AI Skills Hub - Browse 180,000+ Agent Skills

This is a new rule

Use when user asks to review code for quality and security issues.

Use when testing valid model configuration

Use when needing to design or optimize the customer journey from awareness to purchase, maximize conversion rates, and build a sustainable monetization system

Helps you submit a pull request to the project in a manner that follows the projects contributing guidelines and therefore will increase its chance of being accepted.

Multi-AI engineering loop orchestrating Claude, Codex, and Gemini for comprehensive validation. USE WHEN (1) mission-critical features requiring multi-perspective validation, (2) complex architectural decisions needing diverse AI viewpoints, (3) security-sensitive code requiring deep analysis, (4) user explicitly requests multi-AI review or triple-AI loop. DO NOT USE for simple features or single-file changes. MODES - Triple-AI (full coverage), Dual-AI Codex-Claude (security/logic), Dual-AI Gemini-Claude (UX/creativity).

Generate architecture overview documentation from codebase analysis. Uses tree-sitter-analyzer for precise code structure extraction. Triggers: architecture overview, project structure, module diagram.

Generate domain documentation from codebase analysis - entities, glossary, relationships. Triggers: domain model, entity diagram, ドメインモデル, 用語集, glossary, ubiquitous language.

向助手发出协助请求，适用中华文化理解、中文古文理解、中国特色作品创作、小红书与抖音的宣发文案编写、编写测试用例、信息检索等任务场景，同时也是其他专家助手的强力替补与协助，可以作为大部分认为的备选候补方案。

スキルライブラリの管理、検索、一覧表示、構造検証を行うコマンド群を提供するスキル。 スキルの発見、品質検証、使用状況の記録を効率化し、スキルエコシステムの健全性を維持する。

Start the Astro development server for web development

Fast path for small bug fixes: reproduce, fix, verify

Restructure code without changing behavior: safety net first, then transform

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.

Automated compliance checks, continuous monitoring, reporting frameworks for GDPR, HIPAA, SOC2, and CCPA compliance.

Google Cloud Vector Search 2.0 introduction and implementation guide

GPT-5 prompting best practices for creating AI agent prompts in OpenPromo codebase when using ai sdk or agents, or in general writing llm prompts.

Git workflow best practices for commits, rebasing, conflict resolution, and branch management. Use when working with git operations, creating commits, resolving conflicts, or managing branches.

Activates the Project Manager to break down a feature request into tasks. Use when planning new features or organizing work.

Use when the user needs technical research, architecture validation, documentation generation, or code review. Default is read-only mode, but can enable auto-approve (-y) for code changes.

Organization & continuity system - orientation, captures, tasks, knowledge

Iterative planning with Planner, Architect, and Critic until consensus

Parse and validate configuration files

Coordinate Holo output formatting and telemetry so 0102, Qwen, and Gemma receive exactly what they need.

Unicode Daemon Monitor Skill

Qwen Cleanup Strategist (Prototype)

Gemma Noise Detector (Prototype)

翻译中的中文内容，在中文内容下方添加分割线并写入英文翻译，如果英文内容存在，则更新它。

Use when testing unreachable skills

Use when greeting users

Use when testing valid context and agent configuration

Use when testing custom agent validation

Use when analyzing code quality

6-month content calendar, multi-platform SNS strategy, and YouTube channel optimization. Use when creating content strategies or growing social media presence.

API design and implementation command

Test-Driven Development workflow with comprehensive red-green-refactor cycle automation

Personal project milestone template - Simple, focused, productive

Team collaboration milestone template - Simple coordination without complexity

Comprehensive security vulnerability scanning and hardening workflow

Routes legacy documentation commands to the unified documentation generator while preserving backward compatibility.

Orchestrate integration tests with service dependency management and cross-system validation

Synthesize a complete prompt by combining next.md with your arguments

Trade and track stocks, ETFs, commodities, bonds, and forex. Unified portfolio across all asset classes.

Skill template with Bun Shell pattern. Copy this folder to create new skills.

Enterprise SSRF Security Protection with AI-powered request validation, Context7 integration, and intelligent URL filtering for web application security

Reports on the newest news on a specific topic. Use when the user is asking about news, recent events or advancements

Researches topics in-depth and generates comprehensive summaries and references. Use when trying to deeply understand a topic or use a new framework.

指定したプラグインを有効化する。「プラグインを有効化」「〇〇をオンにして」「〇〇を有効にして」「プラグインを有効に」「〇〇を使えるようにして」「プラグインをオンに」「〇〇を有効化して」などで起動。claude plugin enable コマンドを使用して有効化。

指定したプラグインを無効化する。「プラグインを無効化」「〇〇をオフにして」「〇〇を無効にして」「プラグインを無効に」「〇〇を止めて」「プラグインをオフに」「〇〇を無効化して」などで起動。claude plugin disable コマンドを使用して無効化。

Creates OpenCode agents in project folders for opencode serve operations. Use when you need to autonomously create specialized OpenCode agents that will be used by OpenCode serve, not by Claude directly.

