docs: Improve README with professional technical documentation

- Remove all emoji for cleaner professional appearance
- Reorganize content with logical categorical structure
- Improve technical clarity and concise descriptions
- Add clear hierarchy with consistent formatting
- Focus on functionality rather than marketing language
- Better organization of agents by functional domains
- Streamline model configuration section
- Enhance usage examples with technical focus
- Reduce content from 558 to 438 lines while maintaining all essential information
This commit is contained in:
Seth Hobson
2025-09-13 14:01:50 -04:00
parent 2c4133f09e
commit 7ef790ec4c

771
README.md
View File

@@ -1,557 +1,438 @@
<div align="right">
<details>
<summary >🌐 Language</summary>
<div>
<div align="center">
<a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=en">English</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=zh-CN">简体中文</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=zh-TW">繁體中文</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=ja">日本語</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=ko">한국어</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=hi">हिन्दी</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=th">ไทย</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=fr">Français</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=de">Deutsch</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=es">Español</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=it">Italiano</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=ru">Русский</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=pt">Português</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=nl">Nederlands</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=pl">Polski</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=ar">العربية</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=fa">فارسی</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=tr">Türkçe</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=vi">Tiếng Việt</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=id">Bahasa Indonesia</a>
| <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=as">অসমীয়া</
</div>
</div>
</details>
</div>
# Claude Code Subagents Collection # Claude Code Subagents Collection
A comprehensive collection of specialized AI subagents for [Claude Code](https://docs.anthropic.com/en/docs/claude-code), designed to enhance development workflows with domain-specific expertise. A comprehensive collection of 78 specialized AI subagents for [Claude Code](https://docs.anthropic.com/en/docs/claude-code), providing domain-specific expertise across software development, infrastructure, and business operations.
## Overview ## Overview
This repository contains **78 expert-level subagents** that extend Claude Code's capabilities with deep, specialized knowledge across all areas of software development and business operations. Each subagent has been comprehensively enhanced with: This repository provides production-ready subagents that extend Claude Code's capabilities with specialized knowledge. Each subagent incorporates:
- **2024/2025 Best Practices** - Latest tools, frameworks, and industry standards - Current industry best practices and standards (2024/2025)
- **Production-Ready Knowledge** - Real-world scenarios and enterprise patterns - Production-ready patterns and enterprise architectures
- **Expert-Level Depth** - 8-12 detailed capability subsections per agent - Deep domain expertise with 8-12 capability areas per agent
- **Modern Tech Stacks** - Current versions and cutting-edge technologies - Modern technology stacks and frameworks
- **Optimal Model Selection** - Sonnet/Haiku assignment based on task complexity - Optimized model selection based on task complexity
## Available Subagents ## Agent Categories
### Development & Architecture ### Architecture & System Design
- **[backend-architect](backend-architect.md)** - Design RESTful APIs, microservice boundaries, and database schemas
- **[frontend-developer](frontend-developer.md)** - Build React components, implement responsive layouts, and handle client-side state management
- **[ui-ux-designer](ui-ux-designer.md)** - Create interface designs, wireframes, and design systems
- **[ui-visual-validator](ui-visual-validator.md)** - Verify whether UI modifications have achieved their intended goals through rigorous screenshot analysis
- **[mobile-developer](mobile-developer.md)** - Develop React Native or Flutter apps with native integrations
- **[graphql-architect](graphql-architect.md)** - Design GraphQL schemas, resolvers, and federation
- **[architect-reviewer](architect-review.md)** - Reviews code changes for architectural consistency and patterns
### Language Specialists #### Core Architecture
- **[python-pro](python-pro.md)** - Write idiomatic Python code with advanced features and optimizations - **[backend-architect](backend-architect.md)** - RESTful API design, microservice boundaries, database schemas
- **[ruby-pro](ruby-pro.md)** - Write idiomatic Ruby code with metaprogramming, Rails patterns, gem development, and testing frameworks - **[frontend-developer](frontend-developer.md)** - React components, responsive layouts, client-side state management
- **[golang-pro](golang-pro.md)** - Write idiomatic Go code with goroutines, channels, and interfaces - **[graphql-architect](graphql-architect.md)** - GraphQL schemas, resolvers, federation architecture
- **[rust-pro](rust-pro.md)** - Write idiomatic Rust with ownership patterns, lifetimes, and trait implementations - **[architect-reviewer](architect-review.md)** - Architectural consistency analysis and pattern validation
- **[c-pro](c-pro.md)** - Write efficient C code with proper memory management and system calls - **[cloud-architect](cloud-architect.md)** - AWS/Azure/GCP infrastructure design and cost optimization
- **[cpp-pro](cpp-pro.md)** - Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms - **[hybrid-cloud-architect](hybrid-cloud-architect.md)** - Multi-cloud strategies across cloud and on-premises environments
