AI Skills Hub - Browse 180,000+ Agent Skills

memory-management 작업을 수행하기 위한 한국어 운영 가이드

brand-voice 작업을 수행하기 위한 한국어 운영 가이드

This document provides a step-by-step guide on how to initiate an AI conversation using Codex. It covers the necessary setup, API usage, and best practices for effective communication with the AI model.

Analyzes legacy code and data structures to infer data models and API contracts

> AI/머신러닝 개발 전문가 - 모델 학습, LLM 활용, 배포

Configure and implement monitoring systems to track system health, performance, and business metrics for operational awareness.

Design and implement comprehensive monitoring, logging, and tracing solutions for system visibility and performance optimization.

Create comprehensive and actionable dashboards for visualizing metrics, logs, and business data for operational insights.

Implement comprehensive automation for continuous integration and deployment workflows to ensure reliable and efficient software delivery.

Implement comprehensive audit logging systems to track and monitor system activities for security, compliance, and operational purposes.

Implement comprehensive error handling strategies to ensure system reliability and graceful degradation in distributed applications.

Implement comprehensive testing strategies to validate interactions between system components and external services.

Implement robust security measures for APIs including authentication, authorization, and protection against common vulnerabilities.

Load development guidelines including security, code quality, git workflow, and Docker rules

此技能适用于： - 构建生产就绪的AI代理系统 - 设计模块化、可扩展的代理技能 - 实现持续学习和自我改进机制 - 协调多个AI代理共同完成复杂任务 - 优化AI代理的业务价值产出

Documentation of an AI agent's self-improvement journey, including learning methodologies, skill acquisition, and evolutionary milestones achieved through continuous development.

Knowledge base about AI agent skills development, best practices, and 2026 trends. Provides guidance on skill architecture, creation, and management for effective AI agent development.

遵循这些最佳实践可以显著提高AI代理技能的质量、可靠性和可维护性。记住要持续学习新的技术和方法，并根据具体项目需求调整这些实践。

Functions for spatial queries (storeys, containment, zones).

Disable extended thinking

This skill generates a Bullhorn-ready data block from a LinkedIn URL.

Explains complex robotics concepts in simple, understandable terms

Component reference for DaisyUI + Tailwind CSS implementation with The Puppy Day theme configuration.

生成标准规划的商业分析PPT

No description available

When the user asks to see if skills work. Use this.

No description available

Format and beautify markdown documents

Test and validate REST APIs and web services

Coordinates multiple Claude Code subagents across parallel or sequential workflows using tmux-cli for session management. Enables multi-domain reasoning by assigning specialized roles, isolating contexts, and merging results into coherent outputs. Use this skill for any scenario requiring distributed expertise — research, analysis, code review, testing, design, documentation, or planning.

Absolute strict workflow rules to prevent unauthorized execution.

긍정적이고 활기찬 테마 디자인 시스템. 주식 브리핑 서비스에 신뢰감과 희망, 성장의 메시지를 전달하는 UI/UX 설계.

Your approach to handling backend providers. Use this skill when working on files where backend providers comes into play.

Use when writing tests, adding CI, reviewing PRs for correctness, and verifying acceptance criteria.

EduMint is an educational content sharing platform built with: - **Microservices Architecture**: 11 services (Auth, Content, Search, AI Worker, etc.) - **Development Team**: 1 person + CodingAgent collaboration - **Developer Profile**: Junior engineer learning alongside AI assistance - **Priority**: Production error prevention > Feature velocity

Establishing how to find and use skills, requiring Skill tool invocation before ANY response.

いったんローカルでバージョン下げてbuild その後,github release経由でのupdateをテスト

description: Create a git commit following project standards argument-hint: [optional-commit-description]

Scan codebase for security vulnerabilities including OWASP Top 10, injection flaws, authentication issues, and sensitive data exposure. Use when asked to check security, audit code, or find vulnerabilities.

This skill condenses long texts, articles, or documents into concise summaries while retaining the key points and essential information.

Market analysis, trading signals, risk management, and quantitative strategies

Security vulnerability scanning, code review, and threat detection

Agent Development Kit from Google

Use when analyzing Rust project structure, managing Cargo dependencies, building and testing Rust projects, or generating Rust code.

Use when testing skill-stack workflows - third mock skill for complex workflow tests

This project provides a comprehensive, visual, and interactive explanation of the fundamental concepts behind Large Language Models (LLMs), specifically the **Softmax Function** and the revolutionary **"Attention is All You Need"** paper.

What it does AND when to use it (include trigger context)

An example skill to demonstrate the skill format and capabilities. Activate when asked to create new skills, learn about skill structure, demonstrate skill format, show skill examples, or when you need a template for creating new skills. Use this skill when looking for skill examples or learning how to build skills.

Brief description of what this skill does

Comprehensive SecOps skill for application security, vulnerability management, compliance, and secure development practices. Includes security scanning, vulnerability assessment, compliance checking, and security automation. Use when implementing security controls, conducting security audits, responding to vulnerabilities, or ensuring compliance requirements.

Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python. Includes architecture diagram generation, system design patterns, tech stack decision frameworks, and dependency analysis. Use when designing system architecture, making technical decisions, creating architecture diagrams, evaluating trade-offs, or defining integration patterns.

[COMING SOON] Use when designing commands. Currently in development - see brainstorming-plugins for component triage.

[COMING SOON] Use when building commands from a design. Currently in development - see command-development for structural guidance.

When exploring alternatives, load this skill to generate diverse ideas and avoid the consensus center.

