개발, 구현, 기능 개발, 기능 구현, 코딩 - Use when implementing features. Business logic writing, library utilization, and implementation pattern guides.
Implements features by writing production-ready code with a library-first approach. Triggers when you request feature development, business logic implementation, or ask to build specific functionality.
/plugin marketplace add aimskr/aims-toolkit/plugin install aims-toolkit@aims-toolkitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Write actual code:
Always search for existing solutions before implementing yourself
1. Search npm/PyPI/Maven for libraries
2. Evaluate SaaS/services
3. Review third-party APIs
4. Implement yourself only if nothing fits
| Feature | ❌ Custom Implementation | ✅ Use Library |
|---|---|---|
| Retry logic | Write from scratch | cockatiel, tenacity, resilience4j |
| Date handling | Direct manipulation | date-fns, pendulum, java.time |
| Validation | If statements | zod, pydantic, jakarta.validation |
| HTTP requests | Raw fetch/requests | axios, httpx, OkHttp |
| State management | Custom solution | zustand, Framework built-ins |
| Authentication | Custom solution | Auth0, Supabase Auth, Spring Security |
1. Understand requirements
↓
2. Search for existing solutions (npm, PyPI, Maven, services)
↓
3. Decide implementation approach
↓
4. Write tests (TDD recommended)
↓
5. Implement
↓
6. Refactor
Separate domain logic from data access by abstracting storage/retrieval operations.
Encapsulate business logic in service classes.
Centralize object creation logic.
code-conventions)"Every line of custom code is technical debt requiring maintenance, testing, and documentation."
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.