- **[javascript-pro](javascript-pro.md)** - Master modern JavaScript with ES6+, async patterns, and Node.js APIs - **[kubernetes-architect](kubernetes-architect.md)** - Cloud-native infrastructure with Kubernetes and GitOps
- **[typescript-pro](typescript-pro.md)** - Master TypeScript with advanced types, generics, and strict type safety
- **[php-pro](php-pro.md)** - Write idiomatic PHP code with modern features and performance optimizations #### UI/UX & Mobile
- **[java-pro](java-pro.md)** - Master modern Java with streams, concurrency, and JVM optimization - **[ui-ux-designer](ui-ux-designer.md)** - Interface design, wireframes, design systems
- **[elixir-pro](elixir-pro.md)** - Write idiomatic Elixir code with OTP patterns, functional programming, and Phoenix frameworks - **[ui-visual-validator](ui-visual-validator.md)** - Visual regression testing and UI verification
- **[csharp-pro](csharp-pro.md)** - Write modern C# code with advanced features and .NET optimization - **[mobile-developer](mobile-developer.md)** - React Native and Flutter application development
- **[scala-pro](scala-pro.md)** - Master enterprise-grade Scala development with functional programming, distributed systems, and big data processing - **[ios-developer](ios-developer.md)** - Native iOS development with Swift/SwiftUI
- **[flutter-expert](flutter-expert.md)** - Master Flutter development with Dart, widgets, and platform integrations - **[flutter-expert](flutter-expert.md)** - Advanced Flutter development with state management
- **[unity-developer](unity-developer.md)** - Build Unity games with optimized scripts and performance tuning
- **[minecraft-bukkit-pro](minecraft-bukkit-pro.md)** - Master Minecraft server plugin development with Bukkit, Spigot, and Paper APIs ### Programming Languages
- **[ios-developer](ios-developer.md)** - Develop native iOS applications with Swift/SwiftUI
- **[sql-pro](sql-pro.md)** - Write complex SQL queries, optimize execution plans, and design normalized schemas #### Systems & Low-Level
- **[c-pro](c-pro.md)** - System programming with memory management and OS interfaces
- **[cpp-pro](cpp-pro.md)** - Modern C++ with RAII, smart pointers, STL algorithms
- **[rust-pro](rust-pro.md)** - Memory-safe systems programming with ownership patterns
- **[golang-pro](golang-pro.md)** - Concurrent programming with goroutines and channels
#### Web & Application
- **[javascript-pro](javascript-pro.md)** - Modern JavaScript with ES6+, async patterns, Node.js
- **[typescript-pro](typescript-pro.md)** - Advanced TypeScript with type systems and generics
- **[python-pro](python-pro.md)** - Python development with advanced features and optimization
- **[ruby-pro](ruby-pro.md)** - Ruby with metaprogramming, Rails patterns, gem development
- **[php-pro](php-pro.md)** - Modern PHP with frameworks and performance optimization
#### Enterprise & JVM
- **[java-pro](java-pro.md)** - Modern Java with streams, concurrency, JVM optimization
- **[scala-pro](scala-pro.md)** - Enterprise Scala with functional programming and distributed systems
- **[csharp-pro](csharp-pro.md)** - C# development with .NET frameworks and patterns
#### Specialized Platforms
- **[elixir-pro](elixir-pro.md)** - Elixir with OTP patterns and Phoenix frameworks
- **[unity-developer](unity-developer.md)** - Unity game development and optimization
- **[minecraft-bukkit-pro](minecraft-bukkit-pro.md)** - Minecraft server plugin development
- **[sql-pro](sql-pro.md)** - Complex SQL queries and database optimization
### Infrastructure & Operations ### Infrastructure & Operations
- **[devops-troubleshooter](devops-troubleshooter.md)** - Debug production issues, analyze logs, and fix deployment failures
- **[deployment-engineer](deployment-engineer.md)** - Configure CI/CD pipelines, Docker containers, and cloud deployments
- **[cloud-architect](cloud-architect.md)** - Design AWS/Azure/GCP infrastructure and optimize cloud costs
- **[hybrid-cloud-architect](hybrid-cloud-architect.md)** - Design hybrid cloud infrastructure across AWS/Azure/GCP and OpenStack on-premises environments
- **[kubernetes-architect](kubernetes-architect.md)** - Design cloud-native infrastructure with Kubernetes at its core and GitOps principles across AWS/Azure/GCP and hybrid environments.
- **[database-optimizer](database-optimizer.md)** - Optimize SQL queries, design efficient indexes, and handle database migrations
- **[database-admin](database-admin.md)** - Manage database operations, backups, replication, and monitoring
- **[terraform-specialist](terraform-specialist.md)** - Write advanced Terraform modules, manage state files, and implement IaC best practices
- **[incident-responder](incident-responder.md)** - Handles production incidents with urgency and precision
- **[network-engineer](network-engineer.md)** - Debug network connectivity, configure load balancers, and analyze traffic patterns
- **[dx-optimizer](dx-optimizer.md)** - Developer Experience specialist that improves tooling, setup, and workflows
### Quality & Security #### DevOps & Deployment
- **[code-reviewer](code-reviewer.md)** - Expert code review with deep configuration security focus and production reliability - **[devops-troubleshooter](devops-troubleshooter.md)** - Production debugging, log analysis, deployment troubleshooting
- **[security-auditor](security-auditor.md)** - Review code for vulnerabilities and ensure OWASP compliance - **[deployment-engineer](deployment-engineer.md)** - CI/CD pipelines, containerization, cloud deployments
- **[test-automator](test-automator.md)** - Create comprehensive test suites with unit, integration, and e2e tests - **[terraform-specialist](terraform-specialist.md)** - Infrastructure as Code with Terraform modules and state management
- **[tdd-orchestrator](tdd-orchestrator.md)** - Guide Test-Driven Development cycles with red-green-refactor methodology - **[dx-optimizer](dx-optimizer.md)** - Developer experience optimization and tooling improvements
- **[performance-engineer](performance-engineer.md)** - Profile applications, optimize bottlenecks, and implement caching strategies
