Communitygithub.com

Biznomad/claude-skills

Generates cinematic film-style video prompts for Seedance 2.0 (Higgsfield). Use this skill when the user wants cinematic, film-like, movie-quality, Hollywood-style, dramatic, or professional film-quality AI videos. Trigger words: cinematic, film look, movie scene, dramatic lighting, depth of field, lens flare, anamorphic, letterbox, film noir, epic, stable camera, dolly shot, crane shot, or any cinematic video generation request. Activate this skill even if the user does not explicitly say 'cinematic' but describes a film aesthetic.

What is claude-skills?

This skill transforms creative video ideas into precise, production-grade prompts optimized for Seedance 2.0 (Higgsfield), an AI video generation platform. It provides a comprehensive framework for crafting cinematic film-style videos, covering camera language, lighting design, color grading, depth of field, and motion design. The skill includes a '2-second hook framework' to design compelling openings, a layered language architecture (from camera types to color psychology), and complete prompt templates with timecodes and reference integration. It supports optional multimedia inputs (images, videos, audio) and outputs 4-15 second 720p videos with synchronized audio. By structuring prompts with clear intent—every lighting choice, camera movement, and color decision serves the story—the skill helps users consistently achieve Hollywood-quality, professional film aesthetics.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Biznomad/claude-skills/tree/HEAD/seedance-01-cinematic/zh-CN

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Seedance 2.0 (Higgsfield) – Cinematic Film-Style Prompt Generator

Welcome to the ultimate guide for crafting blockbuster-quality video prompts on Seedance 2.0 (Higgsfield). This skill transforms your creative vision into precise, production-grade prompts that produce stunning cinematic sequences.


What Seedance 2.0 (Higgsfield) Accepts

Input Specifications:

  • Images: Up to 9 images (references, storyboards, mood boards, character designs, location photos)
  • Videos: Up to 3 video clips (existing footage, transitions, motion references)
  • Audio: Up to 3 audio files (music tracks, sound effects, dialogue recordings, ambient sound beds)
  • Text: Full prompt descriptions and specifications
  • Combined Assets: Up to 12 items across all categories
  • Output Duration: 4-15 second 720p video with synchronized audio
  • Special Syntax: @material[name] to reference uploaded assets in prompts

Output Characteristics:

  • High-quality 720p video with full audio integration
  • Precise timing synchronization with input audio
  • Motion that respects provided references
  • Consistent rendering across sequential requests

2-Second Hook Framework

Cinematic video success depends on the first two seconds of appeal. This framework helps you design compelling openings.

Core Concept

Hook = a strong visual promise + a unique aesthetic statement

The first two seconds should clearly convey:

  1. Visual Type (what kind of image is this?)
  2. Emotional Tone (how does it feel?)
  3. Motion Promise (what will happen next?)

2-Second Hook Framework Template

[MOMENT 0–1 sec]: [Visual Impact] + [Lighting Characteristic]
[MOMENT 1–2 sec]: [Camera Movement] + [Depth Cue]

Examples of Cinematic Hooks

Example 1: Film Noir Suspense

MOMENT 0–0.5 sec: Dim red neon reflecting on wet pavement. High contrast, foggy.
MOMENT 0.5–1 sec: Close-up pulling back from eyes, revealing a bruised face. Soft focus edges.
MOMENT 1–2 sec: Steadicam panning right, deep foggy layers.

Example 2: Sci-Fi Epic

MOMENT 0–1 sec: A grand futuristic city skyline with extreme depth of field, distant city blurred. Golden sunset.
MOMENT 1–2 sec: Crane shot lifting upward, revealing the scale of the city. Digital lights sweeping across skyscrapers.

Example 3: Romantic Driving Scene

MOMENT 0–1 sec: A vintage convertible driving past the viewer, side-lit. Lens flare.
MOMENT 1–2 sec: Cut to inside the car, character turns head, golden hour light through windows. Shallow depth of field.

