DevOps

Deep research and information gathering specialist for thorough investigation, pattern analysis, and knowledge synthesis

Minimal starter template for creating new Claude skills following the v1.0 specification

Leverage iterator chains for efficient, lazy data processing without intermediate allocations. Use when processing collections.

Write or update repository devops scripts with this project's conventions. Use when creating or modifying shell scripts in scripts/ or packages/*/scripts.

Specialized agent configurations for specific industries

Gathers intelligence from public sources. Use when searching for usernames, geolocating images, investigating social media, analyzing domains, or solving information gathering challenges.

Lombok annotations and best practices for Java 21+ projects. Use when reducing boilerplate, configuring builders, or choosing between Lombok and Records.

Diagnose and fix third-party library loading failures in Vite, Webpack, or other bundlers. Use when encountering "Failed to fetch dynamically imported module", worker loading failures, CDN 404 errors, "Invalid type" errors when importing library assets, or assets loading in wrong format. Covers version mismatches, worker loading patterns, and bundler-specific solutions.

UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.

Coordinates complete comparison of 2 products with parallel subagents and result aggregation. Use when user asks to 'compare X vs Y', 'compare two products', 'research products for comparison', mentions comparing items for purchase decision, or requests product analysis. Handles product validation, cache checking, parallel data collection (specs, reviews, pricing), and comprehensive report generation.

GitHub Actions CI/CD 워크플로우 생성. Use when (1) 워크플로우 생성, (2) CI 추가, (3) GitHub Actions 필요.

How to spawn subagents correctly. Use this reference when you need to delegate work to a specialized agent.

Concise accessibility checklist and practices for components in the repository. Use when implementing UI to ensure keyboard, screen reader, and focus semantics.

View Flask server logs from local or remote server. Shows real-time or recent log entries for debugging. Use when monitoring server activity, debugging issues, or checking server status.

学習目的で、あらゆる提案変更に WHY / VERIFY / RISK とロールバックを必ず付ける（コード・コマンド・AWS手順）。WHYは「選択肢→特徴→結論（最適案）」で統一する。

Creates platform-specific training for LMS, authoring tools, and educational technology.

Sales productivity automation for K-12 rural broadband including proposal generation, RFP responses, pricing models, competitive intelligence, and CRM automation with E-rate expertise

Update the project learning logs (PowerShell/cmd, Git/GitHub/Copilot, AWS, TypeScript, Next.js/React, Playwright) by merging new knowledge into existing categories across one or more files.

Professional report generation system for MyDetailArea dealership management. Creates business intelligence reports with data visualization, multi-format export (HTML/PDF/Excel/CSV), and Notion-style design. Use when generating operational reports, financial analytics, performance dashboards, or custom data exports for the dealership system.

Comprehensive LLM model evaluation and ranking system. Use when users ask to compare language models, find the best model for a specific task, understand model capabilities, get pricing information, or need help selecting between GPT-4, Claude, Gemini, Llama, or other LLMs. Provides benchmark-based rankings, cost analysis, and use-case-specific recommendations across reasoning, code generation, long context, multimodal, and other capabilities.