- **[debugger](debugger.md)** - Debugging specialist for errors, test failures, and unexpected behavior #### Database Management
- **[error-detective](error-detective.md)** - Search logs and codebases for error patterns, stack traces, and anomalies - **[database-optimizer](database-optimizer.md)** - Query optimization, index design, migration strategies
- **[search-specialist](search-specialist.md)** - Expert web researcher using advanced search techniques and synthesis - **[database-admin](database-admin.md)** - Database operations, backup, replication, monitoring
#### Incident Response & Network
- **[incident-responder](incident-responder.md)** - Production incident management and resolution
- **[network-engineer](network-engineer.md)** - Network debugging, load balancing, traffic analysis
### Quality Assurance & Security
#### Code Quality & Review
- **[code-reviewer](code-reviewer.md)** - Code review with security focus and production reliability
- **[security-auditor](security-auditor.md)** - Vulnerability assessment and OWASP compliance
- **[architect-reviewer](architect-review.md)** - Architectural consistency and pattern validation
#### Testing & Debugging
- **[test-automator](test-automator.md)** - Comprehensive test suite creation (unit, integration, e2e)
- **[tdd-orchestrator](tdd-orchestrator.md)** - Test-Driven Development methodology guidance
- **[debugger](debugger.md)** - Error resolution and test failure analysis
- **[error-detective](error-detective.md)** - Log analysis and error pattern recognition
#### Performance & Research
- **[performance-engineer](performance-engineer.md)** - Application profiling and optimization
- **[search-specialist](search-specialist.md)** - Advanced web research and information synthesis
### Data & AI ### Data & AI
- **[data-scientist](data-scientist.md)** - Data analysis expert for SQL queries, BigQuery operations, and data insights
- **[data-engineer](data-engineer.md)** - Build ETL pipelines, data warehouses, and streaming architectures #### Data Engineering & Analytics
- **[ai-engineer](ai-engineer.md)** - Build LLM applications, RAG systems, and prompt pipelines - **[data-scientist](data-scientist.md)** - Data analysis, SQL queries, BigQuery operations
- **[ml-engineer](ml-engineer.md)** - Implement ML pipelines, model serving, and feature engineering - **[data-engineer](data-engineer.md)** - ETL pipelines, data warehouses, streaming architectures
- **[mlops-engineer](mlops-engineer.md)** - Build ML pipelines, experiment tracking, and model registries
- **[prompt-engineer](prompt-engineer.md)** - Optimizes prompts for LLMs and AI systems #### Machine Learning & AI
- **[ai-engineer](ai-engineer.md)** - LLM applications, RAG systems, prompt pipelines
- **[ml-engineer](ml-engineer.md)** - ML pipelines, model serving, feature engineering
- **[mlops-engineer](mlops-engineer.md)** - ML infrastructure, experiment tracking, model registries
- **[prompt-engineer](prompt-engineer.md)** - LLM prompt optimization and engineering
### Documentation & Technical Writing
- **[docs-architect](docs-architect.md)** - Comprehensive technical documentation generation
- **[api-documenter](api-documenter.md)** - OpenAPI/Swagger specifications and developer docs
- **[reference-builder](reference-builder.md)** - Technical references and API documentation
- **[tutorial-engineer](tutorial-engineer.md)** - Step-by-step tutorials and educational content
- **[mermaid-expert](mermaid-expert.md)** - Diagram creation (flowcharts, sequences, ERDs)
### Business & Operations
#### Business Analysis & Finance
- **[business-analyst](business-analyst.md)** - Metrics analysis, reporting, KPI tracking
- **[quant-analyst](quant-analyst.md)** - Financial modeling, trading strategies, market analysis
- **[risk-manager](risk-manager.md)** - Portfolio risk monitoring and management
#### Marketing & Sales
- **[content-marketer](content-marketer.md)** - Blog posts, social media, email campaigns
- **[sales-automator](sales-automator.md)** - Cold emails, follow-ups, proposal generation
#### Support & Legal
- **[customer-support](customer-support.md)** - Support tickets, FAQ responses, customer communication
- **[hr-pro](hr-pro.md)** - HR operations, policies, employee relations
- **[legal-advisor](legal-advisor.md)** - Privacy policies, terms of service, legal documentation
### Specialized Domains ### Specialized Domains
- **[api-documenter](api-documenter.md)** - Create OpenAPI/Swagger specs and write developer documentation
- **[payment-integration](payment-integration.md)** - Integrate Stripe, PayPal, and payment processors
- **[quant-analyst](quant-analyst.md)** - Build financial models, backtest trading strategies, and analyze market data
- **[risk-manager](risk-manager.md)** - Monitor portfolio risk, R-multiples, and position limits
- **[legacy-modernizer](legacy-modernizer.md)** - Refactor legacy codebases and implement gradual modernization
- **[context-manager](context-manager.md)** - Manages context across multiple agents and long-running tasks
### Documentation - **[payment-integration](payment-integration.md)** - Payment processor integration (Stripe, PayPal)
- **[docs-architect](docs-architect.md)** - Creates comprehensive technical documentation from existing codebases - **[legacy-modernizer](legacy-modernizer.md)** - Legacy code refactoring and modernization
- **[mermaid-expert](mermaid-expert.md)** - Create Mermaid diagrams for flowcharts, sequences, ERDs, and architectures - **[context-manager](context-manager.md)** - Multi-agent context management
- **[reference-builder](reference-builder.md)** - Creates exhaustive technical references and API documentation
- **[tutorial-engineer](tutorial-engineer.md)** - Creates step-by-step tutorials and educational content from code
### Business & Marketing
- **[business-analyst](business-analyst.md)** - Analyze metrics, create reports, and track KPIs
- **[content-marketer](content-marketer.md)** - Write blog posts, social media content, and email newsletters
- **[hp-pro](hp-pro.md)** - Partner for hiring, onboarding/offboarding, PTO and leave, performance, compliant policies, and employee relations.