Language Architecture for Cinematic Video

Layer 1: Camera Language

Camera Types and Movement

TechniqueDefinitionWhen to Use
Dolly Zoom In/OutSlow, fluid forward or backward movementDramatic revelation, establishing shots, emotional moments
Dolly ShotLateral sliding movement, often tracking a subjectFollowing characters, showing scene depth
Crane ShotArc movement up or downEstablishing panoramas, revealing environmental scale
PanRotation around an axisRevealing environmental information, dramatic turns
ZoomFocal length change (optical or digital)Emphasizing important elements, quick shifts
Aerial Drone ShotWide view from a high angleLarge-scale scenes, location establishment, chases
Over-the-Shoulder ShotShot over a subject's shoulderDialogue, confrontation, interactive moments
Low Angle ShotShot from below looking upPower, intimidation, threat
High Angle ShotShot from above looking downWeakness, vulnerability, isolation

Layer 2: Lighting Design

Lighting Tones and Styles

StyleCharacteristicsCommon Application
High Key LightingBright, even, minimal shadowsHope, safety, optimistic scenes
Low Key LightingHigh contrast, dramatic shadows, dark areasMystery, danger, suspense, horror
Cinematic Ratio3:1 to 5:1 key-to-fill ratioStandard film look, sense of depth
Rim Light/BacklightLight hitting the subject from behindSeparating subject from background, three-dimensionality
Single Source LightingUsing only one key light sourceDrama, emphasizing form, stylization
Multi-Color LightingMultiple sources with warm/cool contrastComplex emotions, dynamic scenes
Practical LightIn-scene light sources like fire, neon, lampsRealism, location authenticity

Lighting Color Psychology

Golden/Amber Hour Light → warmth, nostalgia, romance
Cool Blue → isolation, sci-fi, unease
Red/Orange → tension, danger, passion
Green → unnatural, sickly, sci-fi
Monochrome Black & White → timeless, classic, emphasis on form

Layer 3: Color Grading and Psychology

Strategic Use of Color Palettes

Warm Tones (Gold, Amber, Red) →
- Use cases: Sunrise, campfires, home interiors, flashback
- Emotions: warmth, safety, nostalgia, love

Cool Tones (Blue, Cyan, Purple) →
- Use cases: Night, underwater, sci-fi, death scenes
- Emotions: isolation, mystery, unease, transcendence

Desaturated/Faded (Low Saturation) →
- Use cases: War films, psychological dramas, memories
- Emotions: despair, weariness, sense of age

High Saturation/Vivid →
- Use cases: Action, adventure, comedy
- Emotions: energy, excitement, drama

Layer 4: Depth of Field (DOF) and Focus

Depth of Field Strategies

StrategyVisual EffectEmotional Impact
Shallow DOF (f/1.4–f/2.8)Sharp subject, blurred backgroundIsolation, intimacy, focus
Medium DOF (f/2.8–f/5.6)Subject and some background clearBalanced emphasis
Deep DOF (f/8+)Everything sharpEnvironmental awareness, panoramic information
Rack FocusFocus shifts during the shotRevealing information, guiding attention
Optical FlareBackground lights beautifully out of focusCinematic quality, dreamy, romantic

Layer 5: Motion Design and Rhythm

Motion Types and Meaning

Linear Motion → purpose, decisiveness, forward momentum
Parabolic Motion → natural, fluid, graceful
Angular Motion → impact, speed, tension
Eased Motion → weight, power, physics
Staccato Motion → surprise, energy, shock

Layer 6: Using References

Effectively leveraging @material references for cinematic aesthetics.

Texture Reference

prompt = "A tabletop with @material[wood_texture] as the main surface, paired with @material[leather_chair].
Soft side light scraping texture details. Cinematic ratio 3:1."

Color Reference

prompt = "Futuristic city skyline, blending colors from @material[cyberpunk_color_palette].
Gold and deep purple neon. Rim light ambient lighting."

Motion Reference

prompt = "Adopt the Steadicam motion style from @video[slow_dolly_example].
Use soft focus and cinematic transitions."

Full Prompt Template

Standard Cinematic Scene Template

[Scene Setup]
In [location], at [time]. [Environmental description].

[Visual Design]
Camera: [Camera type] [Camera movement]
Lighting: [Key light source] [Lighting ratio] [Lighting color]
Focus: [Depth of field selection] [Focus position]
Color Grading: [Palette description]

[Action and Progression]
[Timecode 0–1 sec]: [Action/change]
[Timecode 1–2 sec]: [Camera action/reveal]
[Timecode 2–]: [Climax/twist]

[Emotional Tone]
[Tone and mood]

[@material References]
Reference: @material[name1], @material[name2]

Example 1: Film Noir Night Scene

Scene: Rainy city street, midnight. Wet cement reflecting neon.

Visual Design:
Camera: Steadicam panning right, tracking character
Lighting: Single key light from upper left. Low key. Contrast 5:1. Deep blue and red neon.
Focus: Shallow DOF (f/2.0). Focus on the character's eyes.
Color Grading: Desaturated. Cool blue in shadows. High saturation red in neon.

