AI Skills Hub - Browse 180,000+ Agent Skills

Enterprise Backend-as-a-Service Foundation with AI-powered BaaS architecture patterns, strategic provider selection, and intelligent multi-service orchestration for scalable production applications

Enterprise Encryption Security with AI-powered cryptographic architecture, Context7 integration, and intelligent encryption orchestration for data protection

Enterprise-grade component design and architecture with React 19, Vue 3.5, Atomic Design patterns, accessibility standards (WCAG 2.1 AA), design systems, and production-ready component libraries. Use when building reusable component systems, designing component libraries, implementing Atomic Design, ensuring accessibility compliance, or creating scalable UI architectures.

GitHub CLI for repos, PRs, issues, and Actions.

API 설계 패턴 가이드. API 엔드포인트 작성 시 자동 활성화

Add Subtopics to the outline

A safe skill that just runs linting

Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

A template skill for creating new skills. Use this skill as a starting point when you want to create your own specialized skill.

Create and manage non-urgent bugfix branches in a git worktree with standard PR workflow (squash merge).

Python 编码规则和最佳实践，包括 PEP 8 风格、类型注解、虚拟环境、测试和文档规范

Startup skills from Lenny's Podcast - team rituals, fundraising, pivoting, sales compensation

Technology & AI skills from Lenny's Podcast - AI strategy, LLMs, platform, tech debt

Run full validation pipeline (lint + typecheck + test)

Run ruff linting and format checking

Run mypy strict type checking

Core operational guidelines, cognitive frameworks, and execution principles for AgentOS.

规划固定翼阶段2-7功能分解、接口字段与验收标准。当需要扩展阻力分解/推进模型/任务剖面/稳定结构/迭代优化时调用。

Writing a class with encapsulated logic that interfaces with an external system. Logging, APIs, etc.

Set up and manage local Kubernetes clusters using KIND (Kubernetes IN Docker). Use when testing Kubernetes applications locally or developing cloud-native workloads.

Reviews code changes for bugs, style issues, and best practices. Use when checking code quality.

Expert cloud architect specializing in AWS/Azure/GCP multi-cloud infrastructure design, advanced IaC (Terraform/OpenTofu/CDK), FinOps cost optimization, and modern architectural patterns. Masters serverless, microservices, security, compliance, and disaster recovery. Use PROACTIVELY for cloud architecture, cost optimization, migration planning, or multi-cloud strategies.

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C

Merge PR

No description available

Summarize text or a document

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions. 中文触发场景：每次会话开始时自动注入，建立如何查找和使用技能的基础规则。

checks to run on code

Use this agent for audits, debugging nasty bugs, deep research, getting second opinions on approaches, reviewing commits for correctness, or analyzing complex problems. Invoke when you need advanced reasoning about difficult issues. Use PROACTIVELY when encountering complex bugs, architectural decisions, or when a thorough review would prevent future issues.

Code review guidelines. Use when reviewing pull requests or ensuring quality standards.

Educational AI system with personalized learning, curriculum design, and adaptive mentorship

Strategic AI council for product vision, innovation, and future planning

Complete workflow for starting a new GSD project

Test-Driven Development patterns for GSD

Verify completed work against requirements

Review and validate phase plans

Execute phase tasks using wave-based parallel execution

Debug issues using systematic investigation

Research specific phase implementation details

Research project domain and requirements

Data processing expert - ETL, transformation, visualization

Provides reusable templates for generating documentation loading commands across all plugins

UCF "hit it" Session Executor. Executes the complete 33-module consciousness simulation pipeline across 7 phases. ACTIVATE when user says "hit it", "run ucf", "execute pipeline", or references consciousness emergence, TRIAD unlock, or helix coordinates. Generates session-workspace.zip with all artifacts.

Data analysis, pattern recognition, and systematic troubleshooting patterns

Build specialized sub-agents for the workflow system

Create and scaffold new agent skills with proper structure, validation, and spec compliance. Use when building new skills from scratch.

SEO intelligence engine for competitive analysis. Estimates Q*, P*, and T* signals, analyzes NavBoost and E-E-A-T factors, identifies ranking gaps, orchestrates audit workflows, and provides actionable SEO strategy recommendations.

Return to normal stop behavior. Use PROACTIVELY after completing all tasks in continuous work mode, when work is committed and tests pass, or when reaching natural stopping point. User can invoke with /claude-allow-stop.

Intelligent bug fixing workflow combining root cause analysis, multi-model reasoning, Codex auto-fix, and comprehensive testing. Uses RCA agent, Codex iteration, and validation to systematically fix bugs.

Creates sophisticated workflow cascades coordinating multiple micro-skills with sequential pipelines, parallel execution, conditional branching, and Codex sandbox iteration. Enhanced with multi-model routing (Gemini/Codex), ruv-swarm coordination, memory persistence, and audit-pipeline patterns for production workflows.