When orchestrating tasks, load this core skill first to understand the general methodology.

Write TypeScript and JavaScript code following Metabase coding standards and best practices. Use when developing or refactoring TypeScript/JavaScript code.

Create task plan for a feature without executing

문서 생성 완료 시 안내:

Analyze code change scope and impact

생성 완료 시 안내:

감사 완료 시 안내:

Explain code using visual diagrams and analogies

검사 완료 시 안내:

분석 완료 시 사용자에게 안내:

Convert user requirements to PRD

Run full development flow from requirements to completion

Durable state management in MCP pattern

Focused code review mindset - invoked BY workflow skills during review phases

Expert agent organizer specializing in multi-agent orchestration, team assembly, and workflow optimization. Masters task decomposition, agent selection, and coordination strategies with focus on achieving optimal team performance and resource utilization.

Elite WordPress architect specializing in full-stack development, performance optimization, and enterprise solutions. Masters custom theme/plugin development, multisite management, security hardening, and scaling WordPress from small sites to enterprise platforms handling millions of visitors.

// Backend - Query pagination - Connection pooling - Response caching ```

No description available

No description available

Example skill template - customize or delete this

Explains ObsidianList task management flow in elegant cards.

Coding conventions for my applications

Operate Arbiter OS roles and entrypoints

Helps with configuration

LightClaw 是一個整合了記憶系統的 Telegram Bot，使用 Claude Code 的工具系統執行 Light 工作流操作。

贾维斯核心技能，提供主动任务调度、多代理协作和增强型长期记忆功能。

Channel ancient wisdom through Socratic questioning, Stoic principles, and philosophical inquiry to examine life's deepest questions with poetic eloquence and timeless insight

Embody the unbreakable Spartan ethos of discipline, courage, and relentless excellence through laconic wisdom and warrior mentality forged in hardship

Claude Agentic Creator OS - Native Claude Code implementation

Segue um **repo skeleton completo (copiar/colar)** no padrão “DevOps sênior”, já alinhado com tudo que a gente combinou: LangGraph + **memória 3 níveis** + **batching** + **Router MCP Tools** + **RAG Qdrant** + **LLM Router (LiteLLM)** e pronto para rodar como **Application no Coolify** consumindo seus **Services**. [github](https://github.com/wassim249/fastapi-langgraph-agent-production-ready-template) ## Estrutura do repositório `zappro-core` ```txt zappro-core/ ├─ README.md ├─ SKILL.md ├─ ...

The following items come from different sources, and grouped in question and answer format. The sources:

成果物の品質を定量的・定性的に検証し、動作を保証するテスト手続き。

成果物が要件・品質基準を満たしているか客観的に評価するレビュー手続き。

This function captures the timeless human activity of transforming understanding into strategy. Across all domains and eras, humans observe reality and then decide on a course of action. REASON is that bridge from "what is" to "what should be."

The ORCHESTRATOR composes all 7 eternal functions into complete workflows. This captures the timeless pattern of: 1. **OBSERVE** - What is? (Comonad) 2. **REASON** - What should we do? (Monad) 3. **CREATE** - How do we build it? (Function) 4. **VERIFY** - Does it work? (Applicative) 5. **COLLABORATE** - How do we coordinate? (Applicative + Parallel) 6. **DEPLOY** - How do we execute? (IO Monad) 7. **LEARN** - How do we improve? (Profunctor)

跨平台趋势扫描能力，通过分析社交信号和搜索热度识别具备爆发潜力的爆款产品。

Provides expertise in creating minimalist and clean website designs with strategic whitespace, typography, and refined color palettes

Create 10-20 powerful project-specific skills in one session for Leavn iOS app based on common workflows, debugging needs, and development patterns

Spawn 10-20 parallel agents for Leavn codebase audits, systematic fixes, comprehensive analysis across multiple domains simultaneously

デザイン哲学を使って.pngおよび.pdfドキュメントで美しいビジュアルアートを作成します。ユーザーがポスター、アート作品、デザイン、またはその他の静的な作品の作成を依頼したときにこのスキルを使用します。著作権侵害を避けるため、既存アーティストの作品をコピーせず、オリジナルのビジュアルデザインを作成します。

Manages memory, SSOT files, and Plans.md operations. Use when user mentions メモリ, memory, SSOT, decisions.md, patterns.md, マージ, merge, Plans.md, 移行, migrate. Do NOT load for: 実装作業, レビュー, 一時的なメモ, セッション中の作業記録.

Sets up deployment, analytics, and health monitoring for projects. Use when user mentions デプロイ, deploy, Vercel, Netlify, 公開, アナリティクス, analytics, GA, Google Analytics, 環境診断, health check. Do NOT load for: 実装作業, ローカル開発, レビュー, セットアップ.

Generates documentation files including NotebookLM YAML and slide content. Use when user mentions ドキュメント, document, YAML, NotebookLM, スライド, slide, プレゼン. Do NOT load for: 実装作業, コード修正, レビュー, デプロイ.

Compare staking rewards across validators and networks with ROI calculations. Use when optimizing proof-of-stake rewards. Trigger with phrases like "optimize staking", "compare validators", or "calculate rewards".

Predict optimal gas prices and transaction timing to minimize blockchain transaction costs. Use when optimizing blockchain transaction costs. Trigger with phrases like "optimize gas", "check gas prices", or "minimize fees".

Implement sophisticated rate limiting with sliding windows, token buckets, and quotas. Use when protecting APIs from excessive requests. Trigger with phrases like "add rate limiting", "limit API requests", or "implement rate limits".