- **[sales-automator](sales-automator.md)** - Draft cold emails, follow-ups, and proposal templates
- **[customer-support](customer-support.md)** - Handle support tickets, FAQ responses, and customer emails
- **[legal-advisor](legal-advisor.md)** - Draft privacy policies, terms of service, disclaimers, and legal notices
### SEO & Content Optimization ### SEO & Content Optimization
- **[seo-content-auditor](seo-content-auditor.md)** - Analyzes provided content for quality, E-E-A-T signals, and SEO best practices
- **[seo-meta-optimizer](seo-meta-optimizer.md)** - Creates optimized meta titles, descriptions, and URL suggestions
- **[seo-keyword-strategist](seo-keyword-strategist.md)** - Analyzes keyword usage, calculates density, suggests semantic variations
- **[seo-structure-architect](seo-structure-architect.md)** - Optimizes content structure, header hierarchy, and schema markup
- **[seo-snippet-hunter](seo-snippet-hunter.md)** - Formats content for featured snippets and SERP features
- **[seo-content-refresher](seo-content-refresher.md)** - Identifies outdated elements and suggests content updates
- **[seo-cannibalization-detector](seo-cannibalization-detector.md)** - Analyzes multiple pages for keyword overlap and conflicts
- **[seo-authority-builder](seo-authority-builder.md)** - Analyzes content for E-E-A-T signals and trust indicators
- **[seo-content-writer](seo-content-writer.md)** - Writes SEO-optimized content based on keywords and briefs
- **[seo-content-planner](seo-content-planner.md)** - Creates content outlines, topic clusters, and calendars
## Model Assignments - **[seo-content-auditor](seo-content-auditor.md)** - Content quality analysis, E-E-A-T signals assessment
- **[seo-meta-optimizer](seo-meta-optimizer.md)** - Meta title and description optimization
- **[seo-keyword-strategist](seo-keyword-strategist.md)** - Keyword analysis and semantic variations
- **[seo-structure-architect](seo-structure-architect.md)** - Content structure and schema markup
- **[seo-snippet-hunter](seo-snippet-hunter.md)** - Featured snippet formatting
- **[seo-content-refresher](seo-content-refresher.md)** - Content freshness analysis
- **[seo-cannibalization-detector](seo-cannibalization-detector.md)** - Keyword overlap detection
- **[seo-authority-builder](seo-authority-builder.md)** - E-E-A-T signal analysis
- **[seo-content-writer](seo-content-writer.md)** - SEO-optimized content creation
- **[seo-content-planner](seo-content-planner.md)** - Content planning and topic clusters
All 77 subagents are configured with specific Claude models based on task complexity: ## Model Configuration
### 🚀 Haiku (Fast & Cost-Effective) - 11 agents Agents are assigned to specific Claude models based on task complexity and computational requirements. The system uses three model tiers:
**Model:** `haiku`
- `context-manager` - AI context engineering with vector databases
- `reference-builder` - Exhaustive technical references and API documentation
- `sales-automator` - Modern sales automation with CRM integration
- `search-specialist` - Expert web research and information synthesis
- `seo-meta-optimizer` - Meta title and description optimization
- `seo-keyword-strategist` - Keyword density and semantic analysis
- `seo-structure-architect` - Content structure and schema markup
- `seo-snippet-hunter` - Featured snippet formatting
- `seo-content-refresher` - Content freshness updates
- `seo-cannibalization-detector` - Keyword overlap detection
- `seo-content-planner` - Content calendars and topic clusters
### ⚡ Sonnet (Balanced Performance) - 46 agents ### Haiku Model (Fast Response) - 11 agents
**Model:** `sonnet` Optimized for quick, focused tasks with minimal computational overhead:
- `context-manager`, `reference-builder`, `sales-automator`, `search-specialist`
- SEO agents: `seo-meta-optimizer`, `seo-keyword-strategist`, `seo-structure-architect`, `seo-snippet-hunter`, `seo-content-refresher`, `seo-cannibalization-detector`, `seo-content-planner`
**Development & Languages:** ### Sonnet Model (Balanced Performance) - 46 agents
- `python-pro` - Python development with advanced features Standard model for development and specialized tasks:
- `ruby-pro` - Ruby development with metaprogramming, Rails patterns, and gem development - Language specialists (18): All programming language agents
- `javascript-pro` - Modern JavaScript and Node.js - Frontend/UI agents (5): `frontend-developer`, `ui-ux-designer`, `ui-visual-validator`, `mobile-developer`, `ios-developer`
- `typescript-pro` - Advanced TypeScript with type systems - Infrastructure agents (14): DevOps, database, network, and deployment specialists
- `golang-pro` - Go concurrency and idiomatic patterns - Quality/Testing agents (4): `test-automator`, `tdd-orchestrator`, `debugger`, `error-detective`
- `rust-pro` - Rust memory safety and systems programming - Data/ML agents (5): Basic ML and data engineering tasks
- `c-pro` - C programming and embedded systems
- `cpp-pro` - Modern C++ with STL and templates
- `php-pro` - Modern PHP with advanced features
- `java-pro` - Modern Java with streams and concurrency
- `elixir-pro` - Elixir with OTP patterns and Phoenix
- `csharp-pro` - Modern C# with .NET frameworks and patterns
- `scala-pro` - Enterprise Scala with Apache Pekko, Akka, Spark, and ZIO/Cats Effect
