magic

Use when an HTML micro-app needs MagicBase persistence, window.Magic.db row operations, current-user context through window.Magic.getContext, creators, owners, assignees, permissions, CRUD, forms, surveys, todos, dashboards, filters, statistics, exports, or any saved user data.

Create and manage calendar projects for scheduling, content planning, and event management. Use when user wants to create a calendar, schedule events, or build a content/publishing calendar.

Use FIRST for Super Magic HTML micro-app work. Trigger even when the user does not say "micro-app", "HTML", or "window.Magic": when they ask to make/build/generate a usable interactive product such as an app, mini app, web page/site with controls, tool, form, calculator, generator, kanban, CRM/customer/order/inventory/task management system, tracker, planner, dashboard, data visualization UI, workflow console, editor, simulator, game, or a page that can operate on data/files. Also use FIRST whenever the task will use any window.Magic API (window.Magic.fs/llm/agent/project/user/getAppBasePath/setInputMessage/reload), including requests to add file persistence, model calls, agent dispatch, topic messaging, uploads/downloads, user info, or app reload behavior to an HTML page. Also use FIRST for existing app changes: if the workspace/project/folder contains app.json or legacy magic.project.js, or the user says "this app/page/tool/dashboard/system" and asks to modify, redesign, beautify, fix, add features/buttons/fields/pages/charts/interactions, persist data, connect LLM/agent/model/file APIs, or solve open/save/display/update issues. Required output pattern: a static Super Magic micro-app folder with app.json, minimal magic.project.js display bridge, index.html, window.Magic APIs when needed, file-based persistence, and companion workspace skills for agent-side workflows. Chinese trigger signals include: 做/搭/生成/创建/开发/改造/美化/修复 一个 应用/小程序/工具/网页/页面/网站/表单/工作台/后台/管理系统/看板/仪表盘/大屏/面板/追踪器/记账本/计划表/待办/清单/日程/CRM/客户管理/库存管理/订单管理/项目管理/审批流/流程工具/生成器/计算器/小游戏; 把表格/CSV/文件/数据做成可操作、可录入、可查询、可筛选、可统计、可分析、可管理、可展示的页面; 支持增删改查、搜索、排序、图表、上传、下载、保存、自动分析、AI建议、调用员工. Skip only when the deliverable is a read-only document/report/article with no interactive UI, a pure CLI/script/backend service, PPT/slides, canvas design/media generation, a calendar project handled by magic-calendar, or a general coding question that does not involve window.Magic APIs or an interactive frontend.

Inspect, upgrade, or restart the sandbox this Agent is running in. Use when the user asks about this Agent's sandbox status or Agent image version, or explicitly asks to upgrade or restart its current environment.

Use when the user wants to create, extend, or edit self-media posts or card/article projects for Rednote/Xiaohongshu, Instagram, WeChat Official Accounts, or similar platforms. Trigger on [@self_media_project:...], create/add post, make cards, generate social cards, write WeChat article, multilingual self-media requests, Rednote tags, WeChat article, Instagram cards, social media cards, content project. Also use for self-media post-publication operations such as immediate sync, real data refresh, published-data import, post-publication data sync, operations review dashboards, article ops review, and fixed `ops/*` data updates.

Pre-publish diagnosis skill for self-media works. Use when the user asks for 发布前诊断, 发布前分析, content scoring, pre-publish review, or optimization diagnosis for Xiaohongshu/Rednote image-card posts or WeChat Official Account articles. Reads the mentioned post folder, searches comparable content online, scores the work, and outputs prioritized revision instructions.

Use when a user needs a browser-accessible link to preview, present, or send Agent-generated workspace files, an entire project, or the current topic outside Super Magic—especially rendered output such as HTML that messaging or file-viewing channels cannot display directly—or when they need to find, reuse, change, or delete an existing share.

Create, modify, evaluate, package, and upload skills. Use when users want to create a skill from scratch, edit or optimize an existing skill, run evals to test a skill, benchmark skill performance, optimize a skill's description for better triggering accuracy, package a skill into a zip, or upload a skill to their skill library. Also use when user asks to "capture this workflow as a skill", "make a skill for X", "turn this into a reusable skill", "package this skill", or "upload to my skill library".

Security-first skill vetting protocol for AI agents. Use before installing any skill from the platform skill market, skillhub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns to determine whether a skill is safe to install.

Use when the user asks to create slides with a specific style, wants to use or inspect a slide template by code, wants to see platform-provided slide template options before creating, describes a custom template style, provides a PPTX/PPT file to convert into a platform template, or wants to extract a template from an existing Super Magic slide project.

Use when the user asks to find, select, call, or delegate work to an Agent/智能体, digital employee/数字员工, or Crew; when the target is unknown or must be selected by capability; when independent tasks can run in parallel; or when isolated research or a specialized Agent would improve the result.

Service Worker practical specifications for the current Magic Web implementation. Covers static resource partitioning, read-only API caching, request tagging, server-side kill/off takeover for /sw.js, and emergency rollback environment variables.

Add stable `data-testid` attributes by default for new or refactored UI components. Use when implementing React/TSX views, shadcn/antd-style components, dropdown/menu configs, or interactive UI flows that need reliable selectors for unit/E2E tests.

Use when you need the current user's identity or contact info: name, job title, employee number, email, phone, or department.

Manage scheduled tasks — create, query, update, and delete. CRITICAL - When user message contains any future time intent (e.g. "in 2 days", "tomorrow at 8am", "every morning"), you MUST load this skill first. Use the Code Mode tools described by this skill.

List available large language models and send chat completion requests programmatically. Use this skill when you need to call an LLM within a snippet, including model comparison, visual understanding, batch inference, and model performance testing.

Discover, connect to, and invoke tools on MCP (Model Context Protocol) servers. CRITICAL - When the user message contains [@mcp:...] mention, you MUST load this skill first to use MCP tools correctly.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.