數據與 AI

Create high-quality ASCII art UI/UX previews for web development with a two-phase approach. Phase 1: Design & Preview - visualize interfaces, explore layouts, refine ideas in ASCII format without code. Phase 2: Implementation - when ready, get HTML/CSS/React code and design tokens. Use for exploring ideas, getting stakeholder feedback, and iterating on design before development.

Validate plugin integrity and offer safe auto-fixes for common issues - checks agents, skills, hooks, routing config, and plugin structure

Use when encountering bugs, test failures, unexpected behavior, errors, or performance problems - dispatches systematic-debugging-agent that enforces 4-phase process (root cause investigation, pattern analysis, hypothesis testing, implementation) to prevent quick-fix attempts and ensure proper debugging

This skill should be used when the user asks to "use Gemini Batch API", "process documents at scale", "submit a batch job", "upload files to Gemini", or needs large-scale LLM processing. Includes production gotchas and best practices.

Bayesian time series models including AR, MA, ARMA, state-space models, and dynamic linear models in Stan and JAGS.

Compare AI-generated estimations with actual company PDFs to identify price differences and new items. Use when users need to validate estimations against real company quotes.

환경변수(.env.*), Spring 프로파일(application-*.yml) 수정 시 사용. app/backend/CLAUDE.md 참조 필수. 서비스별 포트 중복 검증, 민감 정보는 .env.local만, application-*.yml은 플레이스홀더만(기본값 금지). 의미없는 override 지양. SQS 엔드포인트 정확성 확인.

Expert deployment automation for cloud platforms. Handles CI/CD pipelines, container orchestration, infrastructure setup, and production deployments with battle-tested configurations. Specializes in GitHub Actions, Docker, HuggingFace Spaces, and GitHub Pages.

Earn trust through verification. Invoke at session start to establish verifiable checkpoints (environment, baseline, completion). Trust comes from gates, not claims.

Expert prompt engineering for LLMs and AI agents. Use when users request help writing, reviewing, or improving prompts for chatbots, AI agents, system prompts, instruction sets, or any LLM-based application. Applies research-backed techniques to minimize hallucinations and maximize reliability.

Design, review, and improve agent workflows & agent using SSOT, SRP, Fail Fast principles. Supports Prompt Chaining, Parallelization, Orchestrator-Workers patterns.

Workflow automation and orchestration for MyDetailArea. Implements state machines for order lifecycles, automated status transitions, task assignments, escalation rules, SLA monitoring, and event-driven automation. Use when building automated workflows for orders, approvals, escalations, and business process automation.

Expert Odoo ERP specialist for module development, customization, configuration, and troubleshooting. Activated for Odoo-specific tasks including custom module creation, XML views, Python models, business logic, workflows, and Odoo framework best practices.

Security management for Hostinger VPS srv759970 - Fail2ban, WordPress security audits (25+ checks, 0-100% scoring), infrastructure audit. Use for security hardening, IP bans, or security assessments.

Standards, conventions, and struct tag reference for models

This skill generates planning documents (기획서) in PowerPoint format from analyzed screen data and project artifacts. It should be invoked by the /auto-draft skill during Phase 4 to create the final PPT output. Not intended for direct user invocation.

Generate images using Google's Nano Banana Pro (Gemini 3 Pro Image) with workflow-based prompting

Use PROACTIVELY when you need to create, update, configure, or validate Claude hooks for various events and integrations

Guide for debugging failing GitHub Actions workflows. Use this when asked to debug failing GitHub Actions workflows.

Builds full-stack React applications with Next.js App Router, Server Components, Server Actions, and edge deployment. Use when creating Next.js projects, implementing routing, data fetching, caching, authentication, or deploying to Vercel.