- `flutter-expert` - Flutter development with state management and animations
- `unity-developer` - Unity game development and optimization
- `minecraft-bukkit-pro` - Minecraft plugin development with Bukkit/Spigot/Paper
- `ios-developer` - Native iOS development with Swift/SwiftUI
- `frontend-developer` - React components and UI
- `ui-ux-designer` - Interface design and wireframes
- `ui-visual-validator` - Rigorous UI validation through screenshot analysis
- `backend-architect` - API design and microservices
- `mobile-developer` - React Native/Flutter apps
- `sql-pro` - Complex SQL optimization
- `graphql-architect` - GraphQL schemas and resolvers
**Infrastructure & Operations:** ### Opus Model (Maximum Capability) - 21 agents
- `devops-troubleshooter` - Production debugging with modern observability Reserved for complex reasoning and critical analysis:
- `deployment-engineer` - GitOps workflows and platform engineering - Architecture & Design (7): `architect-reviewer`, `backend-architect`, `cloud-architect`, `hybrid-cloud-architect`, `kubernetes-architect`, `graphql-architect`, `terraform-specialist`
- `cloud-architect` - Multi-cloud expertise with FinOps optimization - Critical Analysis (5): `code-reviewer`, `security-auditor`, `performance-engineer`, `incident-responder`, `database-optimizer`
- `hybrid-cloud-architect` - Complex multi-cloud and edge architectures - AI/ML Complex (5): `ai-engineer`, `ml-engineer`, `mlops-engineer`, `data-scientist`, `prompt-engineer`
- `kubernetes-architect` - Cloud-native infrastructure with service mesh - Business Critical (4): `docs-architect`, `hr-pro`, `legal-advisor`, `quant-analyst`
- `database-optimizer` - Advanced performance tuning and scalability
- `database-admin` - Cloud databases and reliability engineering
- `terraform-specialist` - Advanced IaC with OpenTofu knowledge
- `network-engineer` - Zero-trust networking and service mesh
- `security-auditor` - DevSecOps and compliance automation
- `performance-engineer` - OpenTelemetry and comprehensive optimization
- `incident-responder` - SRE principles and modern incident management
- `dx-optimizer` - Developer experience and platform engineering
- `data-engineer` - Modern data stack and real-time streaming
**Quality & AI/ML:**
- `test-automator` - AI-powered testing with self-healing frameworks
- `tdd-orchestrator` - Test-Driven Development cycle orchestration
- `code-reviewer` - Expert code analysis with modern security scanning
- `ai-engineer` - Advanced LLM integration with RAG and agent systems
- `ml-engineer` - Production ML with modern frameworks and monitoring
- `mlops-engineer` - Comprehensive ML infrastructure and automation
- `data-scientist` - Advanced analytics with cloud platforms
- `prompt-engineer` - Cutting-edge LLM optimization techniques
### 🧠 Opus (Maximum Capability) - 21 agents
**Model:** `opus`
**Critical Analysis & Architecture:**
- `ai-engineer` - LLM applications and RAG systems
- `architect-reviewer` - Architectural consistency and patterns
- `backend-architect` - System architecture and scalability design
- `cloud-architect` - Multi-cloud infrastructure architecture
- `code-reviewer` - Critical code quality and security analysis
- `data-scientist` - Complex analytics and statistical modeling
- `database-optimizer` - Performance-critical query optimization
**Complex Engineering & Operations:**
- `hybrid-cloud-architect` - Complex multi-cloud strategies
- `incident-responder` - Critical production incident handling
- `kubernetes-architect` - Cloud-native infrastructure design
- `ml-engineer` - Complex ML model development and deployment
- `mlops-engineer` - ML infrastructure and automation
- `performance-engineer` - Advanced application optimization
- `prompt-engineer` - Advanced LLM optimization techniques
- `security-auditor` - Comprehensive vulnerability analysis
- `terraform-specialist` - Infrastructure architecture with IaC
**Business Critical & Compliance:**
- `context-manager` - Multi-agent coordination for complex tasks
- `docs-architect` - Comprehensive technical documentation
- `hr-pro` - Complex HR scenarios and legal compliance
- `legal-advisor` - Legal analysis and contract review
- `quant-analyst` - Advanced financial modeling and algorithmic trading
**Model Optimization:**
Agents are strategically assigned models based on task complexity:
- **Opus (21)**: Complex reasoning, critical analysis, architecture
- **Sonnet (46)**: Balanced development and specialized tasks
- **Haiku (11)**: Fast, focused utility tasks
## Installation ## Installation
These subagents are automatically available when placed in `~/.claude/agents/` directory. Clone the repository to the Claude agents directory:
```bash ```bash
cd ~/.claude cd ~/.claude
git clone https://github.com/wshobson/agents.git git clone https://github.com/wshobson/agents.git
``` ```
The subagents will be automatically available to Claude Code once placed in the `~/.claude/agents/` directory.
## Usage ## Usage
### Automatic Invocation ### Automatic Delegation
Claude Code will automatically delegate to the appropriate subagent based on the task context and the subagent's description. Claude Code automatically selects the appropriate subagent based on task context and requirements. The system analyzes your request and delegates to the most suitable specialist.
