数据库
数据库管理与查询
surrealdb
mikkelkrogsholm
"SurrealDB — multi-model database supporting document, graph, relational, key-value, time-series, and vector search in a single engine using SurrealQL. Use when building with SurrealDB or asking about schema design (schemafull vs schemaless), SurrealQL queries, graph relations with RELATE, live queries, full-text search, JS/TS SDK setup, namespace and database hierarchy, record IDs, authentication with DEFINE ACCESS, or connecting with WebSocket vs HTTP. Fetch live documentation for up-to-date details."
ecs-design
christopher-buss
Use when designing components, systems, or entity structures for jecs in
neon
mikkelkrogsholm
"Neon — serverless PostgreSQL with database branching, autoscaling to zero, and a serverless driver optimized for edge and serverless environments. Use when building with Neon or asking about its serverless driver, database branching, connection pooling, autoscaling configuration, compute suspend behavior, or integration with Drizzle, Prisma, or other ORMs. Fetch live documentation for up-to-date details."
tanstack-query
mikkelkrogsholm
"TanStack Query — powerful async state manager for TypeScript/JavaScript with caching, background refetching, and server state synchronization. Use when building with TanStack Query (React Query) or asking about its caching, query keys, mutations, invalidation, optimistic updates, or integration with React, Vue, Solid, or Svelte. Fetch live documentation for up-to-date details."
prisma
mikkelkrogsholm
"Prisma ORM — a type-safe database toolkit for Node.js and TypeScript with schema-first modeling, auto-generated client, and migration tooling. Use when building with Prisma or asking about its APIs, configuration, patterns, or integration. Fetch live documentation for up-to-date details."
drizzle
mikkelkrogsholm
"Drizzle ORM — lightweight, TypeScript-first SQL ORM with schema-as-code and zero-dependency query builder. Use when building with Drizzle ORM or asking about its schema definition, migrations, query builder, relations, or integration with databases like PostgreSQL, MySQL, or SQLite. Fetch live documentation for up-to-date details."
pnpm
christopher-buss
Node.js package manager with strict dependency resolution. Use when running
turso
mikkelkrogsholm
"Turso — edge-hosted SQLite database built on libSQL with embedded replicas, multi-tenancy, and low-latency global distribution. Use when building with Turso or asking about its libSQL client, embedded replicas, database-per-tenant patterns, auth tokens, sync, or integration with Drizzle or other ORMs. Fetch live documentation for up-to-date details."
zod
mikkelkrogsholm
"Zod — TypeScript-first schema validation with static type inference. Use when building with Zod or asking about schema definitions, type inference, parsing, transformations, refinements, coercion, error handling, or integration with forms, APIs, or tRPC. Fetch live documentation for up-to-date details."
review-perf
mgiovani
Perform comprehensive performance review analyzing database queries,
gdpr-dev
mikkelkrogsholm
"GDPR compliance for European developers. Use when building features that handle personal data: user registration, profiles, authentication, email sending, analytics, error tracking, payments, search indexes, background jobs, or any feature that stores, processes, or transmits information about people. Provides stack-aware gotchas, anti-patterns to avoid, and schema design principles. Does not ask questions — applies principles proactively based on what is being built."
verekia-architecture
verekia
Day-to-day coding style and patterns for R3F game development with Miniplex ECS.
koota
verekia
Use Koota for data-oriented Entity Component System architecture with React bindings.
B 站综合工具箱 (Bilibili Toolkit)
hwj123hwj
Collection of custom skills for AI agents
research-assistant
Ely-S
Use when given a research question to investigate using available data — triggers the full loop of schema exploration, query planning, researcher approval, and notebook generation
bjtuo-classroom-query
hwj123hwj
北京交通大学（BJTU）教室课表查询自动化。支持 AI 验证码识别登录、按周次、教学楼、房号查询占用情况。
openspec
ruan-cat
OpenSpec 规范驱动开发助手 - 基于 OPSX 工作流的 AI 辅助编程框架。在编写代码前与 AI 就需求达成一致，使用 Schema 驱动的工件依赖系统管理变更。 触发条件： 1. 用户提及 "openspec"、"opsx"、规范驱动开发 2. 用户想要开始新功能开发或重构 3. 用户需要探索复杂问题或明确需求 4. 用户抱怨 AI 理解偏差或频繁返工 5. 用户使用斜杠命令如 /opsx:new、/opsx:ff、/opsx:apply 等 6. 项目初始化或准备重大变更时
chroma
L-yifan
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
faion-backend-systems
faionfaion
"Systems backends: Go, Rust, databases, caching."
tanstack-start-architecture
alpoxdev
Use when working on TanStack Start projects - enforces architecture rules (layers, routes, hooks, server functions, conventions) with mandatory validation before any code change. Triggers on file creation, route work, server function writing, hook patterns, or any structural change in a TanStack Start codebase.
faion-software-architect
faionfaion
"Software architecture: system design, patterns, ADRs, quality attributes."
faion-backend-enterprise
faionfaion
"Enterprise backends: Java, C#, PHP, Ruby."
faion-ba-modeling
faionfaion
"BA Modeling: Use cases, user stories, process models (BPMN), data models, decision tables, interfaces, acceptance criteria. 7 methodologies."
faion-pm-agile
faionfaion
"Agile PM specialist: Scrum, Kanban, SAFe ceremonies, PM tools (Jira, Linear, ClickUp, GitHub, Azure DevOps), dashboards, team development, AI in PM, hybrid delivery. 28 methodologies."