seedance-social-hook

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass, no license.

- `Private` — Keep within team, full access control

cat ~/.ssh/id_ed25519.pub

Audit 0.4.1 · source sha 5b7a85fac65d · 20 Oct 2026Report an issue or request a re-scan

• Publisherbeshuaxian GitHub userOwner of the repository this skill is read from
• Source folderbeshuaxian/higgsfield-seedance2-jinengThe exact folder we audited
• LicenceNot declaredAs the repository states it
• Commit pinned for this verdict5b7a85fac65dA new audit runs when the source changes
• Repository statusNot archivedLast push 193 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: 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:…

---
name: seedance-cinematic
description: 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.
---

# Seedance 2.0 on Higgsfield — Cinematic Film-Style Prompt Generator

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

---

## What Seedance 2.0 on Higgsfield Accepts

**Input Specifications:**
- **Images:** Up to 9 images (reference materials, 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 beds)
- **Text:** Full prompt description and specifications
- **Combined Assets:** Maximum 12 total items across all categories
- **Output Duration:** 4–15 seconds of 720p video with synchronized sound
- **Special Syntax:** `@material[name]` references uploaded reference materials within prompts

**Output Characteristics:**
- High-quality 720p video with full audio integration
- Precise timing synchronization with input audio
- Motion that respects reference materials when provided
- Consistent rendering across sequential requests

---

## The 2-Second Hook Framework

**THE CRITICAL PRINCIPLE:** In cinematic storytelling, you have exactly 2 seconds to stop the scroll, catch the eye, and demand sustained attention. This is the difference between viral and invisible.

### Why 2 Seconds?
- **Neuroscience:** Human attention triggers in 0.5–2 seconds at the unconscious level
- **Platform Reality:** TikTok, Instagram, YouTube shorts all show algorithmic preference for videos that hold viewers past the 2-second mark
- **Cinematic Principle:** Great films open with impact—think *Blade Runner 2049* (neon city glow), *Dunkirk* (immediate chaos), *1917* (tracking shot tension)
- **Retention Metric:** Videos that win in the first 2 seconds have 3–5x higher completion rates

### The Hook Table: 10+ Cinematic Techniques

| Hook Technique | Cinematic Effect | Prompt Phrasing Template |
|---|---|---|
| **Extreme Close-Up Snap to Wide Reveal** | Disorientation → context clarity, visual shock | "Open with extreme macro close-up of [detail: water droplet, dust mote, fabric weave]. At 0.5s, whip cut to extreme wide shot of [landscape/space]. Contrast ratio 100:1." |
| **Black Screen to Dramatic Light Burst** | Silence then explosion, creates tension release | "Begin in pure black. At 0.8s, explosive light burst from [direction: top-left corner]. Golden/amber light floods frame in 0.3s. Lens flare blooming across center." |
| **Reverse Motion That Catches the Eye** | Unnatural = immediately interesting to human brain | "Action moves backwards in first 2 seconds: [object] slides in reverse across frame with momentum. Water droplets float upward. Smoke swirls counterclockwise. Hypnotic, impossible motion." |
| **Unexpected Scale — Macro Detail of Familiar Object** | Cognitive dissonance, viewers lean in to understand | "Extreme macro photography of mundane object: fabric texture, concrete pores, leaf veins, raindrop surface. Treat as vast landscape. Shallow depth of field, cinematic bokeh. Viewer doesn't recognize scale for 2 seconds." |
| **Silent Beat Then Explosive Sound** | Audio contrast creates visceral impact | "First 1.2 seconds: complete silence. No dialogue, no music, minimal ambient. At 1.3s, sudden violent sound: gunshot, explosion, door slam, music drop. Synchronized video cut/freeze/blur at audio moment." |
| **Extreme Color Shift** | Palette punch, immediate visual identity | "Frame opens in cool desaturated blue-grey. At 0.6s, sudden color correction to warm amber-gold or saturated neon. 50% color shift in 0.4s. Creates 'time jump' or 'reality shift' feel." |
| **Fast Movement Entering Frame** | Motion catches peripheral vision, forces eyes to track | "Subject enters frame with high-speed movement: speeding car, sprinting figure, falling object, camera push-in at high velocity. Enter from edge (not center), create leading lines, 3–5 mph equivalent speed." |
| **Extreme Depth of Field Rack Focus** | Draws attention via focus, professional cinema technique | "Two planes of focus: foreground and background both sharp initially. At 1s, focus racking to dramatic foreground (completely blurring background), or vice versa. Shallow depth (f/1.4 cinema equivalent). Creates instant depth." |
| **Stark Geometric Contrast** | Visual tension, compositional power | "Frame composition: extreme geometric contrast in first 2s. Sharp horizontal lines vs vertical elements, or concentric circles vs straight edges. High-contrast lighting emphasizes geometry. Asymmetrical frame." |
| **Protagonist's Eyes Open/Look** | Primal human attention grab | "Close shot of eyes in low-light. At 0.8s, eyes snap open or lock on-camera. Dilating pupil effect optional. Followed by subtle head tilt or eye direction shift. Most primal form of attention capture." |
| **Disorienting Camera Rotation** | Immediate sensory engagement | "Camera tilts, rolls, or rotates rapidly in frame 0–1.5s. 45°–180° rotation. Tilted horizon line. Creates slight vertigo. Stabilizes to level frame at 2s marker. Signals 'something is wrong/happening.'" |
| **Scale Impossibility (Tiny in Vast or Huge in Small)** | Awe or claustrophobia | "Tiny human figure in impossibly vast landscape [desert, ocean, space]. OR giant object in confined space

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/beshuaxian/higgsfield-seedance2-jineng
git -C higgsfield-seedance2-jineng checkout 5b7a85fac65d

Works in

1. 2026-10-20
   ✓SAFE B 89 / 100

   first audit · source 5b7a85fac65d

Questions about seedance-social-hook

• github.com/beshuaxian/higgsfield-seedance2-jineng — the audited source at commit 5b7a85fac65d and every finding aboveObserved · 20 Oct 2026

Spotted something wrong? Report a correction · Methodology