
Apple development skills for Claude Code, Codex, and other coding agents — current iOS 26+ APIs, SwiftUI, UIKit, Liquid Glass, Human Interface Guidelines, and practical workflow guides.
2,861 developers. Ranked by the GitHub stars their repos have earned. Each card shows their biggest plugin.
2,861 developers

Apple development skills for Claude Code, Codex, and other coding agents — current iOS 26+ APIs, SwiftUI, UIKit, Liquid Glass, Human Interface Guidelines, and practical workflow guides.

我们读完了孙宇晨的一切公开内容,提炼出了他的认知操作系统。 采集了什么: 21,829 条推文(英文号 14,418 + 中文号 7,411),覆盖 2017-2026 共 9 年 1 本 288 页自传《这世界既残酷也温柔》全文逐章分析 155 集付费音频课《财富自由革命之路》完整转写(喜马拉雅,~18 小时) 5 场深度访谈完整转录(花总《开腔》86 分钟 / 晚点在场《金丝雀》76 分钟 / Bankless 90 分钟 / UpOnly 60 分钟 / Blue Origin 太空飞行记录) 42

Local-first document management and semantic search for AI coding agents. No external databases, no cloud APIs, no vendor lock-in.

Created & maintained by Yoojin Nam, MD Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea MedSci Skills is a set of Agent Skills for clinical research: literature

By George Hartley, co-founder of Nitrosend. The AI email automation skill for Claude, ChatGPT, and any agent.

Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.

"茫茫人海,一旦错过就不再。" simp,是那个敢于真心喜欢一个人的人。这里教的,是把真心说出口的能力。 不教套路,不玩 PUA,只相信一件事——真心,是最强的攻略。 提供聊天记录、社交媒体截图、照片,生成信号分析报告。 量化感情温度,定制追求策略,把心上人追到手。

A production-ready skill that enables Claude Code to build Android applications following Google's official architecture guidance and best practices from the NowInAndroid reference app.

94 Specialized Skills for Blender Artists. Transform Cursor, Claude Code, Kiro, and Codex into your Senior Technical Art team — not a tutorial bot.

다이소(제품/매장/재고), 상품 가격 비교, 주변 음식점/카페, 주유소/유가, 개발자 요청 제출, GS25(매장/상품/재고), 세븐일레븐(상품/매장/재고/인기검색어/카탈로그), CU(매장/재고), 이마트24(매장/상품/재고), 올리브영(매장/재고), 메가박스(지점/영화/시간표/좌석), 롯데시네마(지점/영화/좌석), CGV(극장/영화/시간표), 디트릭스(독립·예술영화관/상영작/잔여 좌석) 조회 기능을 MCP, CLI, Codex Skill로 AI에 연결합니다.

Your agency's design brain. Always on, always yours. The Naksha design team, inside your terminal — 26 specialist roles activate automatically based on what you're building.

Agentic AI EDR for developer workstations and autonomous agent swarms. Build Swarm Detection & Response platforms with Clawdstrike.

Encrypted by default. Plain (unencrypted) when needed. Persist variables, Compose State, StateFlow, and serializable objects across Android, iOS, macOS, Desktop, and Web Easy to use by design — plus key rotation, cross-platform biometrics, and an encryption

Give coding agents direct access to your logs. OpenLogs turns raw product, API, worker, and infra events into a stream agents can inspect so they can debug failures, trace requests, and answer with real runtime context instead of guesses.

Write less code and say less about it. Honey (I Shrunk the AI) by GreenPT is a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — making agents emit less code and less prose without losing correctness.
Bộ công cụ tạo AI Skill từ ý tưởng — Dành cho Antigravity, Claude Code, Cursor, Windsurf. Đánh giá 100/100 S-tier.

Skills, rules, and validation hooks that teach AI coding agents to generate correct UdonSharp code

这是基于 everything-claude-code 进行二次开发,提供npm一键安装方式,协议沿用MIT Claude Code 增强配置,开箱即用。 本仓库包含生产级 agents(代理)、skills(技能)、hooks(钩子)、commands(命令)、rules(规则)和 MCP 配置,帮助你快速提升 Claude Code 的使用体验。

Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path.

One install. Any AI coding agent gets full Twitter/X superpowers. The official skills.sh skill — maintained by the twitterapi.io team — that teaches Claude Code, Cursor, GitHub Copilot, Cline, Codex, Gemini CLI, Amp, Antigravity, Windsurf, and 12+ other AI

🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dangerous until you say go. From your desk or your phone.

Code is cheap. Context, control, and evidence are not. Let the model move the work forward. Let the human own goals, boundaries, permissions, checkpoints, evidence, and acceptance. Strong coding agents no longer stop at suggestions.

Repo for the official Svelte MCP server.