Agents

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.

Use when external HTTP or HTTPS files must be downloaded reliably into the workspace, especially for multiple files, large videos or archives, resumable transfers, custom Referer or Origin headers, or downloads that may take a long time.

Use when the user wants to interact with Lark/Feishu in any way — including but not limited to: reading, querying, searching, sending, replying to, forwarding, or downloading Lark/Feishu 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.

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.

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.

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

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.

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.

Manage persistence for user-installed third-party CLI tools in the Super Magic sandbox. Use when the user wants to install, configure, adopt, restore, inspect, or remove a CLI, or when an external skill, webpage, or installer asks to run CLI install commands such as curl|sh, npm install -g, pipx install, uv tool install, go install, cargo install, or brew install. Do not persist runtime-provided CLIs.

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.

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.

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 wants to interact with DingTalk in any way — including but not limited to: reading, querying, searching, sending, replying to, forwarding, or recalling DingTalk 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 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.

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/listDir/getFileUrl/deleteFile/deleteDir/moveFile/renameFile/watchFile/watchDir), llm (chat/stream/getModels), agent (getAgents/selectAgent), project (createTopicAndSend/sendMessage/uploadFiles/downloadFiles), user (getInfo with app.json userInfo scopes), getAppBasePath, setInputMessage, reload. Also covers file-per-record data storage, list projection file names, 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', 'listDir watchDir', 'getFileUrl', 'get file url', '文件 URL', '获取文件链接', 'deleteFile deleteDir', 'moveFile renameFile', 'watchFile callback', 'watchDir callback', 'llm.stream', 'llm.chat', 'createTopicAndSen

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.

Connect to a user-provided OAuth2 app, complete authorization, and use its access token in Code Mode HTTP requests.

Fetch and summarize the latest news from trusted sources across politics, finance, society, world, tech, sports, and entertainment. Use when the user asks for latest news, headlines, or news in a specific category.

Use this skill whenever the user needs ANY mailbox/email operation — checking, reading, searching, sending, replying, forwarding, organizing or deleting email, managing threads, connecting a personal mailbox, or registering a new mailbox. This skill is the single entry point for email tasks and orchestrates qwenpawmail-mcp for nine supported personal-mail domains.

Use when the user wants to interact with Teamshare capabilities, especially Teamshare Base multi-dimensional tables: files, directories, sheets, fields, records, views, forms, dashboards, or dashboard widgets. Load this skill first to route to the right Teamshare sub-skill. Also trigger for localized requests in the user's language that refer to Teamshare or Teamshare Base.

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 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.

For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via list_agents and chat_with_agent, emphasizing that the plan is executed by the requester, not by the consulted Agent.

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.

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.

交互式引导用户配置 AI Agent 接入 Memory Proxy（逐步探测、逐步验证）

Read and summarize text-based file types only. Prefer read_file for text formats; use execute_shell_command for type detection when needed. PDF/Office/images/archives are handled by other skills.

Generate AI Cards — HTML visual pages (single-file or folder-based multi-file) for scheduled automated reports. Use when: user wants to create a recurring visual card, hotspot tracker, daily digest, analytics panel, inspiration page, or any HTML-based automated visualization that updates on schedule. Trigger signals: AI card, inspiration card, generated card, visual report, hotspot tracker, daily digest, dashboard card, scheduled visualization, and equivalent requests in any user language. Skip when: the task is about creating social media posts (use self-media-composer), or simple file generation without recurring schedule.

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/

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.

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.

Use this skill to proactively send a one-way message to a user/session/channel, usually only when the user explicitly asks to send to a channel/session or when proactive notification is needed. First query sessions with qwenpaw chats list, then push with qwenpaw channels send.

Use this skill when you need to consult another agent, ask for help, or involve a specific agent the user asked for.

Maps topics and keywords from user questions to QwenPaw official documentation paths and common source code entry points, reducing blind searching. Intended for the built-in QA Agent to quickly identify which files to read when answering questions about installation, configuration, skills, MCP, multi-agent, memory, CLI, etc.

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.

使用 Markdown `html:preview` 围栏输出轻量静态 HTML/CSS 可视化。当普通 Markdown 难以清晰表达数值对比、层级关系、流程、时间线、关键指标或布局示意，或用户明确要求可视化 HTML 预览时使用。询问 HTML 源码、教程示例或可复制代码时不要使用。

Launch a visible (headed) Chromium browser for interactive research tasks, demos, or debugging. Use when the user explicitly asks to see a real browser window, watch page interactions, or needs manual login/CAPTCHA handling.

生成 MySQL 查询报表并生成可视化图表。当用户需要查询 MySQL 数据库并以报表形式展示结果时使用此技能，包括：统计销售数据、分析用户行为、生成业务报表、查询业务指标等。

Manage project-centric research workflows, claims, evidence, notes, and experiments. Use when the task should be persisted into ResearchClaw's structured research graph instead of remaining a transient chat reply.

Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.

Use this skill when another agent's expertise or context is needed, or when the user explicitly asks to involve another agent. First list agents, then use qwenpaw agents chat for two-way communication with replies.

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.

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.

Optional sub-skill of self-media-composer. Generates a custom CSS + JS preset pair from a user's style description. Load this skill when the user chooses "Custom style" in Step 4.1 of the self-media-composer workflow, or explicitly asks to create / design a new visual template. English triggers: - "make a new preset", "create a style for me", "I want a custom template" - "design a theme that looks like…", "generate a matching preset" - User provides a reference image / Figma frame / screenshot and asks for a matching preset Multilingual triggers: - Equivalent custom-style, new-template, theme-design, palette-system, design-system, reference-image, Figma, or screenshot-matching requests in any user language.