数据库
SQL、Schema 设计、迁移和数据库操作
Skills 列表
create-spring-boot-java-project
创建Spring Boot Java项目骨架
githubef-core
获取 Entity Framework Core 的最佳实践
githubsnowflake-semanticview
使用 Snowflake CLI (snow) 创建、修改和验证 Snowflake 语义视图。当需要构建或排查语义视图/语义层定义（使用 CREATE/ALTER SEMANTIC VIEW）、通过 CLI 验证语义视图 DDL 或指导 Snowflake CLI 安装和连接设置时使用。
githubpostgresql-code-review
PostgreSQL 代码审查助手，专注于 PostgreSQL 最佳实践、反模式和独特质量标准。涵盖 JSONB 操作、数组使用、自定义类型、模式设计、函数优化以及行级安全（RLS）等 PostgreSQL 专属安全特性。
githubsql-code-review
通用SQL代码审查助手，对MySQL、PostgreSQL、SQL Server、Oracle等所有SQL数据库进行全面安全、可维护性和代码质量分析。专注于SQL注入防护、访问控制、代码标准和反模式检测。与SQL优化提示互补，实现完整的开发覆盖。
githubsql-optimization
通用SQL性能优化助手，提供全面的查询调优、索引策略和数据库性能分析，支持所有SQL数据库（MySQL、PostgreSQL、SQL Server、Oracle）。提供执行计划分析、分页优化、批量操作和性能监控指导。
githubpostgresql-optimization
PostgreSQL专用开发助手，专注于PostgreSQL独特功能、高级数据类型和PostgreSQL专属能力。涵盖JSONB操作、数组类型、自定义类型、范围/几何类型、全文搜索、窗口函数和PostgreSQL扩展生态系统。
github
pr-workflow
General guidelines for Commits, formatting, CI, dependencies, security
tursodatabasetransaction-correctness
How WAL mechanics, checkpointing, concurrency rules, recovery work in tursodb
tursodatabasedifferential-fuzzer
Information about the differential fuzzer tool, how to run it and use it catch bugs in Turso. Always load this skill when running this tool
tursodatabasemvcc
Overview of Experimental MVCC feature - snapshot isolation, versioning, limitations
tursodatabasetesting
How to write tests, when to use each type of test, and how to run them. Contains information about conversion of `.test` to `.sqltest`, and how to write `.sqltest` and rust tests
tursodatabasestorage-format
SQLite file format, B-trees, pages, cells, overflow, freelist that is used in tursodb
tursodatabaseasync-io-model
Explanations of common asynchronous patterns used in tursodb. Involves IOResult, state machines, re-entrancy pitfalls, CompletionGroup. Always use these patterns in `core` when doing anything IO
tursodatabaseindex-knowledge
Generate hierarchical AGENTS.md knowledge base for a codebase. Creates root + complexity-scored subdirectory documentation.
tursodatabasedebugging
How to debug tursodb using Bytecode comparison, logging, ThreadSanitizer, deterministic simulation, and corruption analysis tools
tursodatabase
cloud-monitoring-list-time-series-request
Generates valid Cloud Monitoring ListTimeSeries requests and aggregation specifications from metric descriptors and resource parameters. Use when asked to create, generate, format, or build ListTimeSeries requests, JSON payloads, filter expressions, or aligner/reducer aggregations for Cloud Monitoring metrics and charts. Don't use for metric discovery or metric selection.
googlespanner-basics
Assists in provisioning instances and databases, designing performant schemas, and querying data in Spanner. Use when designing primary keys, writing SQL queries or client library code, or diagnosing performance issues.
google
wren
Wren CLI for AI agents — a semantic SQL layer over 22+ databases (Postgres, MySQL, BigQuery, Snowflake, Spark, …). The actual workflow guides live inside the `wren` CLI itself; this is just a discovery stub. Use whenever the user asks a data question (how many, show me, top N, compare, trend, breakdown, metric, revenue, customers, orders), wants to install / set up Wren Engine, connect a new database, connect SaaS data via dlt (HubSpot, Stripe, Salesforce, GitHub, Slack), generate or regenerate an MDL project from a database schema, enrich a project with business context (enum meanings, units, cubes like ARR / DAU / churn), or turn a project's context layer into a shareable GenBI web app / dashboard and deploy it to Vercel or Cloudflare. Triggers: 'install wren', 'set up wren engine', 'connect database to wren', 'connect SaaS to wren', 'load hubspot / stripe / salesforce data', 'generate mdl', 'scaffold wren project', 'enrich wren context', 'augment my project', 'add cubes', 'build a dashboard', 'make a shareable analytics app', 'deploy my context layer as a web app', 'genbi app', 'wren onboarding', 'wren usage', 'wren generate mdl', 'wren dlt connector', 'wren enrich context', 'wren genbi'.
cannerbigquery-bigframes
Generates Python code using BigQuery DataFrames (BigFrames), the pandas/scikit-learn-style API over BigQuery. Use when writing BigFrames code or doing pandas-style dataframe/ML work against BigQuery (e.g. in a notebook). Don't use for SQL-first workflows or the google-cloud-bigquery client library — use bigquery-basics.
googlecloud-sql-basics
此文件用于生成或解释 Cloud SQL 资源。当用户要求为 MySQL、PostgreSQL 或 SQL Server 创建 Cloud SQL 实例或数据库时，请使用此文件。 Cloud SQL 将第三方 MySQL、PostgreSQL 和 SQL Server 实例作为 Cloud SQL 中的资源进行管理。例如，当 Cloud SQL 创建一个开源 MySQL 实例时，生成的资源是 Google Cloud 管理的 Cloud SQL for MySQL 实例。 Cloud SQL 负责处理关系型数据库工作负载的备份、高可用性和安全连接。
google
fullstack-dev
全栈后端架构与前后端集成指南。 触发场景：构建全栈应用、配合前端开发 REST API、脚手架搭建后端服务、开发 Todo 应用、开发 CRUD 增删改查应用、开发实时应用、开发聊天应用、Express + React、Next.js API、Node.js 后端、Python 后端、Go 后端、设计服务层、实现错误处理、管理配置/鉴权、配置 API 客户端、实现身份验证流程、处理文件上传、添加实时功能（SSE/WebSocket）、生产环境加固。 不触发场景：纯前端 UI 工作、纯 CSS/样式调节、仅数据库 Schema 设计。
minimax-ai
seo-drift
SEO漂移监控：捕获SEO关键元素的基线，检测变化，并随时间追踪回归。SEO的Git：对页面SEO进行基线、差异和变更追踪。当用户提到“SEO漂移”、“基线”、“追踪变化”、“是否出问题”、“SEO回归”、“比较SEO”、“前后对比”、“监控SEO变化”或“部署检查”时使用。
agricidaniel
rails-expert
Rails 7+ 专家，精通通过 includes/eager_load 优化 Active Record 查询、使用 Turbo Frames 和 Turbo Streams 实现页面局部刷新、配置 Action Cable 处理 WebSocket 实时连接、搭建 Sidekiq worker 处理后台异步任务，以及编写全方位的 RSpec 测试套件。适用于构建基于 Hotwire、包含实时功能或后台任务处理的 Rails 7+ Web 应用程序。涉及 Active Record 性能优化、Turbo Frames/Streams、Action Cable、Sidekiq、RSpec Rails 等场景时调用。
jeffallan