LLM & Agents

Alfred SuperAgent의 필수 규칙을 정의합니다. November 2025 enterprise standard 기반. 3-Layer architecture, 4-Step workflow, Agent-first paradigm, Skill invocation rules, AskUserQuestion patterns, TRUST 5 quality gates, TAG chain integrity, commit message standards. 사용: 워크플로우 규칙 검증, 품질 게이트 확인, MoAI-ADK 표준 준수, 아키텍처 규칙 검증.

Agent Factory master skill for intelligent Claude Code agent generation.Includes requirement analysis, domain detection, model selection, template system,validation framework, and advanced features. Contains algorithms, workflows, and patterns.

Enterprise LLM Fine-Tuning with LoRA, QLoRA, and PEFT techniques

Claude Code Agents system, task delegation patterns, and multi-agent coordination. Use when creating custom agents, managing agent workflows, or implementing task delegation.

Enterprise-grade technical document translation system for Korean↔English↔Japanese with OpenAI GPT-4 integration, code block preservation, glossary management, and bilingual review workflows. Optimized for technical books and documentation under 50 pages with comprehensive quality validation including code preservation, terminology consistency, bilingual review, and automated testing.

Complete guide to MoAI-ADK agents, delegation patterns, and agent orchestration for intelligent task distribution

Enterprise Mermaid diagramming skill for Claude Code using MCP Playwright rendering

Handle comprehensive project language and user setup workflows including language selection, agent prompt configuration, user profiles, team settings, and domain selection

Claude Code subagent lifecycle management including initialization, execution, error handling, and cleanup patterns. Covers full lifecycle from startup through resource cleanup.

Claude Code Markdown integration, documentation generation, and structured content patterns. Use when generating documentation, managing markdown content, or creating structured reports.

Claude Code Skills management, skill creation patterns, and knowledge capsule architecture. Use when creating custom Skills, managing skill libraries, or designing knowledge systems.

Claude Code Commands system, workflow orchestration, and command-line interface patterns. Use when creating custom commands, managing workflows, or implementing CLI interfaces.

Core rules for Alfred SuperAgent - 3-Layer Architecture, 4-Step Workflow, Agent-First

Claude Code settings management, preference customization, and user experience optimization. Use when customizing Claude Code behavior, managing user preferences, or optimizing development experience.

Vector icon libraries ecosystem guide covering 10+ major libraries with 200K+ icons, including React Icons (35K+), Lucide (1000+), Tabler Icons (5900+), Iconify (200K+), Heroicons, Phosphor, and Radix Icons with implementation patterns, decision trees, and best practices.

Claude Code hook execution strategies, timing models, sequencing patterns, and orchestration for automated workflow enforcement. Covers all hook types and execution timing models.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Claude Code permission configuration and policy management strategies for enterprise security. Covers permission modes, tool access control, whitelist/blacklist patterns, and enterprise deployment best practices.

Claude Code Commands system, workflow orchestration, and command-line interface patterns. Use when creating custom commands, managing workflows, or implementing CLI interfaces.

Vector icon libraries ecosystem guide covering 10+ major libraries with 200K+ icons, including React Icons (35K+), Lucide (1000+), Tabler Icons (5900+), Iconify (200K+), Heroicons, Phosphor, and Radix Icons with implementation patterns, decision trees, and best practices.