Automated A/B testing and multi-model comparison for AI models with data-driven recommendations
|
デザイントークンの定義・管理、既存コードへのトークン適用、Design System構築。トークン体系の設計、余白・色・タイポグラフィの統一、ダークモード対応を担当。デザイントークン設計、UI一貫性が必要な時に使用。
Generate PhD-level expert agent prompts for Claude Code. Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices. Triggers on: spawn agent, create...
Container and Kubernetes security assessment skill for Docker, Kubernetes, and container orchestration platforms. This skill should be used when scanning container images for vulnerabilities,...
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) strategies for AI-powered search visibility in ChatGPT, Perplexity, Google AI Overviews, and other AI search platforms.
Keep a Changelog format. Covers structure, change types, versioning. Keywords: CHANGELOG.md, semver.
Applies coding standards from CLAUDE.md and coding-standards.md with dynamic learning that adapts to team preferences over time.
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Automatically share skills, migrate local skills to code repositories, open source skills, skill version management, configure git remote
Comprehensive GitHub code review with AI-powered swarm coordination
Comprehensive GitHub code review with AI-powered swarm coordination
Comprehensive GitHub code review with AI-powered swarm coordination
Generic multi-domain research framework with domain-aware scheduling. Model-agnostic and domain-agnostic - perform comprehensive research on any topic.
Auto-activates during requirements analysis to evaluate technical stack
Create Business Requirements Documents (BRD) following SDD methodology - Layer 1 artifact defining business needs and objectives