Best Practices

Guide users through creating Agent Skills for Claude Code. Use when the user wants to create, write, author, or design a new Skill, or needs help with SKILL.md files, frontmatter, or skill structure.

A comprehensive guide for creating skills in Claude Code plugins. It covers skill anatomy, progressive disclosure principles, writing style requirements, and provides step-by-step workflows for planning, creating, validating, and iterating on skills.

A comprehensive guide to Test-Driven Development (TDD) that enforces the red-green-refactor cycle. Provides strict workflows for writing tests before implementation, common rationalizations to avoid, and testing anti-patterns to watch for when creating mocks or test utilities.

A comprehensive security review skill that provides checklists and code examples for secure coding practices. It covers secrets management, input validation, SQL injection prevention, XSS/CSRF protection, authentication, rate limiting, cloud IAM, logging, CI/CD pipeline security, and disaster recovery. This is purely educational documentation with no executable code.

A project-specific documentation skill that provides architecture overview, file structure guidance, code patterns for FastAPI and Next.js, testing requirements, and deployment workflows. It serves as a reference template for developers working on similar tech stacks with Supabase, Claude AI integration, and Google Cloud Run deployment.

A comprehensive reference guide for Go (Golang) development that covers idiomatic patterns, error handling, concurrency, interface design, package organization, and performance optimization. It serves as a best practices companion when writing, reviewing, or refactoring Go code.

This skill provides comprehensive coding standards and best practices for TypeScript, JavaScript, React, and Node.js development. It covers principles like KISS, DRY, and YAGNI, along with practical guidance on variable naming, error handling, async patterns, React components, API design, and testing standards.

This skill provides comprehensive guidance for writing production-grade Bash scripts using defensive programming patterns. It covers strict mode settings, error trapping, safe variable handling, structured logging, and idempotent script design to help developers create reliable shell scripts for CI/CD pipelines, system administration, and automation tasks.

Code Review Excellence is a comprehensive guide for conducting effective code reviews. It provides detailed methodologies for reviewing pull requests including checklists for security, performance, and testing, along with templates for feedback and techniques for giving constructive criticism while maintaining team morale.

A comprehensive guide to error handling patterns across Python, TypeScript, Rust, and Go. Covers exception hierarchies, Result types, circuit breakers, retry logic, and graceful degradation strategies for building resilient applications.

This skill helps teams create and maintain Architecture Decision Records (ADRs) - structured documents that capture the context, rationale, and consequences of significant technical decisions. It provides multiple templates (MADR, lightweight, Y-statement, deprecation, RFC-style), directory structure recommendations, review checklists, and integration with adr-tools CLI.

A comprehensive PostgreSQL database design guide that covers data types, indexing strategies, constraints, partitioning, JSONB usage, and performance optimization patterns. Includes AI agent definitions for database architecture and SQL expertise to help design scalable, maintainable database schemas.

Pre-implementation confidence assessment (≥90% required). Use before starting any implementation to verify readiness with duplicate check, architecture compliance, official docs verification, OSS references, and root cause identification.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

A comprehensive Ruby on Rails style guide based on DHH and 37signals conventions. It provides detailed patterns for controllers, models, frontend (Turbo/Stimulus), architecture, testing (Minitest/fixtures), and gem selection following the 'vanilla Rails is plenty' philosophy.

This skill provides expert guidance for creating, writing, and refining Claude Code Skills. It includes comprehensive documentation on skill structure, XML patterns, workflows, and best practices, along with templates for common skill types and workflows for auditing and verifying existing skills.

A comprehensive guide for writing Ruby gems following Andrew Kane's battle-tested patterns from gems like Searchkick, PgHero, and Chartkick. Covers entry point structure, Rails integration with ActiveSupport.on_load, class macro DSLs, database adapter patterns, Minitest testing, and gemspec best practices.

A comprehensive educational skill that teaches developers how to structure Claude Code plugins. It covers directory layout conventions, plugin.json manifest configuration, component organization (commands, agents, skills, hooks), the ${CLAUDE_PLUGIN_ROOT} portable path variable, and best practices with examples ranging from minimal to enterprise-grade plugins.

This skill teaches developers how to create autonomous agents for Claude Code plugins. It provides comprehensive documentation on agent file structure, YAML frontmatter fields, system prompt design patterns, and triggering conditions with concrete examples. Includes a bash validation script to check agent files for correct structure.

A comprehensive guide for modern Python development using uv, ruff, ty, and pytest. It covers project setup, dependency management, testing, security tooling (pre-commit hooks, secret detection, vulnerability scanning), and migration from legacy tools like pip, black, mypy, and pre-commit.

Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

A comprehensive reference guide for Vue 3 development with TypeScript. Covers vue-tsc strict template checking, Volar 3.0 migration, Pinia store mocking, Vue Router typed params, CSS modules, and various compiler options for catching type errors at compile time.

This skill provides comprehensive guidelines for shipping correct and complete web page metadata. It covers SEO essentials (titles, descriptions, canonical URLs, robots), social sharing (Open Graph, Twitter cards), icons/manifest, structured data (JSON-LD), and localization (lang, hreflang). Can be used to review existing metadata files for violations and suggest fixes.

A comprehensive security reference skill that provides OWASP security patterns, secrets management best practices, and automated security testing workflows. It includes code examples for input validation, authentication, JWT handling, password hashing, and security headers, along with GitHub Actions templates for CI/CD security scanning.

A comprehensive guide for building AI-first applications using LLMs. Covers project structure, typed LLM client patterns, prompt versioning, testing strategies (mocks, fixtures, evaluations), CI/CD integration for LLM tests, and cost/performance tracking. Focuses on the principle of using LLMs for logic and traditional code for infrastructure.

A methodology skill that helps prevent semantic code duplication by maintaining a CODE_INDEX.md capability index. It provides guidelines for checking existing code before writing new functions, documenting files and functions properly, and periodically auditing for duplicate functionality.

Base defines universal coding patterns, strict complexity limits (20 lines/function, 200 lines/file), and enforces Test-Driven Development workflows. It provides templates for atomic todos, bug tracking, session management, and automatically triggers iterative TDD loops for non-trivial tasks.

This skill provides comprehensive guidance for software development following Clean Architecture and Domain-Driven Design principles. It covers code style rules, naming conventions, anti-patterns to avoid, and emphasizes a library-first approach where developers should leverage existing solutions before writing custom code.