Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

Agent Skills

Instruction sets (skills) that teach an AI one way of working, from GitHub repos with 200+ stars and a real SKILL.md · not MCP servers

How a Skill differs from MCP →

25 skills match “code review”

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.

by alibaba★ 51,962 (whole repo)2 skills

Skill · How-to guide

academic-research-skills-codex

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

by Imbad0202★ 14,5981 skills

Skill · How-to guide

academic-research-skills

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

by Imbad0202★ 57,019 (whole repo)4 skills

Skill · How-to guide

tuicr

a code review TUI with vim keybindings

by agavra★ 3,6091 skills

Skill · How-to guide

claude-skills-llm-council

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

by aiwithremy★ 3,0741 skills

Skill · How-to guide

code-review-skill

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

by awesome-skills★ 2,2671 skills

Skill · How-to guide

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.

by morganlinton★ 1,8261 skills

Skill · How-to guide

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.

by RevylAI★ 2,474 (whole repo)2 skills

Skill · How-to guide

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.

by backnotprop★ 11,771 (whole repo)10 skills

Skill · How-to guide

react-doctor

Your agent writes bad React. This catches it

by millionco★ 15,139 (whole repo)14 skills

Skill · How-to guide

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.

by Gentleman-Programming★ 9,221 (whole repo)18 skills

Skill · How-to guide

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

by jnMetaCode★ 8,541 (whole repo)20 skills

Skill · How-to guide

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.

by maxritter★ 2,149 (whole repo)7 skills

Skill · How-to guide

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.

by wanshuiyin★ 19,246 (whole repo)79 skills

Skill · How-to guide

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).

by Gentleman-Programming★ 2,667 (whole repo)12 skills

Skill · How-to guide

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.

by michaelshimeles★ 1,521 (whole repo)7 skills

Skill · How-to guide

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.

by hyhmrright★ 1,577 (whole repo)9 skills

Skill · How-to guide

delegate-skills

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

by amElnagdy★ 2,607 (whole repo)18 skills

Skill · How-to guide

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…

by redhat-et★ 2,544 (whole repo)19 skills

Skill · How-to guide

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

by zubair-trabzada★ 1,841 (whole repo)14 skills

Skill · How-to guide

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。

by tsingyuai★ 1,974 (whole repo)22 skills

Skill · How-to guide

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-…

by AgriciDaniel★ 2,762 (whole repo)33 skills

Skill · How-to guide

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.

by michael-denyer★ 4,346 (whole repo)54 skills

Skill · How-to guide

MCP servers matching your search

Front-End Checklist

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

by thedaviddiasWidely used★ 74.7K Stars for the whole repoUpdated 42 days ago

MCP · Connects a serviceRuns in the cloudTried by the PopNx team

Skylos

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

by duriantacoWidely used↓ 16.9K/wk★ 945Updated 8 months ago

MCP · Connects a serviceRuns on your computer

Mind Upload AI meta harness

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

by Voidborn-IndustriesGrowing↓ 5.5K/wk★ 3Updated today

MCP · Connects a serviceComputer or cloud

Concord MCP

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

by Get-Concord-AIGrowing↓ 991/wk★ 1.2KUpdated 5 days ago

MCP · Connects a serviceRuns on your computer

Trace MCP

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

by nikolai-vysotskyiGrowing↓ 4K/wk★ 204Updated today

MCP · Connects a serviceRuns on your computer

GitWarren

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

by klarluftEarly↓ 88/wk★ 127Updated 33 days ago

MCP · Connects a serviceRuns on your computer

See all MCP servers matching “code review” →