Action:
0–1 sec: Raindrops hitting camera lens. Lens wipe. Visible reflected neon.
1–2 sec: Camera dolly in on the character's black jacket. Rain streaming down his face.
2–4 sec: Crane shot lifting up, revealing empty street. Single red neon sign.
4–6 sec: Steadicam pan, character turns, dramatic backlight.

Emotional Tone: Mystery, danger, isolation. Suspense.

Advanced Prompt Optimization

1. Sequence and Continuity

To chain multiple "film scenes" into a coherent story:

[Scene 1 – Setup]: Camera wide pull. Lighting establishes location.
[Scene 2 – Dialogue]: Switch to over-the-shoulder shot. Lighting and color match Scene 1.
[Scene 3 – Action]: Crane shot. Tense music.
[Scene 4 – Climax]: Quick montage. Bright flashes. High contrast.

Ensure color grading is consistent across scenes. Keep lighting logical (sun's light always from same direction).

2. Audio Sync

prompt = "Dialogue scene. Character says: 'This isn't what it looks like.'
Lighting switches to cool blue. Camera slowly dollies in.
Sync audio rhythm: 500ms pause before keywords in each sentence."

3. VFX and Elements

prompt = "Sci-fi cockpit. Green holographic elements on screens.
Steadicam rotates to track hologram.
Emphasis: Hologram blinks in sync with dialogue.
Lighting: Backlit hologram, deep blue and green."

4. Special Effects & Optical FX

prompt = "City skyline sunset. Add lens flare effect (15 degree lens).
Add glow: light points become blurry.
Add chromatic aberration: distant red/cyan shift on building edges.
Lighting: Golden sunlight. Background blurry. Foreground sharp."

Common Pitfalls and Fixes

ProblemCauseSolution
Blurry visualsUnclear lightingSpecify key and fill light ratio
Flat lookLack of depthAdd shallow DOF and background blur
Unnatural colorsOversaturationUse color grading with contrasting warm/cool hues
Motion looks jerkyInsufficient easingSpecify "ease in and out" and "fluid motion"
Scene inconsistencyLighting and color change between shotsCreate a "lighting card," consistent for the whole sequence
Unclear what's happeningCamera too staticAdd distinct camera movement to guide attention

Prompt Engineering Checklist

Before submitting a cinematic prompt:

  • Is there a clear key light source for the lighting?\n- [ ] Is depth of field and focal plane specified?\n- [ ] Is camera movement clear and purposeful?\n- [ ] Does color grading support the emotional tone?\n- [ ] Does the action have a "hook" within 2 seconds?\n- [ ] Are all references tagged with @material[name]?\n- [ ] Are timecodes clear and realistic?\n- [ ] Is there audio sync guidance for dialogue or sound effects?

Quick Style Reference

Hollywood Blockbuster

Key light from 45 degree angle. Clear backlight.
Shallow depth of field (f/2.8).
Camera slowly dolly in or Steadicam.
Color grading: warm golden sunlight or cool blue night.

TV Documentary Style

Natural lighting. Ambient light.
Deep depth of field (f/5.6+).
Occasional handheld movement.
Low saturation color grading.

Art Film

Asymmetric lighting. Heavy shadows.
Extreme depth of field choices (very shallow or very deep).
Unusual camera angles and movement.
Expressive color grading or monochrome.

Music Video

Highly stylized lighting.
Strong color grading.
Dynamic camera movement synced with music.
Oversaturated or surreal palette.

Final Prompt

The secret to cinematic filmmaking is not in luxury or special effects—it's in clarity of intent. Every light, camera movement, and color choice should serve the story or emotion.

Use this framework as your creative toolkit, not a constraint. The greatest films often break the rules, but they do so for a clear artistic purpose.

Happy creating on Seedance 2.0 (Higgsfield)!

Individual skills in this repo

This repo contains 17 individual skills — each has its own dedicated page.

Biznomad/claude-skills

TikTok Ads deep analysis covering creative quality, tracking, bidding, campaign structure, and TikTok Shop. Evaluates 25 checks with emphasis on creative-first strategy, safe zone compliance, and Smart+ campaigns. Use when user says "TikTok Ads", "TikTok marketing", "TikTok Shop", "Spark Ads", "Smart+", or "TikTok campaign".

Biznomad/claude-skills

YouTube Ads specific analysis covering campaign types, creative quality, audience targeting, and measurement. Evaluates video ad performance across skippable, non-skippable, bumper, Shorts, and Demand Gen formats. Use when user says "YouTube Ads", "video ads", "pre-roll", "bumper ads", "YouTube campaign", or "Shorts ads".

