Agent skill
software-architecture
Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
Install this agent skill to your Project
npx add-skill https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/development/software-architecture
SKILL.md
Software Architecture Development Skill
This skill provides guidance for quality focused software development and architecture. It is based on Clean Architecture and Domain Driven Design principles.
Code Style Rules
General Principles
- Early return pattern: Always use early returns when possible, over nested conditions for better readability
- Avoid code duplication through creation of reusable functions and modules
- Decompose long (more than 80 lines of code) components and functions into multiple smaller components and functions. If they cannot be used anywhere else, keep it in the same file. But if file longer than 200 lines of code, it should be split into multiple files.
- Use arrow functions instead of function declarations when possible
Best Practices
Library-First Approach
- ALWAYS search for existing solutions before writing custom code
- Check npm for existing libraries that solve the problem
- Evaluate existing services/SaaS solutions
- Consider third-party APIs for common functionality
- Use libraries instead of writing your own utils or helpers. For example, use
cockatielinstead of writing your own retry logic. - When custom code IS justified:
- Specific business logic unique to the domain
- Performance-critical paths with special requirements
- When external dependencies would be overkill
- Security-sensitive code requiring full control
- When existing solutions don't meet requirements after thorough evaluation
Architecture and Design
- Clean Architecture & DDD Principles:
- Follow domain-driven design and ubiquitous language
- Separate domain entities from infrastructure concerns
- Keep business logic independent of frameworks
- Define use cases clearly and keep them isolated
- Naming Conventions:
- AVOID generic names:
utils,helpers,common,shared - USE domain-specific names:
OrderCalculator,UserAuthenticator,InvoiceGenerator - Follow bounded context naming patterns
- Each module should have a single, clear purpose
- AVOID generic names:
- Separation of Concerns:
- Do NOT mix business logic with UI components
- Keep database queries out of controllers
- Maintain clear boundaries between contexts
- Ensure proper separation of responsibilities
Anti-Patterns to Avoid
- NIH (Not Invented Here) Syndrome:
- Don't build custom auth when Auth0/Supabase exists
- Don't write custom state management instead of using Redux/Zustand
- Don't create custom form validation instead of using established libraries
- Poor Architectural Choices:
- Mixing business logic with UI components
- Database queries directly in controllers
- Lack of clear separation of concerns
- Generic Naming Anti-Patterns:
utils.jswith 50 unrelated functionshelpers/misc.jsas a dumping groundcommon/shared.jswith unclear purpose
- Remember: Every line of custom code is a liability that needs maintenance, testing, and documentation
Code Quality
- Proper error handling with typed catch blocks
- Break down complex logic into smaller, reusable functions
- Avoid deep nesting (max 3 levels)
- Keep functions focused and under 50 lines when possible
- Keep files focused and under 200 lines of code when possible
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
behavioral-modes
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Didn't find tool you were looking for?