開發

Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.

Deploy and manage Docker containers on Cloudflare's global network alongside Workers. Use when building applications that need to run Python code, process large files (multi-GB zips, video transcoding), execute CLI tools, run AI inference, create code sandboxes, or any workload requiring more memory/CPU than Workers provide. Triggers include requests to run containers, execute arbitrary code, process large files, deploy backend services in Python/Go/Rust, or integrate heavyweight compute with Workers.

Python performance profiling with cProfile, line_profiler, memory_profiler, and py-spy. Covers profiling workflows, interpreting results, finding bottlenecks, memory leak detection, and optimization strategies. Use when code is slow, debugging performance issues, optimizing for production, or investigating memory usage.

Use when spawning Codex agents via Otto to delegate implementation work.

数据分析助手，提供数据清洗、探索性分析（EDA）、统计分析、可视化图表生成等功能，支持Python（Pandas/NumPy/Matplotlib）和JavaScript（ECharts/D3.js），助力数据驱动决策。

Use this skill when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions or structure, or converting Claude Code sub-agents to skills. This includes designing skill workflows, writing SKILL.md files, organizing supporting files with intention-revealing names, and leveraging CLI tools and Node.js scripting.

Build production-ready NestJS modules with entities, DTOs, services, controllers

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

Assists with code refactoring by detecting code smells, suggesting improvements, and providing refactoring patterns. Activates when writing/editing code, explicitly requested refactoring, or when code quality issues are detected. Maintains awareness of core principles while providing detailed patterns and examples.

Modern R development practices emphasizing tidyverse patterns (dplyr 1.1 and later, native pipe, join_by, .by grouping), rlang metaprogramming, performance optimization, and package development. Use when Claude needs to write R code, create R packages, optimize R performance, or provide R programming guidance.

Comprehensive project architecture analyzer that identifies technology stacks, build tools, and architectural patterns. Use when you need to quickly understand a project's structure, dependencies, and technical configuration. Provides analysis for frontend frameworks (Vue/React/Angular), Node.js environments, package managers, TypeScript usage, linters, and architecture patterns.

For leaders evaluating dashboards, metrics, or AI-generated reports to determine if they measure realityor generate confident-looking noise (Potemkin maps).Helps identify gaming potential, blind spots, and whether you should trust a metric more, less, or differently.Use when implementing new metrics, questioning existing dashboards, evaluating vendor claims,or when something feels off about your data.Keywords: dashboard audit, metrics, KPIs, gaming, Goodhart's law, AI reports, data quality,measurement validity, blind spots, Potemkin, are my metrics real, can I trust this data

実装前にノウハウを確認。Tauriコマンド追加、serde、WebSocket通信、設定項目追加、UI/オーバーレイ実装、セキュリティ関連の作業時に自動的にチェックリストを提供する。

Implement Stripe payment processing for robust, PCI-compliant payment flows including checkout, subscriptions, and webhooks. Use when integrating Stripe payments, building subscription systems, or implementing secure checkout flows.

Plan and triage work into GitHub issues. Use when Codex needs to decide whether a new issue is required, describe the problem, outline high-level plans and goals, propose architecture, split large work into sub-issues, add labels, and create a GitHub branch for each issue using gh.

Analyze and validate forms on web pages. Use when users ask to check form accessibility, verify form labels, audit input fields, check form validation, or analyze form UX. Detects missing labels, invalid input types, accessibility issues, and validation problems.

a skill that contains all the best practices for using Verdict Flags in shopify codebases. It should be uses whenever the agent is creating, updating or removing flags

Enforce structured git workflow with conventional commits, feature branches, semver versioning, and work logging. Use for all code changes to prevent work loss and maintain history.

Detect and synchronize Node.js version specifications across project files.

Automatically validate and fix Moodle PHP code for PSR-12 compliance with Moodle-specific exceptions (lowercase_with_underscores naming, frankenstyle prefixes). Activates when working with Moodle plugin PHP files or when code standards issues are detected.