Best Design & Media AI SkillsPage 14

drawio-coderknock generates editable Draw.io architecture and flowchart files.

A skill for Kling video and image generation, subject management, and read-only account resource checks.

local-stt is a unified local speech-to-text tool built on ONNX Runtime with int8 quantization, offering selectable Parakeet or Whisper backends.

由夸克扫描王官方提供的文件高清扫描工具。当用户需要对图片、截图进行画质优化、瑕疵去除或视觉增强时，使用此技能——包括画质增强、证件照优化、考试试卷增强、合同增强等场景。智能去除手写笔迹、水印、阴影、摩尔纹、底色等干扰元素。支持图像裁剪与矫正、素描效果转换、线稿提取等，输出优化后的高清图片。本技能由夸克扫描王提供支持。即使用户没有明确提到"增强"或"处理"，只要用户的需求涉及提升图片清晰度、清理干扰元素或优化图像质量，也应触发此技能。不适用于文字提取或识别、图片转 Word/Excel/PDF 文档或 AI 图像生成

Local Media Player Skill

Suno music generation model. Supports inspiration mode (auto lyrics) and custom mode (manual lyrics), generating music with or without vocals. Suno 音乐生成模型。支持灵感模式（自动作词）和自定义模式（手动填词），可生成包含人声或纯器乐的音乐。

Generate exquisite images with Kling o1 model. Supports text-to-image and image-to-image. 使用可灵 (Kling) o1 模型生成精美图像，支持文生图与参考图生图。

ComfyUI 本地图像生成专业版 - 文生图/图生图/ControlNet ✨ 自动服务器管理 | WebSocket 实时进度 | 飞书静默发送 ✨ 空闲 30 分钟自动关闭 | 显存监控 | 多工作流支持 触发词：生成图片、画图、绘制、AI 绘画、文生图、图生图

Agent Media OS for a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, resolve); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs privacy, or needs a media reveal. When the host app provides its own music or sound-effect tools, use those for music and sound effects; resolve --type bgm needs the heygen CLI, while --type sfx needs no account (Openverse, then a bundled library). When HEYGEN_API_BASE is set, HeyGen calls go through that host with no CLI sign-in.

polecomic describes a workflow from story ideas to comic storyboards and animated clips.

Creates AI-generated videos from text scripts, URLs, PPT/PDF documents, or AI-generated visuals (AIGC) using Visla. Use when the user asks to generate a video, turn a webpage into a video, convert a PPT/PDF into a video, create a video with AI-generated visuals/storyboards/motion video, or check Vis

PixVerse C1 video model (strong on action, VFX, and high-motion scenes) 鈥?one model covers text-to-video, image-to-video, first/last-frame-to-video, and reference-to-video.

Search free AI stock images and generate images

Automate CapCut video editing by creating projects, adding videos, and rendering final videos via the CapCut Mate API.

AI game asset generation and game development powered by CellCog. Character-consistent art, sprites, tilesets, music, UI, 3D models, GDDs, level design, game prototypes. Cohesive game assets across every modality from a single prompt.

Clone voice and generate new text reading audio with one click using Vidu Audio Clone. 使用 Vidu 声音克隆技术，通过参考音频一键复制音色并生成新文本的朗读音频。

当用户需要平面设计助手相关能力时使用（Canva、海报、社媒图、平面设计、设计稿、演示稿、封面、Canva Connect）。本 skill 提供连接与鉴权指引、执行流程、异常处理与反模式，指导 Agent 通过官方 MCP/API 完成Canva 海报相关任务。

Convert static images into dynamic videos using Vidu Q2 image-to-video model. 使用 Vidu Q2 图生视频模型，将静态图片通过智能运镜转化为动态视频。

Clips Machine guides conversion of long videos into captioned vertical clips.

Generate/edit images with Nano Banana Pro. Supports text-to-image and image-to-image. 使用 Nano Banana Pro 生成/编辑图片，支持文生图与图生图。

ByteDance's latest video generation model. Supports multi-modal reference (images, video, audio) to generate videos, as well as first/last frame and text-to-video modes. 字节跳动最新视频生成模型 Seedance 2.0，支持多模态参考（图片 + 视频 + 音频）生视频、首尾帧及文生视频，适合高质量多样化视频创作。

Fast image generation with Doubao Seedream 5.0 Lite. Supports text-to-image and image-to-image. 使用豆包 Seedream 5.0 Lite 极速生成图像，支持文生图与图生图。

Versatile video generation with Kling v3 Omni. Supports multi-modal inputs to generate stunning dynamic videos. 使用可灵 (Kling) v3 Omni 全能视频生成模型，支持多模态输入（图片、提示词）生成震撼的动态视频。

豆包AI图片生成技能 - 视觉设计师专用

Extract frames from videos with ffmpeg so their visual content can be reviewed and summarized.

