AI Agent Skills

Create a dark HTML landing page that presents a software product through motion and a clear call to action. Useful for turning a product brief into a focused marketing page.

Present a product interface on a device in a dark studio setting. Plan the scroll, key interaction and final brand frame around your actual interface.

Pair a screen demonstration with checklist items that complete at chosen timestamps. Prepare your recording and action times for the sequence.

Reveal a brand mark through the refraction and rupture of a liquid bead. Useful for a compact visual opening or closing sequence.

Tell a product story through a prompt, streamed answer, follow-up action and final result inside an app interface. Plan the script around a real workflow.

Present a software product or waitlist with restrained sections and a clear narrative. Prepare real features and a focused next action for the visitor.

Lead an audience from analysis and evidence to a recommendation and implementation plan. Make the assumptions and decision points visible in the presentation.

AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.

Create beautiful slides on the web using a coding agent's frontend skills

Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user…

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks…

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and batch-capable image generation. Use…

Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 11 color palettes and 7 rendering styles. Supports cinematic (2.35:1),…

Direct and produce videos with Hypit, primarily through generated media and authored components while incorporating briefs, references or supplied material; includes SVM…

将本地视频或用户有权处理的在线视频，经过来源获取、文字稿定位、选题选句、精确取帧、紧凑裁切、3:4 拼图和逐张质检，制作成视频字幕社交长图。支持两种明确分开的输出：保留画面内已烧录字幕的原生字幕模式，以及把已审核的时间点与台词绘制到真实视频帧上的脚本字幕模式。用户要求原生字幕截图、字幕帧拼图、YouTube 金句长图、台词截图、不重绘字…