这是 Supabase Agent Skills，一套帮助开发者配合 AI agent 使用 Supabase 的技能。所谓 Agent Skills 就是包含指令、脚本和资源的文件夹，agent 可以发现并使用它们，从而更准确高效地完成任务。它兼容 Claude Code、GitHub Copilot、Cursor、Cline 等 18 种以上 AI agent，并遵循 Agent Skills 格式。安装上可以参考 Supabase AI Skills 文档，支持一次性安装全部技能，也可以只装某个特定技能，还能作为 Claude Code 插件安装。可用技能里包含一个综合性的 supabase 技能，覆盖 Supabase 全部产品和集成，适用于使用 Database、Auth、Edge Functions、Realtime、Storage、Vectors、Cron、Queues 等产品以及客户端库的场景。适合用 AI agent 开发 Supabase 项目的开发者。
查看英文原文
Supabase Agent Skills Agent Skills to help developers using AI agents with Supabase. Agent Skills are folders of instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently. Compatible with 18+ AI agents including Claude Code, GitHub Copilot, Cursor, Cline, and many others. The skills in this repo follow the Agent Skills format. Installation See the Supabase AI Skills documentation for detailed installation instructions. Install all skills [安装/使用命令见下方] Install a specific skill [安装/使用命令见下方] Claude Code Plugin You can also install the skills as Claude Code plugins: [安装/使用命令见下方] Available Skills supabase Comprehensive Supabase development skill covering all Supabase products and integrations. Use when: Working with any Supabase product (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues) Using client libraries and SSR integrations (supabase js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix Troubleshooting auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS) Using the Supabase CLI or MCP server Working with schema changes, migrations, security audits, or Postgres extensions (pg graphql, pg cron, pg vector) supabase postgres best practices Postgres performance optimization guidelines from Supabase. Contains references across 8 categories, prioritized by impact. Use when: Writing SQL queries or designing schemas Implementing indexes or query optimization Reviewing database performance issues Configuring connection pooling or scaling Working with Row Level Security (RLS) Categories covered: Query Performance (Critical) Connection Management (Critical) Schema Design (High) Concurrency & Locking (Medium High) Security & RLS (Critical) Data Access Patterns (Medium) Monitoring & Diagnostics (Low Medium) Advanced Features (Low) Usage Skills are automatically available once installed. The agent will use them when relevant tasks are detected. Examples: [安装/