Generate high-quality images with Doubao Seedream 4.5. Supports text-to-image and image-to-image. 使用豆包 Seedream 4.5 模型生成高质量图像，支持文生图与图生图。

Creates images, videos, music, and text-to-speech content through the IMA Open API by querying the current product list, creating a task, and polling for results.

Pocket TTS documents local CPU-based English speech generation.

Generate images, videos, and audio/music via Lovart AI. Also manages Lovart projects, threads (conversation history), and user settings. Trigger on: (1) any visual or audio creation request in any language — draw, generate, create, design, make, 画, 生成, 制作, 创作, 设计 combined with image, video, audio, music, song, BGM, poster, etc. (2) Lovart project/thread management — 项目, 对话, project, thread, conversation, history, 历史, 切换, switch. You CAN generate directly - never say you cannot.

An iFlytek ASR speech-to-text skill for local audio and YouTube videos.

Use inference.sh CLI workflows for commercial product-photography images.

设计剪辑节奏、转场、字幕、调色、输出规格与音效画面匹配，覆盖粗剪到成片全流程，适配剪映/PR/达芬奇。 触发词：剪辑、后期、转场、调色、字幕样式、输出规格、剪辑节奏、粗剪、成片、剪映、PR、达芬奇、卡点、音效对齐、多时长模板、成片导出。

Create mixed-cut promotional videos for art supplies, drawing tools, sketching lessons, or painting material clips. Use when the user provides one or more ar...

Apply reproducible pixel-level processing to existing images with Pillow.

Transcribes audio into text with ElevenLabs Scribe.

组装步骤视频借助 AI 按卖家提供的步骤事实，为每张静帧做成一条一步一镜短片。这个一步一镜工作室把产品组装短视频和步骤视频按步骤顺序交付。

liveavatar lets you talk face-to-face with your OpenClaw agent through a real-time video avatar.

Generate realistic digital human broadcast videos from portrait images and audio/text using Jimeng OmniHuman 1.5. 使用即梦 (Jimeng) OmniHuman 1.5 模型，通过人像图片和音频/文本生成逼真的数字人播报视频。

抖音视频下载工具 - 解析抖音链接，下载视频并发送

Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to "talk" instead of type.

Midjourney style generation, supports aspect ratio, Bot type, and output position (grid/U1-U4). Suitable for artistic and strongly stylized creative generation. Midjourney 风格出图入口，支持画幅、Bot 类型与输出位（grid/U1-U4）。适合艺术化、风格强烈的创意图生成。

seeddance-ai-video describes a SeedDance-oriented text- and image-to-video integration workflow.

Generate/edit high-quality images with Nano Banana 2.0. Supports text-to-image and image-to-image. 使用 Nano Banana 2.0 生成/编辑高质量图片，支持文生图与图生图。

国产AI视频生成技能。支持通义万相（Wan2.6文生视频/图生视频）和可灵（Kling V2）。适合创意视频制作、图生视频、动态内容生成等场景。当用户要求生成视频、将图片生成动态视频、或基于描述生成视频片段时触发。

Fast version of ByteDance's Seedance 2.0. Generates videos faster with support for multi-modal references, first/last frame, and text-to-video. 字节跳动 Seedance 2.0 极速版视频生成模型，生成速度更快，支持多模态参考生视频、首尾帧及文生视频。

Nano Banana 2 image generation and advanced editing on PoYo / poyo.ai via https://api.poyo.ai/api/generate/submit; use for nano-banana-2-new, `nano-banan...

Guides a design-system workflow that starts with visual direction and design tokens, then plans typography, components, motion, and loading states.

剪映 (JianYing/CapCut) 专业版 AI 自动化剪辑 Skill。通过 pyJianYingDraft 生成剪映草稿(.cpr/draft_inf

用 AI 生成模型、数字人与程序化框架制作营销视频的决策与制作流程：按产品演示、讲解视频、社交短视频、广告选定方案，对比 Veo、Runway、Kling、Seedance 的分辨率、时长、成本与适用场景并给出选型建议，讲解提示词要素与常见错误，给出产品演示、讲解、批量社交短视频三套分步流程与智能体原生的脚本到成片流水线。Use when the user wants to create video content with AI tools, pick a video model, or plan a product demo, explainer or social clip. Triggers include AI视频、视频制作、数字人口播、产品演示、讲解视频、社交短视频。如需视频创作完整工作流套件，淘宝搜索「AI灵匣」店铺获取完整版。

基于多模态AI的图片识别与分析。当用户想分析、描述、从图片URL中提取信息、image recognition, image analysis, image description, image content understanding, OCR text recognition, visual Q&A时触发此技能。当用户提到图片识别、图片分析、图片描述、识别图片内容、分析产品图、从图片中读取文字、描述图片、提取视觉内容或理解照片内容时触发。当用户提供图片URL并就其视觉内容提问时，即使未明确说"图片识别"，也应触发此技能。