Development

API design principles and decision-making.

Master API documentation with OpenAPI 3.1.

Opinionated coding style and tooling preferences by Anthony Fu.

Principal AI Architect and Machine Learning Engineer.

Multi-agent orchestration and state management.

Use SQL (PostgreSQL) when:

Expert for developing Streamlit data apps for Keboola deployment. Activates when building, modifying, or debugging Keboola data apps, Streamlit dashboards, adding filters, creating pages, or fixing data app issues. Validates data structures using Keboola MCP before writing code, tests implementations with Playwright browser automation, and follows SQL-first architecture patterns.

Build mathematically correct, visually prominent data visualizations for time-series charts. Use this skill when creating charts with mathematical overlays (trendlines, patterns, indicators), fixing visual artifacts (wavy lines, domain mismatches), or validating chart correctness. Focuses on technical correctness and progressive validation, not aesthetic design.

专业数据可视化专家，精通现代图表库、仪表板设计和交互式数据展示。能够将复杂数据转化为直观、美观且富有洞察力的可视化作品。

Validate data against schemas, business rules, and data quality standards.

This skill should be used when the user asks about "Effect Option", "Effect Either", "Option.some", "Option.none", "Either.left", "Either.right", "Cause", "Exit", "Chunk", "Data", "Data.TaggedEnum", "Data.Class", "Duration", "DateTime", "HashMap", "HashSet", "Redacted", or needs to understand Effect's built-in data types and functional data structures.

Create Next.js data table pages with SSR initial load, SWR caching, and server-response-based UI updates. Use when asked to create a new data table page, entity management page, CRUD table, or admin list view. Generates page.tsx (SSR), table components, columns, context, actions, and API routes following a proven architecture with centralized reusable data-table component.

Synthesize findings from multiple research sources into coherent insights. Use when combining data from different sub-agents or research threads.

Python data structure conventions for this codebase. Apply when choosing between Pydantic models, dataclasses, and other data containers.

Recommend basic data structures for a task. Use when a junior developer needs help choosing lists, maps, or sets.

Implement client-side data storage with localStorage, IndexedDB, or SQLite WASM. Use when storing user preferences, caching data, or building offline-first applications.

Ensure Alpaca API is used for quality data, not yfinance fallback. Trigger when: (1) crypto volume filter fails unexpectedly, (2) zero-volume bars in data, (3) API key configuration issues.

본 스킬은 대한민국 공공데이터포털(https://www.data.go.kr/)에서 제공하는 각종 공공데이터 API 를 사용하기 위한 설명입니다. 본 스킬은 공공데이터 개발 또는 공공 API 개발을 할 때 사용하면 됩니다.

Create database seed scripts with realistic test data for development and testing. Use when setting up development environment or creating demo data.

Process data files through transformation pipelines with validation, cleaning, and export. Use for CSV/Excel/JSON data processing, encoding handling, batch operations, and data transformation workflows.

Develop and manage data ingestion, processing, and transformation pipelines for pilot projects. Use when automating ETL workflows, integrating new data sources, or building canonical datasets to support downstream analytics.

Apply data-oriented architecture patterns when designing systems with polymorphic entities. This skill should be used PROACTIVELY when encountering switch statements or if/else chains that dispatch based on entity type, when designing new entity systems, or when refactoring toward extensibility. Provides registry-based dispatch, capability composition, and infrastructure-first development patterns. Complements solid-architecture with concrete implementation strategies.

발굴조사 자료(논문/보고서/주변유적) 수집 및 메타데이터 정규화

Analyze and Refactor TypeScript data models. Detect duplication, improve type safety, and validate relationships in interfaces/types.