AI Agent Skills

Use when implementing an unfamiliar PlayCanvas feature such as animation, particles, shaders, physics, UI, splats, or XR to find the official Engine, React, or Web Compo…

Sogni Creative Agent: image, 3D, speech, video, and music generation using Sogni AI's decentralized GPU network. Supports personas, persistent memories, custom personali…

Audits a stateful game's specification, phase/state machine, implementation, presentation, and tests for scenario-specific omissions such as one phase missing an input a…

Designs and validates event-driven retro-arcade sound kits (SFX + jingles) where game code emits abstract event names and an adapter/synth layer maps and plays them. Use…

The voice-mode skill owns the conversation’s delivery and interaction behavior when the user needs to listen instead of look at a display. It triggers on explicit “/voic…

Use this skill whenever motion, animation, timing, easing, or composition over time is the subject. Triggers on "animate", "motion", "easing", "timing", "keyframe", "tra…

Use this skill when something has gone wrong, looks wrong, or needs a second opinion. Triggers on: "something looks off", "this doesn't look right", "why is this happeni…

Create accurate visual explainers for non-specialists, covering intuition, mechanisms, examples, and boundaries in a standalone HTML page. Use when the user invokes ELI5…

将故事创意转化为 3D 动画短片，依次完成简报、角色与场景卡、镜头表、分镜、片段、BGM 和成片。适用于皮克斯 / 迪士尼 / Q 版 / 动态图形风格，并强调口型安全、单镜单说话人、变身锚点与连续性控制。

根据剧情与参考素材制作30–90秒、16:9横屏的日本90年代赛璐璐 City Pop短片，完成连续性资产、分段分镜、视频、声音与剪辑；不用于静图或简单图生视频。

将已授权品牌素材、官网链接或推广创意制作成品牌宣传短片。先核验品牌事实和素材来源，再确定叙事与节拍、生产音画素材并合成交付；适用于新品、网站、应用和社交推广，不用于虚构主张、仿造未授权标识或长篇剧情片。

将神话、民间、古典与文化题材创意或剧本，按上影美术电影制片厂气质完成故事、风格、角色场景设定、分镜视频、声音、合成与复核。适合民族动画短片，不用于真人剪辑、海报或无关风格。

Use when a HyperFrames composition needs a punch-in, punch-out, zoom, reframe, Ken Burns treatment, camera move, visual match/whip handoff, or other seek-safe 2D/3D keyf…

在用户要求持续监控已登记视频任务、下载结果或停止已有监控时使用。

查询已登记视频任务、下载完成视频，或处理需要授权重试与创作修正的失败。

Use when Creator needs current Dreamina image/video capabilities, configuration diagnosis, or authorized generation and recovery.