Biznomad/claude-skills

Help users get promoted at work. Use when someone is preparing for a promotion conversation, building their case for advancement, trying to understand what's blocking their promotion, or figuring out how to get to the next level in their career.

Biznomad/claude-skills

CSS animation adapter patterns for HyperFrames. Use when authoring CSS keyframes, animation-delay based timing, animation-fill-mode, animation-play-state, or CSS-only motion that HyperFrames must seek deterministically during preview and rendering.

Biznomad/claude-skills

HyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.

Biznomad/claude-skills

Asset preprocessing for HyperFrames compositions — text-to-speech narration (Kokoro), audio/video transcription (Whisper), and background removal for transparent overlays (u2net). Use when generating voiceover from text, transcribing speech for captions, removing the background from a video or image to use as a transparent overlay, choosing a TTS voice or whisper model, or chaining these (TTS → transcribe → captions). Each command downloads its own model on first run.

Biznomad/claude-skills

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, and registry discovery.

Biznomad/claude-skills

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the hyperframes-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the hyperframes-media skill.

Biznomad/claude-skills

Optimize landing pages for higher conversion rates using proven frameworks and design patterns. Use when designing, reviewing, or improving landing pages, hero sections, pricing pages, CTAs, or when the user asks about conversion optimization.

Biznomad/claude-skills

Building promotion cases, brag documents, tracking wins, and self-advocacy for career advancement. Use when preparing for promotions, documenting accomplishments, or building your case for advancement.

Biznomad/claude-skills

Translate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames (e.g. "port my Remotion project to HyperFrames"). Do NOT use when (a) authoring a NEW HyperFrames composition (even if A/B-testing a Remotion video); (b) Remotion is mentioned in passing; (c) Remotion code is shared as reference, not for translation; (d) the user wants "the same video as my Remotion one" without explicitly asking to migrate the source — treat as a fresh HyperFrames build. When in doubt, default to the `hyperframes` skill. Detects unsupported patterns (useState, useEffect side effects, async calculateMetadata, third-party React component libraries, `@remotion/lambda`) and recommends the runtime interop escape hatch instead of a lossy translation.

Biznomad/claude-skills

Produce programmable videos with Remotion using scene planning, asset orchestration, and validation gates for automated, brand-consistent video content.

Biznomad/claude-skills

Generate cinematic film-style video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants cinematic, film-like, movie-quality, Hollywood-style, dramatic, or professional film-quality AI video. Triggers on: cinematic, film look, movie scene, dramatic lighting, depth of field, lens flare, anamorphic, letterbox, noir, epic, Steadicam, dolly, crane shot, or any cinematic video generation request. Always use this skill even if the user doesn't explicitly say "cinematic" but describes a film-like aesthetic.

Biznomad/claude-skills

Convert comic book panels, manga pages, webtoons, and illustrated storyboards into animated video using Seedance 2.0 on Higgsfield. Use whenever the user wants to animate comics, bring illustrations to life, convert manga to video, animate storyboards, or create motion from static sequential art. Triggers on: comic to video, manga animation, panel animation, storyboard to video, webtoon animation, comic book motion, sequential art, graphic novel animation, or any illustrate-to-animate request. Use even when user says "make this drawing move" or "animate this page.

Biznomad/claude-skills

Generate music video and beat-synced visual content prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants to create a music video, lyric video, beat-synced visuals, performance video, concert visual, album art animation, or music-driven visual content. Triggers on: music video, lyric video, beat sync, music visualization, performance video, concert visual, album visual, song video, music clip, beat drop visual, rhythm sync, or any music-driven video request. Use even for "make visuals for my song" or "video for this track.

Biznomad/claude-skills

Build, redesign, and deploy websites across any stack — static HTML, Next.js, Astro, or Shopify Liquid themes. Handles design systems, brand-aware layouts, component architecture, and deployment pipelines (Netlify, Vercel, Shopify API). Use when asked to build a website, redesign a site, create a landing page, build a web app, create Shopify sections/templates, or deploy web projects. Triggers on requests like "build me a website", "redesign this page", "create a landing page", "build a Shopify theme", "deploy to Netlify".

Biznomad/claude-skills

Capture a website and create a HyperFrames video from it. Use when: (1) a user provides a URL and wants a video, (2) someone says "capture this site", "turn this into a video", "make a promo from my site", (3) the user wants a social ad, product tour, or any video based on an existing website, (4) the user shares a link and asks for any kind of video content. Even if the user just pastes a URL — this is the skill to use.

Related Skills