數據與 AI

Handles backend integration using best practices like expo/fetch and React Query. Use when the user needs to connect to an API, handle data fetching, or implement caching.

Creates video presentations with static AI-generated slides and animated transitions. Auto-trigger when users ask to create presentations, slideshows, video presentations, pitch decks, training videos, or animated slide shows. Supports brand consistency via reference images (logos, colors) from the Reference Images folder. Uses fal.ai APIs (Nano Banana Pro for slides, Eleven Labs for voiceover, Kling 2.6 Pro for transitions) and FFmpeg for assembly.

Code review, best practices, maintainability

Export WaveCap transcriptions and pager data. Use when the user wants to export transcriptions as JSON, download reviewed transcriptions with audio, or export pager feed data.

Guide on optimizing Bluera Knowledge search results through proper intent selection, detail level strategies, result limiting, and store filtering. Teaches when to use minimal vs contextual vs full detail, and how to choose the right search intent for different query types.

Write failing tests before implementation (RED phase of TDD). Creates test file with test functions that fail because code doesn't exist yet. Use when starting TDD workflow or adding tests for new functionality.

Master database design, SQL optimization, system architecture, and design patterns. Learn PostgreSQL, MongoDB, Redis, and distributed system design.

Ingest project documentation and code into persistent semantic memory (Qdrant + Voyage embeddings). Use when user wants to remember context across sessions, ingest docs, or search previous work. Requires Qdrant running locally and VOYAGE_API_KEY set.

Inspect Supabase database schemas and data. Use when the user asks to "check table", "list columns", or "query data" in Supabase. READ-ONLY.

Manage blog posts including creating, editing, viewing, and troubleshooting blog-related features. Use when working with blog posts, articles, post forms, rich text editor, tags, thumbnails, or publishing workflows.

Get contact information from macOS. Use when texting, calling, emailing or social networking with people and companies.

Pattern for creating skills with YAML frontmatter that enables progressive disclosure and token optimization. Use when building skills, optimizing context usage, or implementing domain expertise with minimal token overhead. Demonstrates how to structure SKILL.md files with metadata-driven loading that achieves 84% token reduction compared to manual instructions. Triggers on "create skill with metadata", "token optimization", "progressive disclosure", "skill frontmatter", "efficient skill design".

A simple example skill that demonstrates the basic structure of a Claude Skill, including scripts, references, and best practices. Use this as a learning template when creating new skills.

Utilities and patterns for detecting execution environment (CI/CD vs local, network access, available ports, timeouts). Use when you need to adapt scripts or workflows based on where the agent is running, or when creating helper scripts that need environment-aware behavior.

Advanced visibility analysis using head pose, face mesh, and temporal patterns. Use for face-visible vs body-only breakdowns.

JD(채용공고) 분석 및 맞춤형 지원서 작성. JD Pain Point 추론, 경험 매칭, 자기소개서/이력서 생성을 지원합니다.

Implement or refactor the Python CLI tic-tac-toe game in this repo, including board model, move validation, win/draw logic, game loop, and bot behavior. Use when working on core gameplay modules or CLI entrypoints for this project.

Data splitting for model validation using TD_TrainTestSplit

Manages testing lifecycle including unit tests, integration tests, validation, and quality assurance.

This skill should be used when building UI components, adding animations, or reviewing design decisions with Emil Kowalski's design philosophy. Triggers include "make it feel Linear", "emil style", "tasteful animation", or when designing interactive components that need craft and restraint.