프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. Google로 로그인하면 리뷰를 쓸 수 있어요.프로토타입 · 30분마다 업데이트
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

Agent Skills

AI에게 한 가지 일하는 방식을 가르치는 지시 묶음(skill), 스타 200개 이상이고 SKILL.md가 실제로 있는 GitHub repo에서 · MCP server가 아니에요

Skill과 MCP의 차이 →

“code review”와 일치 25개

open-code-review

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

제작자: alibaba★ 51,962 (whole repo)skill 2개

Skill · 안내서

academic-research-skills-codex

Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

제작자: Imbad0202★ 14,598skill 1개

Skill · 안내서

academic-research-skills

Academic Research Skills for Claude Code: research → write → review → revise → finalize

제작자: Imbad0202★ 57,019 (whole repo)skill 4개

Skill · 안내서

tuicr

a code review TUI with vim keybindings

제작자: agavra★ 3,609skill 1개

Skill · 안내서

claude-skills-llm-council

LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review

제작자: aiwithremy★ 3,074skill 1개

Skill · 안내서

elephant-goldfish-model

Open-source plugin for designing and reviewing software with agents

제작자: google★ 19,685 (whole repo)skill 7개

Skill · 안내서

code-review-skill

A comprehensive code review skill for Claude Code, covering React 19, Vue 3, Rust, TypeScript, TanStack Query v5, and more.

제작자: awesome-skills★ 2,267skill 1개

Skill · 안내서

BeautifulRust

Agent Skills that teach coding agents to write, review, and port idiomatic Rust, plus a tested clippy config. Works with Claude Code, Codex, Copilot, Cursor, and Gemini CLI.

제작자: morganlinton★ 1,826skill 1개

Skill · 안내서

greenlight

Pre-submission compliance scanner for the Apple App Store and Google Play. Scans code, privacy manifests, Android manifests, and IPA/APK/AAB binaries against the review guidelines. Offline, no account.

제작자: RevylAI★ 2,474 (whole repo)skill 2개

Skill · 안내서

plannotator

The workspace to stay in the loop and on top of agents - shape, decide, plan, annotate, review code, share with team, and send all feedback to agents with one click.

제작자: backnotprop★ 11,771 (whole repo)skill 10개

Skill · 안내서

react-doctor

Your agent writes bad React. This catches it

제작자: millionco★ 15,139 (whole repo)skill 14개

Skill · 안내서

gentle-ai

Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Organic-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.

제작자: Gentleman-Programming★ 9,221 (whole repo)skill 18개

Skill · 안내서

superpowers-zh

🦸 AI 编程超能力 · 中文增强版 — superpowers(250k+ ⭐)完整汉化 + 4 个中国原创 skills,让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI / Qoder 等 26 款 AI 编程工具真正会干活

제작자: jnMetaCode★ 8,541 (whole repo)skill 20개

Skill · 안내서

qualitylayer

Plan, implement and verify software with your favorite coding agents. Work in the App or browser, or in your own terminal, IDE or agent app.

제작자: maxritter★ 2,149 (whole repo)skill 7개

Skill · 안내서

Auto-claude-code-research-in-sleep

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

제작자: wanshuiyin★ 19,246 (whole repo)skill 79개

Skill · 안내서

gentle-shell

Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD).

제작자: Gentleman-Programming★ 2,667 (whole repo)skill 12개

Skill · 안내서

rstack

Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.

제작자: michaelshimeles★ 1,521 (whole repo)skill 7개

Skill · 안내서

brooks-lint

Portable AI code quality reviews for Codex, Cursor, Copilot and other coding agents: six Agent Skills for architecture, technical debt, tests and remediation.

제작자: hyhmrright★ 1,577 (whole repo)skill 9개

Skill · 안내서

delegate-skills

Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer.

제작자: amElnagdy★ 2,607 (whole repo)skill 18개

Skill · 안내서

ripwire

The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Cut agent token costs by finding code without reading the repo, then keep large codebases off the complexity wall: blast radius, tests to run, quality deltas as you write. Every guess labelled, every loss publish…

제작자: redhat-et★ 2,544 (whole repo)skill 19개

Skill · 안내서

ai-legal-claude

AI Legal Assistant skill for Claude Code. Contract review, risk analysis, NDA generation, compliance auditing, negotiation strategy, and PDF reports — 14 skills, 5 parallel agents. If you want to learn how to sell this to real businesses, check out the Skool community

제작자: zubair-trabzada★ 1,841 (whole repo)skill 14개

Skill · 안내서

growth-lab

An end-to-end growth tool that understands the product, fetch the data it needs, researches the market, executes campaigns, and reviews results to improve the next round of growth. 从代码到市场的开源端到端增长工具。理解产品、接入信息渠道、研究市场、执行增长行动,并基于真实数据自我改进。

제작자: tsingyuai★ 1,974 (whole repo)skill 22개

Skill · 안내서

claude-blog

Free, open source blog writer for Claude Code. Researches current sources, writes answer-first posts for Google and AI answers, has an independent reviewer score each one out of 100 and ships only after five delivery gates. 32 skills, 30 /blog commands, 5 agents. Active development at AI-Marketing-…

제작자: AgriciDaniel★ 2,762 (whole repo)skill 33개

Skill · 안내서

pstack-claude

Antigravity, Claude Code, Codex, Copilot, Gemini, Muse, OpenCode, Pi, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

제작자: michael-denyer★ 4,346 (whole repo)skill 54개

Skill · 안내서

검색에 맞는 MCP

Front-End Checklist

Review frontend code and live pages against 386 quality-gated web development rules.

제작자: thedaviddias널리 사용됨★ 7.5만 저장소 전체의 별42일 전 업데이트

MCP · 서비스 연결클라우드에서 실행PopNx 팀이 직접 써 봄

Skylos

Dead code, security, secrets detection and code quality for Python, TypeScript, Go.

제작자: duriantaco널리 사용됨↓ 1.7만/주★ 9458개월 전 업데이트

MCP · 서비스 연결내 컴퓨터에서 실행

Mind Upload AI meta harness

Your AI mind directs coding agents; work reviewed against your memories: Claude Code, Codex, Cursor

제작자: Voidborn-Industries성장 중↓ 5.5천/주★ 3오늘 업데이트

MCP · 서비스 연결컴퓨터 또는 클라우드

Concord MCP

Cross-harness communication and shared work-state for AI coding agents.

제작자: Get-Concord-AI성장 중↓ 991/주★ 1.2천5일 전 업데이트

MCP · 서비스 연결내 컴퓨터에서 실행

Trace MCP

Code graph MCP: 81 languages, 91 frameworks, 72.7% fewer PR-review tokens, comprehension at parity

제작자: nikolai-vysotskyi성장 중↓ 4천/주★ 204오늘 업데이트

MCP · 서비스 연결내 컴퓨터에서 실행

GitWarren

Code review on your own machine, for you and your coding agent. Nothing leaves your computer.

제작자: klarluft초기↓ 88/주★ 12733일 전 업데이트

MCP · 서비스 연결내 컴퓨터에서 실행

“code review”에 맞는 MCP 모두 보기 →