01-cinematic
Generate cinematic film-style video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants cinematic, film-like, movie-quality, Hollywood-style,…
Generate 3D CGI and rendered video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants 3D rendered, CGI, Pixar-style, Unreal Engine, photorealistic 3D, computer-generated, or digitally rendered video content. Triggers on: 3D animation, CGI, rendered, Blender,
$ npx -y skills add beshuaxian/higgsfield-seedance2-jineng --skill 02-3d-cgi --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/02-3d-cgiContext preview
The summary Claude sees to decide when to auto-load this skill.
Generate 3D CGI and rendered video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants 3D rendered, CGI, Pixar-style, Unreal Engine, photorealistic 3D, computer-generated, or digitally rendered video content. Triggers on: 3D animation, CGI, rendered, Blender,
name: seedance-3d-cgi description: Generate 3D CGI and rendered video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants 3D rendered, CGI, Pixar-style, Unreal Engine, photorealistic 3D, computer-generated, or digitally rendered video content. Triggers on: 3D animation, CGI, rendered, Blender, Unreal Engine, octane render, ray tracing, volumetric, subsurface scattering, physically based rendering, or any 3D/CG video request. Always use even if the user just says "make it look 3D" or describes a rendered aesthetic.
This skill guides you through creating world-class 3D CGI and rendered video prompts optimized for **Seedance 2.0 on Higgsfield**. Whether you're targeting Pixar-style animation, photorealistic product visualization, architectural walkthroughs, sci-fi environments, or creature animation, this framework provides the terminology, structure, and psychology needed to generate compelling CGI content.
The difference between a generic "make it look 3D" request and a production-ready CGI prompt lies in specificity: render engine terminology, material properties, lighting language, camera dynamics, and the architectural "hooks" that grab attention in the first two seconds. This skill teaches all of it.
---
**Seedance 2.0 on Higgsfield** is a generative video platform optimized for high-quality rendered content. It excels at:
**Key Constraint**: Prompts must be visual-first and technically descriptive. Vague requests ("make it look cool") are rejected. Specific render terminology significantly improves output quality.
---
Every successful CGI video begins with an immediate visual hook—something that stops the viewer's eye in the first two seconds. The subsequent 8 seconds develop the hook into a complete narrative or reveal.
The camera moves through impossible geometry at high speed. Used for: sci-fi spaces, architectural visualization, abstract environments, tunnel sequences. Example: "Camera hurtles through a crystalline tunnel, refracting light into fractals as we move."
Start with an extreme closeup—a water droplet, a grain of sand, a single fiber—then pull back to reveal it's part of something enormous. Example: "Begin on a single raindrop on a leaf. Pull back to reveal a forest canopy in a thunderstorm. Pull back further: a continent being drenched."
Utilize camera positions that human cameras can't occupy: inside glass, on the surface tension of water, rotating through a solid object's cross-section, or orbiting an object impossibly fast. Example: "Camera rotates around a spinning hourglass, rotating through its surface to show the sand inside in realtime."
Begin with thousands of small particles (dust, light, pixels, data) that coalesce into a recognizable 3D object. Example: "Golden particles swirl and coalesce into the shape of a dancing figure, settling into a detailed humanoid form."
Place a hyper-real object (like a perfect glass sphere or a photographic product shot) in an impossible or dreamlike environment. Example: "A pristine crystal crown sits alone on a floor of clouds while a aurora borealis swirls overhead."
One object smoothly transitions into another, often defying physics. Example: "A marble rolls across white space, morphing mid-motion into a silver sphere, then into a water droplet."
Start with a solid opaque object, then it becomes transparent or reflective, revealing internal structure. Example: "A stone statue begins to crack, light pouring through the fissures. The exterior dissolves to reveal a glowing core of molten light within."
Begin with extreme DOF (background/foreground blurred). Shift focus to reveal background, midground, or foreground in crisp detail while other planes blur. Example: "Focus on a dust particle suspended in light. Shift focus to reveal a vast interior architecture behind it."
Light bends, splits, or refracts, creating rainbow effects and optical distortion. Often used for luxury goods, technology, or abstract sequences. Example: "A prism catches sunlight, fragmenting the entire frame into a spectrum. The light gradually refracts around a product."
A structured object (building, sculpture, machine) disassembles into floating comp
15 个专业 Claude 技能,专为 Seedance 2.0(Higgsfield)打造。每个技能将 Claude 变成特定视频风格的提示词工程师——生成大型、详细、可直接使用的提示词,包含强力 2 秒钩子,让观众停止滑动。 15 specialized Claude skills built for Seedance 2.0 on Higgsfield.
Repo: beshuaxian/higgsfield-seedance2-jineng
Generate cinematic film-style video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants cinematic, film-like, movie-quality, Hollywood-style,…
Generate cartoon and animation style video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants cartoon, 2D animation, cel-shaded, hand-drawn,…
Convert comic book panels, manga pages, webtoons, and illustrated storyboards into animated video using Seedance 2.0 on Higgsfield. Use whenever the user wants…
Generate intense fight scene and action sequence video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants fight scenes, combat, martial arts,…
Generate motion design advertisement video prompts for software and tech companies using Seedance 2.0 on Higgsfield. Use whenever the user wants to create a…