LLM & Agents

Optimize websites for AI assistant recommendations. ChatGPT, Gemini, Perplexity, Claude. Get cited in AI answers.

Execute TDD workflow for user stories - spawn tester agent to write tests (RED), then coder agent to implement (GREEN). Use when executing stories in test-first discipline with parallel wave-based orchestration.

Advanced multi-agent coordination for managing AI agent pods and human teams. Includes agent architectures, communication patterns (pub/sub, message queues), task distribution, consensus mechanisms, conflict resolution, agent specialization, collaborative problem-solving, shared state management, lifecycle management, and multi-agent observability. Supports LangGraph, AutoGen, CrewAI, and distributed systems patterns.

SEMO 패키지 시맨틱 버저닝 자동화. Use when (1) Agent/Skill/Command 변경 후 릴리스, (2) VERSION 및 CHANGELOG 업데이트, (3) Keep a Changelog 형식 버전 관리.

Create specialized agents for Claude Code that handle specific tasks autonomously.Generate agent definitions with proper configuration and best practices.Use when: creating agents, generating sub-agents, setting up autonomous workflows.Activates for: "create agent", "generate agent", "new agent", "sub-agent", "make agent"

Code quality standards for PR review agents including try/except rules, logging patterns, type hints, and verification requirements. Use when reviewing code, spawning PR review agents, or validating code quality.

Analyze codebases to generate optimal Claude Code Sandbox configurations. Use this skill when users need to set up sandbox security settings for their projects. This skill should be triggered when users ask about sandbox configuration, security settings, or when setting up Claude Code for a new project. It analyzes the codebase stack (Node.js, Python, Rust, Go, PHP, etc.), detects dependencies, and generates appropriate sandbox and permission settings through an interactive Q&A process.

This skill should be used when the user asks to "create LaTeX handout", "compile handout", "generate presentation handout", "create PDF document from slides", or needs guidance on LaTeX document structure, formatting, embedding images, or creating comprehensive presentation materials.

Claude Code expert guidance - features, configuration, hooks, plugins, MCP servers, IDE integration, and enterprise deployment

Rob - Senior QA Engineer specializing in black-box testing and feature validation. Use when testing features against acceptance criteria, validating user requirements, creating test reports, or performing exploratory testing. Also responds to 'Rob' or /rob command.

Optimize Cljr compiler and runtime performance. Use when optimizing emitter output, runtime collections, REPL evaluation, or leveraging .NET 10/C# 14 features. Covers Span<T>, FrozenDictionary, AggressiveInlining, benchmarking, and allocation reduction strategies.

Multi-agent thread orchestration and coordination

Specialized agent for code review, debugging critique, and quality assessment

Quality validation after execution. Runs confidence-check skill (if complexity ≥15), spawns code-quality-validator for build verification, and reviewer agent for quality assessment. Scales checks based on change size.

Track billable hours for clients. This skill should be used when the user requests to log work hours, record time spent on client projects, view worklog entries, calculate total billable hours, or summarize recent work. Automatically prompts for missing information (client, hours, description) and validates client names against the invoice skill's client database.

Integrate React+Vite web apps with bodhi-js-sdk for local LLM integration. Use when user asks to: "integrate bodhi", "add bodhi sdk", "connect to bodhi", "setup bodhi provider", "bodhi react integration", "deploy bodhi to github pages", or troubleshoot bodhi-js-sdk connection/auth issues.

Standardized camera movement vocabulary for Veo 3 video generation. Use when creating video prompts that require specific camera movements, cinematography terminology, or when validating camera movement specifications. Provides authoritative reference for 50+ camera movements (Dolly, Arc, Crane, FPV Drone, Whip Pan, etc.) to ensure consistent, production-ready terminology.

Guide for creating effective skills that extend Claude capabilities with specialized knowledge, workflows, or tool integrations. Use when users want to create or update a skill. Follows progressive disclosure (metadata → SKILL.md → bundled resources) and provides 6-step creation process.

Use when executing implementation plans with independent tasks in the current session

Pre-implementation confidence assessment to prevent wrong-direction execution. Automatically invoked for complexity score ≥15. Performs 5 weighted checks (no duplicate implementations 25%, MetaSaver pattern compliance 25%, architecture verified 20%, similar implementations found 15%, requirements clear 15%). Requires ≥90% confidence to proceed, 70-89% triggers clarification, <70% stops execution. ROI of 25-250x token savings by catching misaligned work early. Use when complexity score ≥15 to validate implementation direction before spawning agents.