Development

Default testing standard for all implementation work - ensures code actually works through mandatory execution validation before confirming to user. Applies automatically whenever writing, modifying, debugging, or implementing any code (scripts, APIs, UI, configs, data operations, logic changes). This is the baseline expectation, not an optional extra - every implementation must be verified through actual execution, not assumed correct.

Submit complex code questions to OpenAI GPT-5 Pro for deep analysis when you have 20 minutes. Use when the user asks for architectural analysis, comprehensive code review, debugging complex issues, or requests expert analysis of their codebase that requires extended reasoning. Automatically handles file selection, code packing with Repomix, cost estimation, long-running API requests, and result presentation.

Kindle Web Reader/Kindle macOSアプリからスクリーンショットをキャプチャしてPDF生成。書籍名やASIN指定でKindle本を自動PDF化。Kindleライブラリ検索、Playwrightでページ自動取得、PNG画像からPDF変換、レイアウト設定（single/double）、範囲指定、品質調整、リサイズに対応。タイトル取得に失敗した場合は表紙キャプチャをAIで視認して命名する。

Generate a skeleton template for a new Claude Code Skill.

This skill should be used for periodic review of all Claude Code skills. Triggers include "audit my skills", "which skills need work", "skill inventory", or when starting a skill improvement session. Identifies staleness, gaps, redundancy, and prioritizes improvements.

Defines the 'Composite Asset' problem and the correct data mapping patterns for Wing Commander Saga (WCS) assets. This skill should be used when understanding the relationship between POF 3D models and TBL data files, or when designing asset migration strategies that preserve gameplay functionality.

Use this skill when developing Next.js/React frontend code for Brokle. Includes components, pages, hooks, API clients, stores, or any frontend features.

Running precommit checks and build validation. ALWAYS use after ANY code changes.

Technical content writer for marketing pages, blogs, documentation, and video scripts. Use when asked to create marketing content, landing pages, blog posts, technical documentation, video scripts, or any content that requires deep understanding of the codebase and task history.

Codex CLI를 sub-agent로 활용하여 실제 구현 작업을 수행합니다. Claude가 작업을 분석/분해하고, Codex가 코드 작성/수정/리팩토링을 담당합니다. "Codex로 구현", "구현해줘", "코드 작성해줘", "병렬 구현" 요청 시 활성화됩니다.

Comprehensive Playwright automation testing skill with E2E testing standards, test generation workflows, and browser automation best practices. Use when writing automated browser tests, testing user flows, or performing web application QA.

A comprehensive skill that helps Claude review, analyze, and generate Ruby on Rails code according to established best practices.

Performance monitoring and regression prevention. Lighthouse CI, performance budgets, Core Web Vitals monitoring, alerting. Keep sites fast over time.

A Tailwind CSS component library that provides a set of pre-designed UI components. Use for accessible, themed components that match Williamstown SC brand.

Provides three production-ready ML training examples (sentiment classification, text generation, RedAI trade classifier) with complete training scripts, deployment configs, and datasets. Use when user needs example projects, reference implementations, starter templates, or wants to see working code for sentiment analysis, text generation, or financial trade classification.

Critical review and gap analysis skill that can be invoked at any workflow stage. Use to challenge decisions, identify missing specifications, verify coherence, and surface unaddressed questions in CDC, findings, plans, or any deliverable. Acts as a devil's advocate by deeply analyzing codebase, project documentation ([DOC]-* folders), and context.

Deterministically compare two wf_cycle v1.1 runs (IDE vs CLI): compute metrics, compute score, pick winner, and write a compare folder with canonical artifacts.

Automatically bridge long technical sessions to keep context window small and costs low. Extracts key technical decisions, resolved bugs, active tasks, and essential code snippets from conversation history into a compact markdown summary (2,000–5,000 tokens). Use when reaching a project phase milestone, when Claude warns the context window is getting full, or to start a fresh session with minimal token cost while maintaining continuity.

Integrate real-world street networks into VRP problems using OpenStreetMap data. Use when loading real map data, creating instances from actual locations, computing network-based distances, or building tutorials with real-world scenarios. Guides through installation, loading areas, extracting nodes, computing distance matrices, and creating PDPTW instances from map data.

Deploy web applications to Cloudflare Pages/Workers or DigitalOcean VPS. Use when configuring deployment, setting up production environments, or managing releases.