Enterprise Frontend Development with AI-powered modern architecture, Context7 integration, and intelligent component orchestration for scalable user interfaces

Comprehensive change tracking and audit logging system that monitors file modifications, code changes, and project evolution. Use when tracking project history, maintaining audit trails, analyzing development patterns, or when detailed change documentation is required for compliance and team collaboration.. Enhanced with Context7 MCP for up-to-date documentation.

REST API and GraphQL design with OpenAPI 3.1, authentication, versioning, and rate limiting.

Enterprise Configuration Management with AI-powered settings architecture, Context7 integration, and intelligent configuration orchestration for scalable applications

Claude Code Markdown integration, documentation generation, and structured content patterns. Use when generating documentation, managing markdown content, or creating structured reports.

Linked list data structures and operations

Stack and queue data structures with applications

Run a full cognitive analysis on your Claude Code usage

Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.

Maximum parallel execution with multiple custom droids

Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback, identifying issues, or ensuring code quality standards.

Design & engineering skills from Lenny's Podcast - design systems, reviews, engineering culture

Advanced PM skills from Lenny's Podcast - product taste, systems thinking, behavioral design, coaching

Curated skill combinations for specific roles - founder, PM, manager, growth leader, and more. Each playbook combines essential Lenny skills.

Run pytest test suite

Deterministic directory state inspection. Converts natural language intent into an explicit, auditable plan and executes bounded enumeration/stat/ranking with optional git status mapping.

CRITICAL - Required security_risk parameter for ALL tool calls. Without this parameter your actions WILL FAIL.

Helps with deployment tasks and scripts

Initialize Flutter projects for AI assisted workflow. Triggers on: init flutter.

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

Master modern business analysis with AI-powered analytics, real-time dashboards, and data-driven insights. Build comprehensive KPI frameworks, predictive models, and strategic recommendations. Use PROACTIVELY for business intelligence or strategic analysis.

Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without constant human guidance. The challenge isn't making them capable - it's making them reliable. Every extra decision multiplies failure probability. This skill covers agent loops (ReAct, Plan-Execute), goal decomposition, reflection patterns, and production reliability. Key insight: compounding error rates kill autonomous agents. A 95% success rate per step drops to 60% b

Use when working with comprehensive review full review

No description available

OODER A2UI Skill 是一个提供图生代码功能的技能，其主要特点包括：

> *"Intelligence that doesn't flow is intelligence that dies."*

Git integration reference for GSD

Multi-repository analysis and research specialist

Helpers to discover, rank, and invoke repository symbols from natural language with minimal context.

LLM integration patterns for Claude, GPT, Gemini, and Ollama. Activate for AI API integration, prompt engineering, token management, extended thinking, and multi-model orchestration.

Expert SuperClaude prompt engineering assistant that analyzes user needs and crafts optimal prompts using the full SuperClaude framework - commands, flags, personas, MCP servers, wave orchestration, parallel execution patterns, continuous execution directives, and the new PM Agent orchestration system with PDCA cycles and Serena memory integration.

DevOps scripting with Bash, Python, and Go for automation, tooling, and infrastructure management

Git version control, branching strategies, GitHub/GitLab workflows, and collaborative development

Distributed tracing with Jaeger, OpenTelemetry, and observability platforms for microservices insights

Generates clean, runnable ROS 2, Gazebo, Isaac Sim, and VLA code for humanoid robotics

Creates 4 high-quality MCQs with full explanations and correct answer marked

Summarizes any chapter into 6–8 bullet points with bold key terms

[Code Quality] Scans codebase for technical debt indicators: code smells, complexity hotspots, duplications, outdated patterns, and anti-patterns. Use when starting a refactoring session to identify what needs attention.

Use this to read the MUI (Material UI) documentation.

Example skill showing the basic structure and format for custom skills

Convert plan.md into taskmaster PRD format in .taskmaster/docs

Generate and expand taskmaster tasks from PRDs with complexity analysis

Generate comprehensive pytest test files for Python using the test-generator-framework

Guidelines for application structure and dependency management.

Guidelines for dependency injection patterns.

Comprehensive frontend development skill for building modern, performant web applications using ReactJS, NextJS, TypeScript, Tailwind CSS. Includes component scaffolding, performance optimization, bundle analysis, and UI best practices. Use when developing frontend features, optimizing performance, implementing UI/UX designs, managing state, or reviewing frontend code.

Comprehensive backend development skill for building scalable backend systems using NodeJS, Express, Go, Python, Postgres, GraphQL, REST APIs. Includes API scaffolding, database optimization, security implementation, and performance tuning. Use when designing APIs, optimizing database queries, implementing business logic, handling authentication/authorization, or reviewing backend code.

move plan to completed, merge to develop, cleanup branch

Reading package lists... Done Building dependency tree... Done Reading state information... Done The following packages were automatically installed and are no longer required: libbasicusageenvironment1 libc++1-16 libc++abi1-16 libcamera0.3 libgroupsock8 liblivemedia77 libunwind-16 libwlroots12 linux-headers-6.6.51+rpt-common-rpi linux-headers-6.6.51+rpt-rpi-2712 linux-headers-6.6.51+rpt-rpi-v8 linux-image-6.6.51+rpt-rpi-2712 linux-image-6.6.51+rpt-rpi-v8 linux-kbuild-6.6.51+rpt python3-v4l2 ...

This file tracks MicroSims that need screenshots captured.