通过阿里云百炼 DashScope 生成 AI 图片 — 文生图、图像编辑、风格重绘、背景生成、画面扩展、涂鸦作画、电商套图。任务异步执行+轮询，成功后可自动下载到本地。
Smart browser task agent - describe what you want done in natural language and it completes automatically.
Generate AI videos with Google Veo, Seedance, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine Video, OmniHu — from…
Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover.
Analyze images using GPT-4 Vision for detailed description, OCR text extraction, object recognition, and visual Q&A.
Generate AI videos using ByteDance Seedance models via Volcengine Ark API. Supports text-to-video, image-to-video (first frame, first+last frame), multimodal reference…
Guide AI-powered video editing, highlight extraction, silence removal, and talking-head polish through ClipSense.
AI PPT Generator skill. Quickly generate well-structured, professionally formatted presentation drafts from topics and outlines.
Baidu Scholar academic search skill. Search academic papers, journals, and knowledge resources. Use when user needs academic literature, research papers, or scholarly information.
Switch to a specific browser tab by index. When you need to work with a different tab or return to previous page. Use browser_list_tabs to get tab indices.
AI Picture Book generation skill. Transform short text descriptions into coherent picture book stories with visual compositions.
Baidu Baike encyclopedia search skill. Provides authoritative, real-time, structured Chinese encyclopedia knowledge.
Qianfan Deep Research Agent for complex research tasks. Combines information retrieval, multi-source analysis, content synthesis, and report generation.
AI Video Notes skill for video content analysis and note generation. Extract key information from videos for learning, meetings, and content summarization.
Import an Agent from a .akita-agent package file. Installs the Agent profile and any bundled skills to the local system.
Baidu Maps skill for location search, nearby place search, geocoding, route planning, and weather queries.
Open new browser tab and navigate to URL (keeps current page open). When you need to open additional page without closing current, or multi-task across pages.
PaddleOCR document parsing skill based on PaddleOCR-VL-1.5. Provides SOTA-level document understanding with ultra-high precision recognition and parsing.
Extract page content and element text from current webpage. When you need to read page information, get element values, scrape data, or verify page content.
Miaoda App Builder - create web apps, WeChat mini-programs, games, AI tools, SaaS products, and dashboards through natural language conversations.
List all open browser tabs with their index, URL and title. When you need to check what pages are open, manage multiple tabs, or find a specific tab to switch to.