LLM 與 Agent

Analyzes Claude Code chat history to identify optimization opportunities, track Skills/Commands utilization, detect repetitive patterns, measure token usage, and recommend improvements. This skill should be used when reviewing productivity, identifying underutilized resources, or finding patterns that could become new Skills.

Expert in ALL computational collage composition: photo mosaics, grid layouts, scrapbook/journal styles, magazine editorial, vision boards, mood boards, social media collages, memory walls, abstract/generative arrangements, and art-historical techniques (Hockney joiners, Dadaist photomontage, Surrealist assemblage, Rauschenberg combines). Masters edge-based assembly, Poisson blending, optimal transport color harmonization, and aesthetic optimization. Activate on 'collage', 'photo mosaic', 'grid layout', 'scrapbook', 'vision board', 'mood board', 'photo wall', 'magazine layout', 'Hockney', 'joiner', 'photomontage'. NOT for simple image editing (use native-app-designer), generating new images (use Stability AI), single photo enhancement (use photo-composition-critic), or basic image similarity search (use clip-aware-embeddings).

Guide for implementing Specification-Driven Development in any project using GitHub's spec-kit. Use when users want to start spec-driven development, need to initialize spec-kit in a project, or want guidance on the spec-kit workflow (constitution, specify, clarify, plan, tasks, implement). Covers installation, initialization, and step-by-step prompts for each phase.

Apifox 生成器核心工具（由 Agent 内部使用，不对外暴露）

Hyper-opinionated Claude agent for building production-ready Next.js apps with DynamoDB. Enforces best practices, eliminates technology debates, and focuses on shipping functional apps fast. Use when building full-stack applications with Next.js 15 App Router and AWS DynamoDB.

Analyze disk usage across directories, identify large/old directories, and generate storage reports. Use when you need to find directories consuming disk space, identify candidates for cleanup (directories older than X days AND larger than Y MB), sort results by size, or generate disk usage reports. Supports filtering by age and size, automatic sorting by disk space, and file-based report generation.

Quality vectors for code comments

Create and manage Claude Code plugins including commands, agents, skills, hooks, and MCP servers. This skill should be used when building new plugins, debugging plugin issues, understanding plugin structure, or working with plugin marketplaces.

Provides FastMCP templates, patterns, and reference materials. Use when building MCP servers, implementing FastMCP tools/resources/prompts, or working with MCP protocol compliance.

This skill guides creating Claude skills—modular packages that extend capabilities with specialized knowledge and workflows. Use when creating new skills, packaging skills for distribution, or understanding skill architecture.

DSPy declarative framework for automatic prompt optimization treating prompts as code with systematic evaluation and compilers

Expert knowledge for writing cutting-edge, idiomatic Rust code with Rust Edition 2024, strict clippy compliance, and functional-but-pragmatic philosophy. Use when writing any Rust code, fixing clippy warnings, structuring modules or crates, reviewing or refactoring Rust code, or questions about Rust 2024 features, async patterns, documentation standards, or performance optimization.

Generates comprehensive documentation and API references

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.

Create MCP servers, function calling tools, and composable tool frameworks for AI agents

Prevent request timeouts in Claude Code sessions by chunking long operations, implementing progress checkpoints, using background processes, and optimizing tool usage patterns. Use when performing bulk operations, processing large datasets, running long-running commands, downloading multiple files, or executing tasks that exceed 2-minute timeout limits. Implements strategies like task decomposition, incremental processing, parallel execution, checkpoint-resume patterns, and efficient resource management to ensure reliable completion of complex workflows.

检测"我叫乐乐"等触发词，切换暴躁回复模式

Create clear, step-by-step implementation plans with acceptance criteria. EXCLUSIVE to planner agent.

Expert Neovim consultant and configuration assistant. Use when answering questions about Neovim configuration, plugins, or feature behavior. Ensures version-specific accuracy by checking actual config and installed plugins before providing advice.

Skill for building Claude Code plugin commands.