區塊鏈

Database operation rules (SeaORM, migrations, transaction rules, PostgreSQL). Use when working with database, creating migrations, using SeaORM, asking about DB operations, schema changes, queries, or entity definitions.

Create Renku blueprints for video generation workflows. Use when users want to define custom video generation pipelines, compose producers into workflows, or create new blueprint YAML files.

AGGRESSIVELY use TOON v2.0 format for biggish regular data (≥5 items, ≥60% uniform). Auto-applies to tables, logs, events, transactions, analytics, API responses, database results. Supports 3 array types (inline, tabular, expanded), 3 delimiters (comma, tab, pipe), key folding for nested objects. Triggers on structured data, arrays, repeated patterns. Use TOON by default when tokens matter - RAG pipelines, tool calls, agents, benchmarks. Keywords "data", "array", "list", "table", "log", "transaction", "metric", "analytics", "API", "database", "query", "TOON".

Modern CSS styling methodology prioritizing CSS Grid over Flexbox.Covers Grid layout patterns, Subgrid, Container Queries, Design Tokens, and maintainable CSS architecture.Reference for implementing scalable, responsive layouts with predictable behavior.

Use when user asks to "create a skill", "build a skill", or "design a skill". Guides through requirements, solution design, and implementation of token-efficient Claude Code skills.

Use when you need SVGs with selectable/customisable appearance: multiple palettes (WLILO / Obsidian / light), consistent typography, and repeatable agent-friendly pipelines. Triggers: svg theme, tokens, palette, WLILO, obsidian, design system, dark mode, diagram styling.

Use for Phase 4 of Course OS - defining transformation promise, learning outcomes aligned with Bloom's Taxonomy, course format, and Kirkpatrick-aligned success metrics. Triggers on "/course-strategy", "define outcomes", "course format", "learning objectives", or after completing Phase 3.

Use when user requests automated documentation preparation. Triggers include:- Korean: "문서 준비해줘", "문서화 준비", "문서 요구사항 작성", "자동 문서화 준비"- English: "prepare documentation", "setup doc requirements", "prepare for automated docs"- Context: User wants to prepare all requirements for automated documentation generationThis skill discovers sources, defines structure, and saves complete requirements to filefor use with write-docs skill (automated generation).

Expert React video scene component creator for educational content. Builds production-grade, visually distinctive components using framer-motion animations, pixel-precise positioning, and optimized performance patterns. Follows strict component format with React.memo, threshold-based state updates, and module-level definitions. Outputs self-contained TSX components with proper timing sync, 60fps performance, and comprehensive reference-based implementation.

Token usage and cost tracking with model-specific pricing for monitoring and optimizing AI token consumption. Use when tracking sessions, calculating costs, analyzing efficiency, or budget planning.

Expert guidance for SQLAlchemy 2.0 + Pydantic + PostgreSQL. Use when setting up database layers, defining models, creating migrations, or any database-related work. Automatically activated for DB tasks.

Use when building NuxtHub v0.10 applications - provides database (Drizzle ORM with sqlite/postgresql/mysql), KV storage, blob storage, and cache APIs. Covers configuration, schema definition, migrations, multi-cloud deployment (Cloudflare, Vercel), and the new hub:db, hub:kv, hub:blob virtual module imports.

Comprehensive audit of Expo/React Native app API integration layer. Use when asked to: (1) Review API interactions, auth handling, or token management, (2) Find hardcoded data or screens bypassing API, (3) Verify user interactions properly sync to backend, (4) Analyze offline behavior and caching, (5) Audit Orval/OpenAPI code generation, (6) Check for API security issues. Supports TanStack Query, Zustand, axios, Expo Router, expo-secure-store, and expo-constants patterns.

Guides creation of user stories and epic design documents. Use when defining new features, writing Given-When-Then criteria, creating story logs, or designing larger features that need scope definition.

Core orchestration skill for the Claude Organization. Manages async sub-agents, worktrees, daily logs, and context handoff. This skill defines how the main Claude Code instance operates as Secretary to the CEO.

Master requirements gathering, user story writing, acceptance criteria definition, and scope management. Transform insights into clear, actionable specifications.

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

Blockchain Captain - Smart contracts, DeFi, Web3, and decentralized systems specialist

Implement and validate FastAPI authentication strategies including JWT tokens, OAuth2 password flows, OAuth2 scopes for permissions, and Supabase integration. Use when implementing authentication, securing endpoints, handling user login/signup, managing permissions, integrating OAuth providers, or when user mentions JWT, OAuth2, Supabase auth, protected routes, access control, role-based permissions, or authentication errors.

Guide for designing Instance resources in OptAIC. Use when creating DatasetInstance, SignalInstance, ExperimentInstance, ModelInstance, PortfolioOptimizerInstance, or BacktestInstance. Covers definition references, config patterns, composition, flow execution pairing, and scheduling.