數據與 AI

Build the project, commit all changes, and deploy to main via the claude/merge-to-main branch. Use when deploying changes to production.

Code review and quality assurance specialist for ensuring code quality, security, and maintainability

This skill should be used when the user asks about "snapshot.md", "constraints.md", "decisions.md", "debt.md", ".ctx/", "living context", "documentation freshness", "stale docs", "ADR", "architecture decision", "technical debt", "system context", "co-located documentation", "context health", "validation", or needs help managing co-located documentation that stays synchronized with code.

Implements Anthropic's Routing pattern to classify incoming tasks and direct them to specialized handlers. Analyzes task complexity, intent, and category to select optimal processing path and model (Haiku/Sonnet/Opus). Use as the entry point for complex requests requiring intelligent dispatch.

Production-grade Go CLI patterns, automated release workflows with Release Please, versioned docs, and coverage enforcement for DevSecOps build pipelines.

Factory.ai Droid CLI integration for autonomous AI coding agent. Supports interactive and exec modes with multiple autonomy levels for code review, feature development, and testing. Activated when users need terminal-based AI assistance for comprehensive code tasks.

Guidelines for safely executing destructive file operations (mv, rm, cp). Use when performing file moves, deletions, or overwrites to prevent accidental data loss. Provides verification steps and best practices for batch operations.

Unified enterprise programming language skill covering 25+ languages including Python 3.13, TypeScript 5.9, Go 1.23, Rust 1.91, Java 21, JavaScript ES2025, C++, C#, PHP, Swift, Kotlin, Scala, Elixir, Ruby, R, SQL, Shell, and more with patterns, best practices, and Context7 integration

OpenRouter unified AI API - Access 200+ LLMs through single interface with intelligent routing, streaming, cost optimization, and model fallbacks

Production-ready 3D globe implementation with React Three Fiber for React Native. Use when implementing interactive 3D globes with GLB models, country/continent selection, smooth camera animations, and gesture controls in Expo apps. Optimized for iOS 60fps performance.

Interact with Dagster data orchestration platform running locally or on Kubernetes. Use when Claude needs to monitor Dagster runs, get run logs, list assets/jobs, materialize assets, launch jobs, or debug pipeline failures. Supports both local Dagster dev server and Kubernetes deployments where each job run is a separate pod.

Generate optimized indirect prompt injection, H-CoT, and multi-layer attack payloads for AI security testing and CTF competitions with automated family selection and success rate optimization

Manage the Registry platform - unified Convex database for tasks, articles, courses, emails, and all personal/professional data with MCP server integration

创建高效技能的指南。当用户想要创建新技能（或更新现有技能）以扩展 Claude 的能力时应使用此技能，包括专业知识、工作流程或工具集成。

Maintains synchronized project context for long-running work across sessions.Use when: starting a session (read context), completing significant work (update context),making architectural decisions (document rationale), or before stopping work (ensure clean handoff).Triggers on: "continue working", "what's next", "resume", "pick up where", "context", "progress","document", "handoff", "session", "PROGRESS.md", "plan feature", "feature list"

Execute Sprint 1 tasks for FASA optimization and trade analytics. This skill should be used when the user requests execution of any Sprint 1 task (Tasks 1.1-1.4, 11-13, 2.1-2.4, 3.1-3.2), including cap space parsing, Sleeper integration, FASA target marts, FA acquisition history, roster depth analysis, enhanced FASA targets, notebooks, valuation models, trade analysis, automation workflows, or documentation. Each task is atomic, standalone, and designed for independent execution with built-in validation. Current focus: Phase 2 FASA Intelligence (Tasks 11-13, 1.4).

Generate detailed technical design documents including architecture, APIs, database schemas, and implementation specifications

Guide for implementing MCP Apps (SEP-1865) - interactive UI extensions for MCP servers. Use when building MCP servers that need to return rich, interactive HTML-based UIs alongside tool results for conversational AI hosts like Claude Desktop or ChatGPT.

cc-sdd (Claude Code Spec-Driven Development) 統合スキル。/kiro:* コマンドで呼び出し可能。要件定義、設計、タスク分解、実装を自動化。Use when: spec-driven development, requirements, design, tasks, /kiro commands,設計, タスク分解, 仕様から実装へ, Plans.md generation.

ML 모델 벤치마크 및 평가 실행. "벤치마크", "모델 평가", "성능 테스트", "inference 속도" 요청 시 활성화됩니다.