundan 66 yıldız erken ilgi göstergesi; 2 commit ve 1 farklı yazar ise henüz sınırlı geliştirme kanıtı sunuyor.

A compiler for LEGO® models, built for AI agents.

A lightweight, all-in-one connection manager — SSH, Serial, SFTP, Telnet, FTP, WebDAV and S3 in a single TUI 🔥

A Codex skill that delegates work to ChatGPT on the web.

Agent-friendly CLI for Shenzhen University web services with persistent browser login and structured JSON output.

Claude Code ve Codex geçmişindeki tekrarlanan istekleri bulup proje içinde kullanılabilir kısa agent komutlarına dönüştüren bir Agent Skill.

Neden yükseliyor · Agent araçları arasında tekrar kullanılabilir iş akışlarına ilgi çekiyor olabilir; ancak yükselişin nedenini doğrulayacak bağımsız kanıt yok. 9 günlük yaşında 104 yıldız ve son 28 günde 17 commit başlangıç ilgisi ve hareketlilik gösteriyor; 2 farklı yazarla proje henüz küçük ölçekli.

Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, synthetic users, quant surveys, p

The security-first skill manager for AI agents — every install runs a security scan. Manage skills & MCP servers across 90 agents. Zero-depe

Universal long-term project memory for AI coding agents — Claude Code, Cursor, Windsurf, Cline + 4 more. TDD rules, code graph, spec-driven

코딩 에이전트가 만들어 주는 데모 영상 — 바이브코딩 결과물을 제대로 뽐내세요.

基于麦当劳官方 mcd-mcp-server 的 MCP 客户端与 WorkBuddy 技能：扫描历史订单中仍来得及用餐评价的权益机会，盘点积分兑换，聚合当月活动。

Asks what to optimise and how to measure it, then runs experiments on its own branch.

Install, manage, and share skills across every major coding agent — Claude Code, Cursor, Copilot, and more.

Make your AI agent write documents like Notion — Codex & Claude Code skill that locks document structure & Notion visual style

Turn any skill into a standalone, runnable RAG-native AI Agent

The Rails audit skill for AI coding agents, ranked by blast radius. 🚂☢️

Generate images from local Grok, Antigravity, Cursor, or Codex logins, with official API keys as fallback.

Double-check before you ship: grill the requirements, test the implementation, prove the delivery. An engineering-discipline bundle for Deep

Durable, repo-native project memory for coding agents, without context bloat.

Generates a test suite from acceptance criteria, then converges code against it with an agent that never sees those criteria.

Agent-agnostic semantic skill for MaxCompute SQL — CLI + bare SKILL.md bundle

锻造任何领域的思维工具 — 不是角色扮演一个智者，而是锻造一把可执行的思维工具。基于 Agent Skills 开放协议，可在 Claude Code、Cursor 等 50+ runtime 中运行。

An Enterprise-Grade Full-Stack RBAC Permission Management System Built with Go + React

Astra Skill Optimizer for GPT-6/Astra project Skill and workflow adaptation

The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lig

Privacy-conscious Apple Health export analyzer with bilingual health and multi-sport training reports

deptrust is a CLI that checks package versions for known vulnerabilities across npm, PyPI, crates.io, Go modules, RubyGems, NuGet, Maven, Pa

跨 agent 的 skill 管理器 + skill 推广工具，欢迎fork和pr。管理你所有 skill ，创建技能自带讲解pdf或ppt。支持各种Agent。

A Claude Code skill that consolidates scattered project markdown files into a single canonical CLAUDE.md, with a pinned PROGRESS block at th

Turn any codebase into an AGENTS.md playbook AI coding agents can actually follow.

Claude Code skill: daily tech digest from Hacker News, Lobste.rs and more. Zero dependencies, score-based filtering.

Zero-dependency CLI to scan, recommend, deduplicate, audit, and visualize Claude Code / Codex skills and MCP servers.

微信读书 CLI / WeRead CLI: 基于官方支持 API，面向人类与 AI Agent 的书架、笔记、划线、书评、阅读统计和推荐工具。Official API-based WeRead command-line tool with Agent Skill support

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

洁癖.skill：让 AI Agent 少留痕，留下的都有用。 Tidy Skill: make AI agent artifacts intentional, scoped, and disposable when needed.

针对中文AI编程的Top 20 提示词，做skill用于辅助codex/claude生成代码

Stop being lost in a codebase. CLI + Claude Code skill that builds an import graph, runs PageRank to find the files holding a repo together,

DSH 插件开发踩坑与做法档案（skill + 文档）：cordis 双副本、tsconfig 三件套、Windows junction、多帧 zstd 等实测记录

Fast, daily-updated skill and CLI for arXiv, PubMed, PMC, and policy retrieval

⚡ TidyFactor Architecture Ecosystem , AI-Native Web Architecture, Design Systems & Agent Skills .

A benchmarking suite for Agent Skills (SKILL.md files) that measures whether a skill actually improves LLM output quality, and by how much.

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

CDP-powered perf CLI: goes beyond Lighthouse scores, builds causal degradation graphs. Tells you why it's slow, not just that it is.