视频剪辑、缩略图、漫画、音频（3181 个）
Generate complete songs locally from lyrics and tags describing mood, instruments, or genre. The skill guides setup, input formatting, memory-saving settings, and MP3 output using the open-source HeartMuLa music models.
中文简介正在准备中。当前显示英语简介。
读取项目内容，确定介绍角度和表达风格，制作简短发布视频，并同时生成海报图片与分享文案。可指定横屏、竖屏或方形比例、时长及音频选项。
使用HTML和CSS设计画面，通过GSAP为文字和图像添加动画，导出MP4或WebM视频。支持带字幕的旁白、商品介绍，以及根据网站制作视频。
根据主题或台本及获准使用的成人肖像制作讲解视频，生成旁白与字幕，检查口型同步和画面一致性，调整音量后输出存档版、分享版视频及验证报告。
Create meme PNGs from a topic by choosing a familiar template and writing short captions. The skill uses Pillow to place readable text on templates or custom images, with optional text bars above and below.
中文简介正在准备中。当前显示英语简介。
使用ComfyUI工作流生成图像、视频、音频和3D内容，支持调整参数、批量生成、查看进度和保存结果，并检查与安装所需模型及自定义节点。
分析文章内容，建议图解和插图的位置，协调图表类型、画风与配色后生成图片，保存构思方案及生成提示词，并将完成的图片插入正文相应位置。
Use AudioCraft to generate music, sound effects, and environmental audio from text descriptions. Follow implementation examples for model selection, melody and reference audio guidance, stereo output, batch generation, and saving audio files.
中文简介正在准备中。当前显示英语简介。
Create a launch video from a project folder or website URL using its actual interface, fonts, and assets. Produce a plan, visuals, music, sound effects, a rendered video, and accompanying share copy.
中文简介正在准备中。当前显示英语简介。
将视频需求整理成制作计划，按风格组建专业智能体团队并配置制作环境。通过Hermes看板分配任务、查看进度，协助应对停滞或失败的任务。
将音频文件的频率、响度、音高和节奏等特征转为图像，可把多种图表排在同一张图中，或仅显示指定片段，用于比较音频和检查语音合成。
将视频或图片转换为彩色字符艺术，也可制作随音乐变化的动画。支持叠加歌词和文字、调整颜色与字符、组合视觉效果，并导出MP4、GIF或连续图片。
Turn YouTube transcripts into summaries, timestamped chapters, X threads, blog posts, or selected quotes. Provide a video link or ID, and the skill retrieves available subtitles and organizes their content into the format you request.
中文简介正在准备中。当前显示英语简介。
Find and download GIFs from Tenor for chat reactions and visual content. Retrieve full GIFs or smaller previews, inspect titles and dimensions, and choose media formats through API requests using curl and jq.
中文简介正在准备中。当前显示英语简介。
将数学概念、公式推导和算法执行过程制作成动画解说视频。使用Manim Community Edition，从内容规划、场景绘制到视频拼接，以图形辅助理解。
Create animated GIFs for Slack emoji and messages from uploaded images or drawn shapes. Adjust dimensions, colors, and frame rate, combine motion effects, and use included validation tools to check the finished file.
中文简介正在准备中。当前显示英语简介。
Turn a topic or script into a finished MP4 with MoneyPrinterTurbo. The skill handles installation, configuration, generation, and delivery, with support for voice-over, subtitles, background music, and recovery from fixable generation errors.
中文简介正在准备中。当前显示英语简介。
Create photos, illustrations, product mockups, and other bitmap images, or edit existing images by replacing backgrounds, removing objects, and making transparent cutouts. Use reference images to guide style, composition, or visual variants.
中文简介正在准备中。当前显示英语简介。
Plan or improve motion graphics by refining the message, typography, scene transitions, pacing, and timeline. It helps connect movement to meaning while leaving artifact creation and export to the active task's production workflow.
中文简介正在准备中。当前显示英语简介。
Plan artistic animations and explainer scenes using 35 style recipes, nine explanation patterns, storyboards, and reusable Canvas drawing code. Build motion within the host environment’s timeline, using its available tools for assets and export.
中文简介正在准备中。当前显示英语简介。
Generates short, single-shot videos for product reveals, teasers, and ambient loops. Plans the subject, movement, and lighting, then saves an MP4 in the project folder using the selected model, duration, and aspect ratio.
中文简介正在准备中。当前显示英语简介。
Create HTML-based videos with animated titles, synchronized captions, text-to-speech narration, scene transitions, and visuals that react to music. Define timing and layout, then check for overflowing content, readable contrast, and animation choreography.
中文简介正在准备中。当前显示英语简介。
Generate posters, key art, and editorial illustrations from a brief. The skill organizes composition, lighting, colors, and textures into an image prompt, then saves the result as a PNG or JPEG in the project folder.
中文简介正在准备中。当前显示英语简介。
Edit existing images, enlarge them, or remove their backgrounds through the Venice.ai API. This skill connects agent requests with these image processing tasks, helping prepare and adjust image assets for different uses.
中文简介正在准备中。当前显示英语简介。