LLM 與 Agent

테스트 케이스 생성을 test-case-agent에 위임

Creates Claude Code subagents for task delegation. Guides through agent configuration,tool selection, and system prompts. Use this skill when the user wants to create a new agent,delegate tasks to specialists, or asks about subagents.

Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization

Multi-agent orchestration system for automatically generating comprehensive Azure DevOps wiki documentation from Python codebase. Creates hierarchical wiki pages matching repository structure with bidirectional linkages between documentation and source files. Use when needing to document entire directories or maintain wiki docs synchronized with code.

接收用户输入的诗词，通过自主创意决策，将其转化为一份详细的、导演级的多幕视觉叙事绘图指令。在用户想要将古诗词转化为图像，或需要为诗词创作高质量提示词时使用。

Comprehensive code review workflow coordinating quality, security, performance, and documentation reviewers. 4-hour timeline for thorough multi-agent review.

Smart money tracker. Analyzes institutional investor behavior through 13F filings, Form 4 insider transactions, and large block trades to identify where big money is flowing.

Select the right skill for any task. Use when starting work, uncertain which skill applies, or to identify gaps in skill coverage.

Agent with minimal Gemini safety settings using default threshold only

Inject structured reasoning blocks into prompts to encourage step-by-step thinking. Use when tasks require complex problem-solving, multi-step reasoning, planning, analysis, or when you need the model to show its work and reflect on decisions before providing answers.

This skill should be used when the user asks about "prompt_toolkit Application", "app.run", "run_async", "asyncio", "event loop", "run_in_terminal", "async key binding", "background task", "Application lifecycle", or needs to understand the Application run loop and async patterns in prompt_toolkit.

Expert guidance for creating effective Claude Code agents (subagents). Use when users want to create a new agent, update an existing agent, or learn agent design best practices. Covers agent architecture, prompt engineering, tool selection, model choice, and common pitfalls. Integrates with skill-creator when agent needs accompanying skills.

Validates Implementation Phase completion before advancing to Testing Phase. Checks code compilation, test coverage, implementation completeness, and code quality standards.

Delegate asynchronous coding tasks to Jules (Google's AI coding agent) to maximize efficiency. Use for code reviews, refactoring, adding tests, bug fixes, and documentation. Proactively suggest Jules delegation when appropriate. Invoke when user asks to interact with Jules, create sessions, check task status, or when tasks are suitable for async delegation.

Use when starting ANY session or task. Entry point for the skill system - explains how skills work, mandatory loading rules, and dispatches to planners, guidelines, experts, and agents. Load this skill FIRST.

Collects the user's body weight and provide aggregations, charts and trends. Responds to commands like "today I'm 90Kg", "I gained 1Kg since yesterday", "What's my weekly average in the last 2 months?"

Index of AI agent skills and how to use them when implementing features in this repo.

Automated documentation auditing - ensures CLAUDE.md coverage, updates stale docs, recommends structural improvements

LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications

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.