Prototyp · Vorschau: alle Server aus der offiziellen Registry, alle 30 Minuten synchronisiert. Mit Google anmelden, um Bewertungen zu schreiben.Prototyp · alle 30 Min. aktualisiert
PopNx MCPMCP-Server für alle, die KI nutzen · in einfachen Worten erklärt

Agent Skills

Anweisungssammlungen (Skills), die einer KI eine Arbeitsweise beibringen, aus GitHub-Repos mit 200+ Sternen und echter SKILL.md · keine MCP-Server

Was einen Skill von MCP unterscheidet →

19 Skills passen zu „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.

von alibaba★ 51.962 (whole repo)2 Skills

Skill · Anleitung

academic-research-skills-codex

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

von Imbad0202★ 14.5981 Skills

Skill · Anleitung

academic-research-skills

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

von Imbad0202★ 57.019 (whole repo)4 Skills

Skill · Anleitung

tuicr

a code review TUI with vim keybindings

von agavra★ 3.6091 Skills

Skill · Anleitung

claude-skills-llm-council

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

von aiwithremy★ 3.0741 Skills

Skill · Anleitung

elephant-goldfish-model

Open-source plugin for designing and reviewing software with agents

von google★ 19.685 (whole repo)7 Skills

Skill · Anleitung

code-review-skill

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

von awesome-skills★ 2.2671 Skills

Skill · Anleitung

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.

von RevylAI★ 2.474 (whole repo)2 Skills

Skill · Anleitung

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.

von backnotprop★ 11.771 (whole repo)10 Skills

Skill · Anleitung

react-doctor

Your agent writes bad React. This catches it

von millionco★ 15.139 (whole repo)14 Skills

Skill · Anleitung

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.

von Gentleman-Programming★ 9.221 (whole repo)18 Skills

Skill · Anleitung

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

von jnMetaCode★ 8.541 (whole repo)20 Skills

Skill · Anleitung

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.

von maxritter★ 2.149 (whole repo)7 Skills

Skill · Anleitung

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.

von wanshuiyin★ 19.246 (whole repo)79 Skills

Skill · Anleitung

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).

von Gentleman-Programming★ 2.667 (whole repo)12 Skills

Skill · Anleitung

delegate-skills

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

von amElnagdy★ 2.607 (whole repo)18 Skills

Skill · Anleitung

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…

von redhat-et★ 2.544 (whole repo)19 Skills

Skill · Anleitung

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-…

von AgriciDaniel★ 2.762 (whole repo)33 Skills

Skill · Anleitung

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.

von michael-denyer★ 4.346 (whole repo)54 Skills

Skill · Anleitung

Passende MCP-Server

Front-End Checklist

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

von thedaviddiasWeit verbreitet★ 74.747 Sterne des ganzen ReposAktualisiert vor 42 Tagen

MCP · Verbindet einen DienstLäuft in der CloudVom PopNx-Team ausprobiert

Skylos

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

von duriantacoWeit verbreitet↓ 16.891/Wo.★ 945Aktualisiert vor 8 Monaten

MCP · Verbindet einen DienstLäuft auf deinem Computer

Mind Upload AI meta harness

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

von Voidborn-IndustriesWachsend↓ 5460/Wo.★ 3Aktualisiert heute

MCP · Verbindet einen DienstComputer oder Cloud

Concord MCP

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

von Get-Concord-AIWachsend↓ 991/Wo.★ 1155Aktualisiert vor 5 Tagen

MCP · Verbindet einen DienstLäuft auf deinem Computer

Trace MCP

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

von nikolai-vysotskyiWachsend↓ 4003/Wo.★ 204Aktualisiert heute

MCP · Verbindet einen DienstLäuft auf deinem Computer

GitWarren

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

von klarluftAm Anfang↓ 88/Wo.★ 127Aktualisiert vor 33 Tagen

MCP · Verbindet einen DienstLäuft auf deinem Computer

Alle MCP-Server zu „code review“ ansehen →