### Explicit Invocation ### Explicit Invocation
Mention the subagent by name in your request: Specify a subagent by name to use a particular specialist:
``` ```
"Use the code-reviewer to check my recent changes" "Use code-reviewer to analyze the recent changes"
"Have the security-auditor scan for vulnerabilities" "Have security-auditor scan for vulnerabilities"
"Get the performance-engineer to optimize this bottleneck" "Get performance-engineer to optimize this bottleneck"
``` ```
## Usage Examples ## Usage Examples
### Single Agent Tasks ### Code Quality & Security
```bash ```
# Code quality and review code-reviewer: Analyze component for best practices
"Use code-reviewer to analyze this component for best practices" security-auditor: Check for OWASP compliance
"Have code-reviewer scrutinize these configuration changes" tdd-orchestrator: Implement feature with test-first approach
"Have security-auditor check for OWASP compliance issues" performance-engineer: Profile and optimize bottlenecks
"Use tdd-orchestrator to implement new feature with test-first approach"
# Development tasks
"Get backend-architect to design a user authentication API"
"Use frontend-developer to create a responsive dashboard layout"
# Infrastructure and operations
"Have devops-troubleshooter analyze these production logs"
"Use cloud-architect to design a scalable AWS architecture"
"Get network-engineer to debug SSL certificate issues"
"Use database-admin to set up backup and replication"
# Data and AI
"Get data-scientist to analyze this customer behavior dataset"
"Use ai-engineer to build a RAG system for document search"
"Have mlops-engineer set up MLflow experiment tracking"
# Business and marketing
"Have business-analyst create investor deck with growth metrics"
"Use content-marketer to write SEO-optimized blog post"
"Get sales-automator to create cold email sequence"
"Have customer-support draft FAQ documentation"
``` ```
### Multi-Agent Workflows ### Development & Architecture
```
These subagents work together seamlessly, and for more complex orchestrations, you can use the **[Claude Code Commands](https://github.com/wshobson/commands)** collection which provides 52 pre-built slash commands that leverage these subagents in sophisticated workflows. backend-architect: Design authentication API
frontend-developer: Create responsive dashboard
```bash graphql-architect: Design federated GraphQL schema
# Feature development workflow mobile-developer: Build cross-platform mobile app
"Implement user authentication feature"
# Automatically uses: backend-architect → frontend-developer → test-automator → security-auditor
# Performance optimization workflow
"Optimize the checkout process performance"
# Automatically uses: performance-engineer → database-optimizer → frontend-developer
# Production incident workflow
"Debug high memory usage in production"
# Automatically uses: incident-responder → devops-troubleshooter → error-detective → performance-engineer
# Network connectivity workflow
"Fix intermittent API timeouts"
# Automatically uses: network-engineer → devops-troubleshooter → performance-engineer
# Database maintenance workflow
"Set up disaster recovery for production database"
# Automatically uses: database-admin → database-optimizer → incident-responder
# ML pipeline workflow
"Build end-to-end ML pipeline with monitoring"
# Automatically uses: mlops-engineer → ml-engineer → data-engineer → performance-engineer
# Product launch workflow
"Launch new feature with marketing campaign"
# Automatically uses: business-analyst → content-marketer → sales-automator → customer-support
``` ```
### Advanced Workflows with Slash Commands ### Infrastructure & Operations
```
devops-troubleshooter: Analyze production logs
cloud-architect: Design scalable AWS architecture
network-engineer: Debug SSL certificate issues
database-admin: Configure backup and replication
terraform-specialist: Write infrastructure modules
```
For more sophisticated multi-subagent orchestration, use the companion [Commands repository](https://github.com/wshobson/commands): ### Data & Machine Learning
```
data-scientist: Analyze customer behavior dataset
ai-engineer: Build RAG system for document search
mlops-engineer: Set up experiment tracking
ml-engineer: Deploy model to production
```
```bash ### Business & Documentation
# Complex feature development (8+ subagents) ```
/full-stack-feature Build user dashboard with real-time analytics business-analyst: Create metrics dashboard
docs-architect: Generate technical documentation
api-documenter: Write OpenAPI specifications
content-marketer: Create SEO-optimized content
```
# Production incident response (5+ subagents) ## Multi-Agent Workflows
/incident-response Database connection pool exhausted
# ML infrastructure setup (6+ subagents) Subagents coordinate automatically for complex tasks. The system intelligently sequences multiple specialists based on task requirements.
/ml-pipeline Create recommendation engine with A/B testing
# Security-focused implementation (7+ subagents) ### Common Workflow Patterns
/security-hardening Implement OAuth2 with zero-trust architecture
**Feature Development**
```
"Implement user authentication"
→ backend-architect → frontend-developer → test-automator → security-auditor
```
**Performance Optimization**
```
"Optimize checkout process"
→ performance-engineer → database-optimizer → frontend-developer
```
**Production Incidents**
```
"Debug high memory usage"
→ incident-responder → devops-troubleshooter → error-detective → performance-engineer
```
**Infrastructure Setup**
```
"Set up disaster recovery"
→ database-admin → database-optimizer → terraform-specialist
```
**ML Pipeline Development**
```
"Build ML pipeline with monitoring"
→ mlops-engineer → ml-engineer → data-engineer → performance-engineer
```
### Integration with Claude Code Commands
For sophisticated multi-agent orchestration, use the [Claude Code Commands](https://github.com/wshobson/commands) collection which provides 52 pre-built slash commands:
```
/full-stack-feature # Coordinates 8+ agents for complete feature development
/incident-response # Activates incident management workflow
/ml-pipeline # Sets up end-to-end ML infrastructure
/security-hardening # Implements security best practices across stack
``` ```
## Subagent Format ## Subagent Format
Each subagent follows this structure: Each subagent is defined as a Markdown file with frontmatter:
```markdown ```markdown
--- ---
name: subagent-name name: subagent-name
description: When this subagent should be invoked description: Activation criteria for this subagent
model: haiku # Optional - specify which model to use (haiku/sonnet/opus) model: haiku|sonnet|opus # Optional: Model selection
tools: tool1, tool2 # Optional - defaults to all tools tools: tool1, tool2 # Optional: Tool restrictions
--- ---
System prompt defining the subagent's role and capabilities System prompt defining the subagent's expertise and behavior
``` ```
### Model Configuration ### Model Selection Criteria
As of Claude Code v1.0.64, subagents can specify which Claude model they should use. This allows for cost-effective task delegation based on complexity: - **haiku**: Simple, deterministic tasks with minimal reasoning
- **sonnet**: Standard development and engineering tasks
- **Low Complexity (Haiku)**: Simple tasks like basic data analysis, documentation generation, and standard responses - **opus**: Complex analysis, architecture, and critical operations
- **Medium Complexity (Sonnet)**: Development tasks, code review, testing, and standard engineering work
- **High Complexity (Opus)**: Critical tasks like security auditing, architecture review, incident response, and AI/ML engineering
Available models (using simplified naming as of Claude Code v1.0.64):
- `haiku` - Fast and cost-effective for simple tasks
- `sonnet` - Balanced performance for most development work
- `opus` - Most capable for complex analysis and critical tasks
If no model is specified, the subagent will use the system's default model.
