图像视频 技能

使用微软 markitdown 库将多种文档格式（PDF、DOCX、PPTX、XLSX、XLS、CSV、JSON、TXT、EPUB、HTML等）转换为 Markdown。支持批量转换、保留格式、图片提取等功能。使用场景：(1) "把这个 PDF 转成 Markdown"，(2) "把这个 word 文档转成 Ma...

一句话写文章并自动发布到微信公众号草稿箱。用户说"帮我写一篇关于xxx的文章"或"写xxx"时触发。 自动完成：AI写作 → AI配图 → AI封面 → 排版美化 → 发布到微信公众号草稿箱。

Use when users need ecommerce image help such as background removal, transparent or white background output, blurry photo restoration, or listing image gener...

基于 Seedance 2.0 模型的 AI 视频生成器，输入关键词/描述文案即可生成 MP4 视频。支持文生视频、分辨率/比例/时长控制、预置虚拟人像引用。使用 Seedance 视频生成、AI 视频、text-to-video 时调用此 Skill。

Use this skill when the user needs to create AI videos, manage canvases, nodes, files, or interact with the ZenVFX platform via CLI. Trigger keywords include...

Generate new videos from text prompts, images, or reference inputs using EachLabs AI models. Supports text-to-video, image-to-video, transitions, motion control, talking head, and avatar generation. Use when the user wants to create new video content. For editing existing videos, see eachlabs-video-edit.

Use when user has/is reading a component datasheet or spec sheet to find chip parameters: pinout, voltage, I2C address, timing, register map, electrical char...

AI Video Enhancement - Upscale video resolution, denoise, sharpen. Supports local files and YouTube/Bilibili URLs. HD/4K upscaling with real-time progress.

Using fixed cameras at home (living room, bedroom) of elderly people living alone, the system analyzes daily videos and detects negative behavior indicators...

Generate fashion model imagery, virtual try-on, runway videos, and campaign visuals using EachLabs AI. Use when the user needs fashion content, model photography, or virtual try-on.

Extract clean, plain-text transcripts from YouTube videos using a dual fallback system with Supadata API and yt-dlp for fast, accurate results.

Cloud-based video enhancement skill that uploads a user-selected local video file to Wondershare-hosted endpoints for AI enhancement, then downloads the proc...

Generate images via BigModel APIs and send them as chat images (e.g. Feishu). Invoke when user asks to create a single picture with specific style/size.

This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses duckse (DDGS-based CLI) to return clean results in pretty text or JSON.

Publication-quality figure generator. 14 chart types (bar, hbar, stacked_bar, heatmap, scatter, line, dual_axis, box, forest, violin, km, roc, composite, dia...

Use PoYo AI Seedance 1.5 Pro for higher-end image-to-video generation through the `https://api.poyo.ai/api/generate/submit` endpoint. Use when a user wants l...

学术论文深度阅读技能。当用户提供 PDF 论文或论文文件路径时，自动执行全文翻译、 结构化讲解、图片解读和细节问答。适用场景：提供 PDF 文件路径、发送论文截图、 询问论文内容、请求解释某个术语或段落。 分析完成后可生成标准化摘要，方便后续生成 PPT（可选，非强制）。

AgentCall (agentcall.dev) — Join a video meeting (Google Meet, Teams, Zoom) as an AI bot with voice and visual presence. Supports audio-only mode with voice intelligence (barge-in, interruptions), text-to-speech mode, and webpage modes for custom UI. Use when asked to join a call, attend a meeting,

Accurately identifies plant diseases based on computer vision and deep learning, supports both image and video input, outputs structured diagnostic reports i...

Convert unstructured documents into LLM-ready structured data. Supports PDF, Word, PPT, and images; extracts paragraphs, formulas, tables, charts, and other...

Generate images or videos via AIMLAPI from prompts. Use when Codex needs reliable AI/ML API media generation with retries, explicit User-Agent headers, and a...

对银行卡图片 OCR，返回卡号、银行与卡类型等。当用户说：银行卡卡号从照片里读出来、识别这张卡哪家银行，或类似银行卡 OCR 时，使用本技能。

Route Alibaba Cloud Model Studio requests to the right local skill (Qwen Image, Qwen Image Edit, Wan Video, Wan R2V, Qwen TTS and advanced TTS variants). Use when the user asks for Model Studio without specifying a capability.

Search Google and get the full structured SERP as JSON — organic results, ads, knowledge graph, AI overview, related questions, and more. Use for any query n...