區塊鏈

Define database models and schemas with proper data types, constraints, relationships, and validation rules for PostgreSQL (Supabase/Bun.sql) and Firestore (Firebase). Use this skill when creating or modifying database models, ORM entity definitions, Prisma schemas, or Firestore document structures. Apply when working on model files (models/*.ts, entities/*.ts, schema.prisma, models/*.py, Models/*.cs), defining database relationships, setting up validation rules, or implementing data integrity constraints. This skill ensures snake_case naming for SQL and camelCase for NoSQL, required timestamps (created_at/updated_at), UUIDs for SQL and auto-generated IDs for Firestore, foreign key constraints with indexed columns, Row Level Security (RLS) policies for Supabase, strict Firestore security rules, normalized data for SQL (3NF) with denormalization for Firestore read performance, and pgvector setup for AI embeddings.

Expert in securing FastAPI applications with JWT tokens and Better Auth. Use this when implementing authentication middleware, route protection, and user isolation.

Write type-safe TypeScript 5.x code using ES2022+ features, strict mode, discriminated unions, and modern async patterns. Use for TypeScript files (.ts), type definitions (.d.ts), configuration, or full-stack type safety.

Advanced LangGraph patterns for production applications. Use when implementing streaming (tokens, updates, custom data), parallel node execution, subgraphs for modular workflows, error handling and retries, or Command-based control flow. Covers stream modes, fan-out/fan-in, nested graphs, and production best practices.

Explore external reference source code to understand implementations, draw inspiration, debug issues, or answer questions. Use when exploring repos like InstantDB, Trigger.dev, Vercel AI SDK, HeroUI Native, or any external codebase. Handles two modes - "inspiration" (adaptive, translating concepts to user's stack) or "understanding" (direct, definitive answers about the source). Always cite file:line references.

Match SAE features between Ultra (24K) and Full (2K) models based on activation patterns and token overlap

Natural Language Processing utilities for PyTorch (Legacy). Includes tokenizers, vocabulary building, and DataPipe-based dataset handling for text processing pipelines. (torchtext, tokenizer, vocab, datapipe, regextokenizer, nlp-pipeline)

Understanding GITHUB_TOKEN scope, default permissions, and implementing least-privilege principle for GitHub Actions workflows.

Standard patterns for using Better Auth in Next.js 16+ App Router projects, including server and client integration, JWT plugin usage, and attaching tokens to backend API calls in a reusable way.

Use when building React UIs for TheGP applications, migrating existing UIs to @gp/ui components, integrating Tailwind v4 with @gp/ui theme, or answering questions about available components, design tokens, icons, or setup. Activate when user mentions @gp/ui, TheGP design system, or asks about GP-specific UI patterns and components.

Project type definitions with type-specific questions, patterns, and stacks.Use when: determining project architecture, asking type-specific questions.Referenced by: idea-validation, brainstorming, /ship command.

Batch upload local Markdown files to Notion via Python script. Optimized for single or multiple files with zero token cost. Direct script execution bypasses LLM parsing, saving significant tokens on large files while preserving formatting (tables, code blocks, rich text).

When explicitly authorized, execute end-to-end with a phased plan in one run until Definition of Done is met.

Set up MetaMask wallet extension for Web3 DApp testing - download extension, import wallet from private key. Run at test start if tests/config.yaml has web3.enabled=true.

Mandatory verification protocol after code changes for Solidity projects. Use after any code modification to ensure quality.

Security patterns for input validation, PII protection, and cryptographic operations

Automatically applies when implementing monitoring and alerting. Ensures proper metric instrumentation, alerts, SLO/SLI definition, dashboards, and observability patterns.

Use when working with Linear issues across development workflow - uses Linearis CLI with JSON output for zero-context issue management. Get details, create issues, update status, and add comments without consuming tokens in main session.

Convert Claude Code slash commands to OpenCode commands format. Use when migrating from Claude Code to OpenCode or when you have existing slash command definitions to port.

Automatically applies when adding logging and observability. Ensures structured logging, OpenTelemetry tracing, LLM-specific metrics (tokens, cost, latency), and proper log correlation.