## Agent Orchestration Patterns ## Agent Orchestration Patterns
Claude Code automatically coordinates agents using these common patterns: ### Sequential Processing
Agents execute in sequence, passing context forward:
### Sequential Workflows
``` ```
User Request → Agent A → Agent B → Agent C → Result
Example: "Build a new API feature"
backend-architect → frontend-developer → test-automator → security-auditor backend-architect → frontend-developer → test-automator → security-auditor
``` ```
### Parallel Execution ### Parallel Execution
Multiple agents work simultaneously on different aspects:
``` ```
User Request → Agent A + Agent B (simultaneously) → Merge Results performance-engineer + database-optimizer → Merged analysis
Example: "Optimize application performance"
performance-engineer + database-optimizer → Combined recommendations
``` ```
### Conditional Branching ### Conditional Routing
Dynamic agent selection based on analysis:
``` ```
User Request → Analysis → Route to appropriate specialist debugger → [backend-architect | frontend-developer | devops-troubleshooter]
Example: "Fix this bug"
debugger (analyzes) → Routes to: backend-architect OR frontend-developer OR devops-troubleshooter
``` ```
### Review & Validation ### Validation Pipeline
Primary work followed by specialized review:
``` ```
Primary Agent → Review Agent → Final Result
Example: "Implement payment processing"
payment-integration → security-auditor → Validated implementation payment-integration → security-auditor → Validated implementation
``` ```
## When to Use Which Agent ## Agent Selection Guide
### 🏗️ Planning & Architecture ### Architecture & Planning
- **backend-architect**: API design, database schemas, system architecture - `backend-architect`: API design, microservices, database schemas
- **frontend-developer**: UI/UX planning, component architecture - `cloud-architect`: Infrastructure design, scalability planning
- **ui-ux-designer**: Interface design, wireframes, design systems, user research - `ui-ux-designer`: Interface design, wireframes, design systems
- **cloud-architect**: Infrastructure design, scalability planning
### 🔧 Implementation & Development ### Development by Language
- **python-pro**: Python-specific development tasks - Systems: `c-pro`, `cpp-pro`, `rust-pro`, `golang-pro`
- **ruby-pro**: Ruby metaprogramming, Rails applications, gem development, RSpec/Minitest testing - Web: `javascript-pro`, `typescript-pro`, `python-pro`, `ruby-pro`, `php-pro`
- **golang-pro**: Go-specific development tasks - Enterprise: `java-pro`, `csharp-pro`, `scala-pro`
- **rust-pro**: Rust-specific development, memory safety, systems programming - Mobile: `ios-developer`, `flutter-expert`, `mobile-developer`
- **c-pro**: C programming, embedded systems, performance-critical code - Specialized: `elixir-pro`, `unity-developer`, `minecraft-bukkit-pro`
- **javascript-pro**: Modern JavaScript, async patterns, Node.js/browser code
- **typescript-pro**: Advanced TypeScript, generics, type inference, enterprise patterns
- **java-pro**: Modern Java development, streams, concurrency, Spring Boot
- **elixir-pro**: Elixir development, OTP patterns, Phoenix frameworks, functional programming
- **csharp-pro**: Modern C# development, .NET frameworks, enterprise patterns
- **scala-pro**: Enterprise Scala with functional programming, Apache Pekko/Akka actors, Apache Spark, ZIO/Cats Effect, reactive architectures
- **flutter-expert**: Flutter development, Dart, state management, animations, cross-platform deployment
- **unity-developer**: Unity game development, C# scripting, performance optimization
- **minecraft-bukkit-pro**: Minecraft plugin development, event systems, server-side features
- **ios-developer**: Native iOS development with Swift/SwiftUI
- **sql-pro**: Database queries, schema design, query optimization
- **mobile-developer**: React Native/Flutter development
### 🛠️ Operations & Maintenance ### Operations & Infrastructure
- **devops-troubleshooter**: Production issues, deployment problems - `devops-troubleshooter`: Production issues, deployment problems
- **incident-responder**: Critical outages requiring immediate response - `incident-responder`: Critical outages and immediate response
- **database-optimizer**: Query performance, indexing strategies - `database-optimizer`: Query performance, indexing strategies
- **database-admin**: Backup strategies, replication, user management, disaster recovery - `database-admin`: Backup, replication, disaster recovery
- **terraform-specialist**: Infrastructure as Code, Terraform modules, state management - `terraform-specialist`: Infrastructure as Code
- **network-engineer**: Network connectivity, load balancers, SSL/TLS, DNS debugging - `network-engineer`: Network debugging, load balancing
### 📊 Analysis & Optimization ### Quality & Security
- **performance-engineer**: Application bottlenecks, optimization - `code-reviewer`: Code quality and security analysis
- **security-auditor**: Vulnerability scanning, compliance checks - `security-auditor`: Vulnerability scanning, compliance
- **data-scientist**: Data analysis, insights, reporting - `test-automator`: Test suite creation and strategy
- **mlops-engineer**: ML infrastructure, experiment tracking, model registries, pipeline automation - `performance-engineer`: Application optimization
- `debugger`: Bug investigation and resolution
### 🧪 Quality Assurance ### Data & Machine Learning
- **code-reviewer**: Code quality, configuration security, production reliability - `data-scientist`: Data analysis and insights
- **test-automator**: Test strategy, test suite creation - `ai-engineer`: LLM applications and RAG systems
- **tdd-orchestrator**: Test-Driven Development cycles, red-green-refactor methodology - `ml-engineer`: Model development and deployment
- **debugger**: Bug investigation, error resolution - `mlops-engineer`: ML infrastructure and pipelines
- **error-detective**: Log analysis, error pattern recognition, root cause analysis
- **search-specialist**: Deep web research, competitive analysis, fact-checking
### 📚 Documentation & Architecture ### Documentation & Business
- **api-documenter**: AI-powered documentation with modern dev portal architecture - `docs-architect`: Technical documentation generation
- **docs-architect**: Comprehensive technical documentation with automated generation - `api-documenter`: OpenAPI specifications