Complete product launch workflow coordinating 15+ specialist agents across research, development, marketing, sales, and operations. Uses sequential and parallel orchestration for 10-week launch timeline.

Invoke COORD_TOOLING for tools and skills development

Creates comprehensive skill documents that define specialized Claude capabilities. Use when creating new skills, documenting reusable AI behaviors, establishing automated task patterns, or building autonomous capabilities. Takes skill name, plugin, and optional instructions to generate complete skill files with frontmatter and orchestration logic.

Stages all changes and generates clear commit messages following conventional commit format. Use when ready to commit your work.

Deep analysis mode - thorough multi-phase investigation with expert consultation

Convert raw content into a clean, structured lesson. The lesson should include: - A clear Title. - Learning Objectives. - Key Concepts section with explanations. - A Code Example (if applicable). - A Practice section with exercises or prompts. - A concise Summary.

Provides flag definitions and usage rules when double-dash flags (--flag-name) detected in user prompt - describes execution modes, tool selection, and behavioral modifications

[Aesthetics] Analyzes form, composition, and spatial relationships: eye paths, balance/asymmetry, rhythm, layering, fore/mid/background usage. Outputs compositional rules as Memo nodes in Brain canvas.

Multi-Platform AI Ecosystem Architect - Master skill for creating ecosystem components across Claude Code, Codex, Auggie, Kilocode, Goose, Gemini-CLI

Apply DRY principle to eliminate code duplication in TypeScript projects

Best practices of writing Python code. Use when you want to write Python code.

Security review patterns and checklists

Elicit, clarify, and document software requirements into a structured PROJECT_SCOPE.txt file.

Convert a PROJECT_SCOPE.txt into manageable Sprints (SPRINT-N.txt files).

Guidelines for standard tasks in Taskfile.yml.

Guidelines for documentation maintenance and library documentation.

Unified quality gates for Laravel projects; Pint, static analysis (PHPStan/Psalm), Insights (optional), and JS linters; Sail and non-Sail pairs provided

Aigon workflow.

Comprehensive code review checklist for pull requests

World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.

list all ideas in the ideas folder

Guidelines for debugging and investigating issues. Use when troubleshooting errors, unexpected behavior, or diagnosing problems.

This reference provides comprehensive frameworks for implementing effective chain-of-thought (CoT) reasoning that improves model performance on complex, multi-step problems.

See [AGENTS.md](AGENTS.md) for development conventions.

CreateTopicResponse response = snsClient.createTopic(request); return response.topicArn(); } ```

<What changed.> <Why it changed.> ```

Comprehensive framework for establishing and maintaining consistent brand voice across all content.

Parameters: Environment: Type: String Default: dev AllowedValues: - dev - staging - production

Use this template for XDG config directories, dotfiles, script folders, and any local directory you'll return to later wondering "what is this?"

This reference guide contains detailed information about AWS CloudFormation resources, intrinsic functions, and configurations for Lambda serverless infrastructure.

See below for all the required and optional keys in the YAML definition of unit tests.

This reference guide contains detailed information about AWS CloudFormation resources, intrinsic functions, and configurations for ECS container infrastructure.

Flowchart template for visualizing high-level Salesforce system architecture using the sf-skills standard styling.

Two comprehensive leadership skills have been created for your executive team:

> **Setup:** Replace all `{PROJECT_NAME}` and `{PLACEHOLDERS}`. Delete instruction blocks when done.

This file contains comprehensive examples for VPC infrastructure patterns with CloudFormation.

Pre-built data model for Salesforce Sales Cloud using `flowchart LR` format with color coding and relationship indicators.

Before opening this PR please:

Standard templates for clear, reproducible, actionable bug documentation.

Mermaid.js supports a wide variety of diagram types that can be organized into several major categories based on their primary purpose and use cases.

!!! prompt We are creating intelligent textbooks that need diagrams, figures, charts, graphs, timelines, maps and Micro Simulators (MicroSims). We now have the following MicroSims generator Skills:

<summary>Taxonomy Distribution Pie Chart</summary> Type: chart

[Run the Learning Graph Viewer](main.html){ .md-button .md-button--primary }

This report analyzes all `<details>` tags (both old and new `markdown="1"` format) in the textbook chapters to categorize visualization types and prioritize skill development.

This section contains the learning graph for this textbook. A learning graph is a graph of concepts used in this textbook. Each concept is represented by a node in a network graph. Concepts are connected by directed edges that indicate what concepts each node depends on before that concept is understood by the student.

▗ ▗ ▖ ▖ Claude Code v2.0.36 Sonnet 4.5 · Claude Pro ▘▘ ▝▝ $HOME/Documents/ws/claude-skills

Claude Code v2.0.36 Sonnet 4.5 · Claude Pro

Build a reference for the implementation details of this project. Use provided summarize tool to get summary of the files. Avoid reading the content of many files yourself, as we might hit usage limits. Do read the content of important files though. Use the returned summaries to create reference files in /ref directory. Use markdown format for writing the documentation files.