Claude Skills

Creates Claude Code rules (.claude/rules/*.md) with YAML frontmatter and path-specific scoping. Use when creating project rules, coding standards, or conditional guidelines for specific file types.

Next.js data fetching - Server actions, caching, revalidation

Guides creation of custom subagents with YAML frontmatter, system prompts, tool restrictions, and permission modes. Use when creating or configuring subagents.

Scale PostgreSQL - partitioning, connection pooling, high availability

Claude Code memory (CLAUDE.md) configuration reference. Use when setting up project memory, understanding memory hierarchy, or configuring persistent instructions.

Board meeting preparation: agenda, metrics, narrative, follow-ups. Use when preparing for a board meeting.

Use when creating Minecraft mods, integrating with mod APIs (JEI/AE2/Create), setting up modding environments, or migrating to newer versions

Use PROACTIVELY when checking if tests catch real bugs, assessing test suite quality, finding weak tests, or measuring mutation score. Validates test effectiveness beyond coverage metrics by introducing code mutations. Supports Stryker (JS/TS), PIT (Java), mutmut (Python). Not for projects without existing test suites.

Activates when the user asks about Agent Skills, wants to find reusable AI capabilities, needs to install skills, or mentions skills for Claude. Use for discovering, retrieving, and installing skills.

Expert-level Vercel AI SDK v5 patterns for production chatbots. Use for: (1) Chat persistence with Drizzle/PostgreSQL, (2) Generative UI with typed tool parts, (3) Human-in-the-loop tool confirmations, (4) Custom data streaming with reconciliation, (5) Anthropic provider with extended thinking/reasoning, (6) Type-safe message metadata with token tracking. Covers advanced patterns only - assumes basic AI SDK knowledge. NOT for AI SDK v6.

Next.js deployment - Vercel, Docker, self-hosting strategies

Defines the layered output format for development plans (TL;DR, Approach, Tasks with dependencies). Ensures plans are readable at multiple levels - from executive summary to detailed implementation steps.

Defines the standard output format and template for creating development plans. Use this skill to ensure consistent, well-structured development plan formatting across any project type and technology stack.

OpenAPI/Swagger 사양, 인증 패턴, 버전 관리 전략 및 모범 사례를 사용하여 RESTful 및 GraphQL API를 설계하고 문서화합니다. 사용 사례: (1) API 사양 생성, (2) REST 엔드포인트 설계, (3) GraphQL 스키마 설계, (4) API 인증 및 권한 부여, (5) API 버전 관리 전략, (6) 문서 생성

Use this skill when validating ANY potential code review finding. Apply BEFORE classifying to verify the finding is real; can you trace incorrect behavior, is it handled elsewhere, and are you certain about framework semantics? If any answer is no, DO NOT create the finding.

Expert implementation of @vis.gl/react-google-maps library for Google Maps in React. Use when building maps, markers, pins, infowindows, places autocomplete, geocoding, draggable markers, polygons, circles, polylines, drawing tools, or any Google Maps JavaScript API integration in React/Next.js applications.

Autonomous overnight execution. Orchestrate subagents to implement a plan while human sleeps.

Guidelines for gathering task requirements through focused clarifying questions. Use when creating tasks and the provided requirements are incomplete, ambiguous, or missing critical information like acceptance criteria, scope, technical constraints, or target users.