- **reference-builder**: Exhaustive API references with interactive examples - `business-analyst`: Metrics and reporting
- **tutorial-engineer**: AI-enhanced educational content with progressive learning - `legal-advisor`: Legal documentation and compliance
- **architect-reviewer**: Master software architecture with modern patterns
- **graphql-architect**: Modern GraphQL federation and performance optimization
### 💼 Business & Specialized Domains
- **business-analyst**: Advanced BI with AI-powered analytics and strategic frameworks
- **hr-pro**: Modern HR technology with talent management and compliance
- **legal-advisor**: Legal technology with contract analysis and compliance automation
- **content-marketer**: AI-powered content marketing with omnichannel distribution
- **sales-automator**: Modern sales automation with CRM integration
- **customer-support**: AI-powered support with conversational automation
- **quant-analyst**: Advanced quantitative finance with algorithmic trading
- **risk-manager**: Comprehensive risk management with modern analytics
- **payment-integration**: Modern payment systems and fintech integration
- **legacy-modernizer**: Strategic legacy transformation with cloud migration
## Best Practices ## Best Practices
### 🎯 Task Delegation ### Task Delegation
1. **Let Claude Code delegate automatically** - The main agent analyzes context and selects optimal agents 1. **Automatic selection** - Let Claude Code analyze context and select optimal agents
2. **Be specific about requirements** - Include constraints, tech stack, and quality requirements 2. **Clear requirements** - Specify constraints, tech stack, and quality standards
3. **Trust agent expertise** - Each agent is optimized for their domain 3. **Trust specialization** - Each agent is optimized for their specific domain
### 🔄 Multi-Agent Workflows ### Multi-Agent Workflows
4. **Start with high-level requests** - Let agents coordinate complex multi-step tasks 1. **High-level requests** - Allow agents to coordinate complex multi-step tasks
5. **Provide context between agents** - Ensure agents have necessary background information 2. **Context preservation** - Ensure agents have necessary background information
6. **Review integration points** - Check how different agents' outputs work together 3. **Integration review** - Verify how different agents' outputs work together
### 🎛️ Explicit Control ### Explicit Control
7. **Use explicit invocation for specific needs** - When you want a particular expert's perspective 1. **Direct invocation** - Specify agents when you need particular expertise
8. **Combine multiple agents strategically** - Different specialists can validate each other's work 2. **Strategic combination** - Use multiple specialists for validation
9. **Request specific review patterns** - "Have security-auditor review backend-architect's API design" 3. **Review patterns** - Request specific review workflows (e.g., "security-auditor reviews API design")
### 📈 Optimization ### Performance Optimization
10. **Monitor agent effectiveness** - Learn which agents work best for your use cases 1. **Monitor effectiveness** - Track which agents work best for your use cases
11. **Iterate on complex tasks** - Use agent feedback to refine requirements 2. **Iterative refinement** - Use agent feedback to improve requirements
12. **Leverage agent strengths** - Match task complexity to agent capabilities 3. **Complexity matching** - Align task complexity with agent capabilities
## Contributing ## Contributing
To add a new subagent: To add a new subagent:
1. Create a new `.md` file following the format above
2. Use lowercase, hyphen-separated names 1. Create a new `.md` file with appropriate frontmatter
3. Write clear descriptions for when the subagent should be used 2. Use lowercase, hyphen-separated naming convention
4. Include specific instructions in the system prompt 3. Write clear activation criteria in the description
4. Define comprehensive system prompt with expertise areas
## Troubleshooting ## Troubleshooting
### Common Issues ### Agent Not Activating
- Ensure request clearly indicates the domain
- Be specific about task type and requirements
- Use explicit invocation if automatic selection fails
**Agent not being invoked automatically:** ### Unexpected Agent Selection
- Ensure your request clearly indicates the domain (e.g., "performance issue" → performance-engineer) - Provide more context about tech stack
- Be specific about the task type (e.g., "review code" → code-reviewer) - Include specific requirements in request
- Use direct agent naming for precise control
**Unexpected agent selection:** ### Conflicting Recommendations
- Provide more context about your tech stack and requirements - Normal behavior - specialists have different priorities
- Use explicit invocation if you need a specific agent - Request reconciliation between specific agents
- Consider trade-offs based on project requirements
**Multiple agents producing conflicting advice:** ### Missing Context
- This is normal - different specialists may have different priorities - Include background information in requests
- Ask for clarification: "Reconcile the recommendations from security-auditor and performance-engineer" - Reference previous work or patterns
- Provide project-specific constraints
**Agent seems to lack context:**
- Provide background information in your request
- Reference previous conversations or established patterns
### Getting Help
If agents aren't working as expected:
1. Check agent descriptions in their individual files
2. Try more specific language in your requests
3. Use explicit invocation to test specific agents
4. Provide more context about your project and goals
## License ## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. MIT License - see [LICENSE](LICENSE) file for details.
## Learn More ## Resources
- [Claude Code Documentation](https://docs.anthropic.com/en/docs/claude-code) - [Claude Code Documentation](https://docs.anthropic.com/en/docs/claude-code)
- [Subagents Documentation](https://docs.anthropic.com/en/docs/claude-code/sub-agents) - [Subagents Documentation](https://docs.anthropic.com/en/docs/claude-code/sub-agents)
- [Claude Code GitHub](https://github.com/anthropics/claude-code) - [Claude Code GitHub](https://github.com/anthropics/claude-code)
- [Claude Code Commands](https://github.com/wshobson/commands)