magic

Use for reading, analyzing, summarizing, and converting complex documents into Markdown artifacts or other supported document formats.

Use when the user provides API keys, tokens, or other configuration values that should persist across sessions, or when the user asks to query, list, or delete saved environment variables. Manages personal env by default and workspace env only when explicitly requested.

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".

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.

Use when the user wants to interact with DingTalk/钉钉 in any way — including but not limited to: reading, querying, searching, sending, replying to, forwarding, or recalling DingTalk/钉钉 chat messages and chat history; managing group chats and conversations; sending DING alerts; querying contacts, org structure, AI search, or coworkers; reading, searching, creating, or editing DingTalk/钉钉 docs, drive files, sheets, AI tables, wiki, mail, calendar events, meeting rooms, AI meeting minutes, attendance, OA approvals, todos, reports/logs, live sessions, AI apps, permissions, or open-platform docs.

Use when the user wants to interact with Lark/Feishu/飞书 in any way — including but not limited to: reading, querying, searching, sending, replying to, forwarding, or downloading Lark/Feishu/飞书 IM messages and chat history; managing group chats; listing, viewing, searching, creating, or editing cloud docs/files, Drive, Markdown, spreadsheets, Base tables, wiki, whiteboards, slides, apps, calendars/events/meeting rooms, contacts/org structure, tasks/todos, approvals, attendance, mail, minutes, VC notes, OKRs, real-time events, or custom Lark CLI skills. Load this skill first to find the right sub-skill.

Complete API reference for window.Magic.* in SuperMagic HTML micro-apps (HTML 微应用). Read this skill when you need exact method signatures, parameters, return types, or usage examples for: fs (readFile/writeFile/listFiles/deleteFile/deleteDir/moveFile/renameFile/watchFile), llm (chat/stream/getModels), agent (getAgents/selectAgent), project (createTopicAndSend/sendMessage/uploadFiles/downloadFiles), user (getInfo with app.json userInfo scopes), getAppBasePath, setInputMessage, reload. Also covers tiptap JSON message format, @file and @skill mention structures, model selector UI rules, user info authorization, error handling patterns, and backward compatibility table. Trigger phrases: 'window.Magic API', 'readFile writeFile', 'deleteFile deleteDir', 'moveFile renameFile', 'watchFile callback', 'llm.stream', 'llm.chat', 'createTopicAndSend format', 'tiptap JSON mention', '@file mention structure', '@skill mention', 'getAppBasePath usage', 'model selector UI', 'user.getInfo', 'get user info', 'user avatar', 'user

Query the list of all agents (employees) available to the current user. Use when generating code that requires a real agentId, or when the user asks "which agents/employees do I have".

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/

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.

Manage and optimize custom agent definition files (IDENTITY.md, AGENTS.md, SOUL.md, TOOLS.md). Also handles first-time employee initialization when .workspace/ has no IDENTITY.md. Use when users want to edit agent identity, modify workflow instructions, adjust personality, add/remove tools, optimize prompts, or initialize a new employee from scratch. Trigger signals: 'modify prompt', 'change identity', 'add tool', 'remove tool', 'optimize workflow', 'adjust personality', 'initialize employee', '修改提示词', '改身份', '加工具', '去掉工具', '优化能力', '调性格', '初始化员工', '创建员工'. Do NOT use for: skill creation (use skill-creator), skill searching (use find_skills tool).

Use when the user asks to create slides with a specific style, wants to see available PPT templates before creating, describes a custom template style, or wants to extract a template from an existing PPT project.

Core canvas design skill covering project management, multimedia principles, AI image generation, web image search, and design marker processing. Load for any canvas design task. CRITICAL - When user message contains [@design_canvas_project:...] or [@design_marker:...] mentions, or when the user wants to generate video/animation/clip on a canvas project, you MUST load this skill first before any operations.

Slide/PPT creation skill that provides complete slide creation, editing, and management capabilities. Use when users need to create slides, make presentations, edit slide content, or manage slide projects. CRITICAL - When user message contains [@slide_project:...] mention, you MUST load this skill first before any operations.

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.

Data analysis dashboard (instrument panel) development skill. Use when users need to develop data dashboards, create/edit Dashboard projects, build large-screen data boards, or perform dashboard data cleaning. Includes dashboard project creation, card plan, data cleaning (data_cleaning.py), card management tools (create_dashboard_cards, update_dashboard_cards, delete_dashboard_cards, query_dashboard_cards), map download tool (download_dashboard_maps), dashboard development, and validation.

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. NEVER write custom scheduler scripts.

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

Use when connecting or configuring IM channel bots (WeChat, WeCom, DingTalk, Lark), or when you receive a user message that contains an <im> block indicating it was sent from an IM channel — read this skill to understand what the context means and how to handle it correctly.

Use when multiple independent subtasks can run in parallel, when a research or exploration task is large enough to keep separate rather than do inline (doing it inline fills the conversation with intermediate steps you'll carry through to the end), or when you need a specialized agent type (explore for deep search, shell for system commands). Any task with a clear deliverable and no dependency on the current thread is a good candidate to delegate.

Summarize and compress the current conversation history into a structured context snapshot, then call compact_chat_history to save it. Read this skill only when the user explicitly asks to compact/summarize — system-triggered compaction injects the instructions directly without requiring a skill read.

Read this skill when the user asks for a research report, deep research, industry report, analysis report, whitepaper, or any substantive document deliverable; or when the topic requires multi-source retrieval and cross-validation (competitive analysis, market analysis, industry research, deep dive, landscape survey); or when the user is unsatisfied with the depth of an existing answer. Keyword signals: research, deep research, deep dive, analysis, investigate, report, survey, industry analysis, competitive analysis, market analysis. Trigger when: (1) the user wants to produce a formal report or research document as the deliverable; (2) the topic requires current, verifiable data from multiple sources — news, market analysis, competitive landscape, industry research; (3) the user is unsatisfied with the depth of an existing answer. Skip when a single search or model recall suffices and no document output is needed.

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.

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.

Migrate existing antd-style CSS-in-JS (createStyles) components to Tailwind CSS utility classes with full dark mode support, following the project's style system transition strategy. Use when the user asks to migrate, convert, or rewrite antd-style components to Tailwind, or when working on new components in files that already use antd-style.

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.

Migrate modules between shared `src/opensource/` code and enterprise overlays under `enterprise/src/opensource/`, while preserving the `src/opensource` boundary and existing component override points.

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.