Skip to content
Content
Skill

/05-faceless-channel

Generate faceless content video prompts for Seedance 2.0 on Higgsfield. Use for faceless YouTube channels, TikTok content without showing face, anonymous creator content, narration-driven videos, stock-footage-style AI content, or any video where the creator doesn't appear on

From plugin
ai-video-generator-claude
44510 skills

Claude Code

$ npx -y skills add rediumvex/ai-video-generator-claude --skill 05-faceless-channel --agent claude-code

SKILL.md

05-faceless-channel.SKILL.md
name: seedance-faceless-channel
description: Generate faceless content video prompts for Seedance 2.0 on Higgsfield. Use for faceless YouTube channels, TikTok content without showing face, anonymous creator content, narration-driven videos, stock-footage-style AI content, or any video where the creator doesn't appear on camera. Triggers on faceless, no face, anonymous, narration, stock footage, b-roll, background video, voiceover video.

Faceless Channel — No-Camera Content Video Prompts

---

Input Specs — Seedance 2.0 Format

When generating a prompt, collect or infer:

| Field | Description | Example | |---|---|---| | **Topic** | Subject matter of the video | "The collapse of Silicon Valley Bank" | | **Platform** | Target platform and aspect ratio | YouTube 16:9 / TikTok 9:16 / Reels 9:16 | | **Duration** | Clip length in seconds | 5s / 8s / 10s | | **Mood** | Emotional tone | cinematic / moody / energetic / calm | | **Style** | Visual language | documentary / motion graphics / aesthetic / abstract | | **Sound priority** | Narration-first or music-first | narration-first | | **Hook type** | Opening pattern | visual metaphor / data reveal / satisfying loop / impossible scene |

Seedance 2.0 prompt structure:

[SCENE DESCRIPTION] — [CAMERA MOVEMENT] — [LIGHTING] — [MOOD/ATMOSPHERE] — [MOTION DETAILS] — [SOUND DIRECTION]

Each prompt block should be 15–25 lines covering: scene, camera, lighting, timing breakdown, motion notes, and sound direction.

---

Three Laws of Faceless Content

1. **Never let the screen rest.** Every second needs motion — camera, subject, or both. 2. **The first frame is the thumbnail.** The opening shot must be arresting on its own. 3. **Lighting is character.** Without a face, emotion comes from color temperature, contrast, and shadow.

---

2-Second Hook Table

The first 2 seconds determine whether the viewer swipes. Use one of these four proven patterns:

| Pattern | Description | Visual Execution | Best For | |---|---|---|---| | **The Visual Metaphor** | Open on a powerful image that symbolizes the entire video's thesis | Extreme close-up of a burning dollar bill, then pull back to reveal a city skyline | Finance, business, history channels | | **The Data Reveal** | Numbers or statistics materialize on screen in a visually dramatic way | Counter spinning rapidly then freezing on a shocking number, overlaid on relevant environment | News, education, statistics-driven content | | **The Satisfying Loop** | A seamless, hypnotic motion that locks the eye before the brain can decide to swipe | Fluid pouring, sand falling, clouds rolling — perfectly timed to feel infinite | Meditation, ASMR, aesthetic channels | | **The Impossible Scene** | A physically impossible or hyperreal visual that creates instant curiosity | A city at the bottom of the ocean, a forest growing in fast-forward inside a skyscraper atrium | Sci-fi, speculative, "what if" channels |

---

Visual Style Templates

1. Cinematic B-Roll

**Best for:** Documentary, history, finance, crime, geopolitics

  • Color grade: teal-orange or desaturated with selective color pops
  • Depth of field: shallow — always keep one plane soft
  • Frame composition: rule of thirds strictly, negative space for text overlay
  • Motion: slow push-ins and parallax reveals preferred; avoid handheld shake
  • Texture: film grain overlay at 15–20% opacity adds perceived production value
  • Key rule: never show the same environment from the same angle twice in one video

2. Motion Graphics Hybrid

**Best for:** Tech explainers, startup breakdowns, tutorials

  • Blend live-action environment with floating UI elements, data flows, or particle systems
  • Color palette: dark background (near-black), neon accent (electric blue, hot pink, or lime)
  • Typography: kinetic text that materializes in sync with narration beats
  • Motion: camera orbits around 3D elements; environment rotates slowly in background
  • Light sources: internal — glowing elements, screens, holographic panels
  • Key rule: every data point gets a visual representation, never just spoken

3. Ambient Aesthetic

**Best for:** Mindset, productivity, study-with-me, lo-fi, wellness

  • Color grade: warm golden hour, cool twilight, or monochrome with single color pop
  • Motion: ultra-slow — drift, float, breathe; never rush
  • Subjects: coffee steam, rain on windows, pages turning, candle flames, neon reflections in puddles
  • Camera: imperceptible push-in or very slow orbit; never a cut under 3 seconds
  • Sound design: ambient sound leads, music is secondary texture
  • Key rule: every frame should be screenshot-worthy as a wallpaper

4. Documentary Reconstruction

**Best for:** True crime, history, investigative journalism, case studies

  • Color grade: desaturated, slightly green-shifted for "found footage" feel; or high-contrast black-and-white
  • Camera: handheld simulation with subtle drift (not shake); occasional security-camera framing
  • Subjects: empty locations that imply presence — a chair, a document, a phone screen
  • Light: motivated by in-scene sources (desk lamp, phone glow, streetlight through blinds)
  • Typography: timestamps, case numbers, location tags in Courier New or mono fonts
  • Key rule: never show a face; imply the human through objects and traces

---

Camera Movement Library

Push & Pull

  • **Slow push-in (8–10s):** Creates building tension. Use for reveals and escalating narration.
  • **Pull-back reveal:** Starts tight on a detail, expands to show scale. Best hook technique.
  • **Crash zoom:** Sudden fast push to a single element. Punctuates a data point or shocking stat.

Orbit & Rotate

  • **Slow orbit (360°, 10–15s):** Best for product shots, architectural subjects, 3D elements.
  • **Partial orbit (45–90°):** Shows depth without disorienting. Use on static subjects in environment.
  • **Tilt orbit:** Orbits while tilting up or down — creates a sense of discovering the full scale of a scene.

Float & Drift

  • **Horizontal
Read more
@rediumvex
Ships withai-video-generator-claude

10 prompt engineering skills that turn Claude into a cinematic video director for Seedance 2.0 on Higgsfield. You describe an idea — the skill architects a 15-25 line production-grade prompt with exact timing, camera angles, lighting setup, and sound design.

Stars on GitHub

Momentum

stars in total
445
Star history of rediumvex/ai-video-generator-claude on GitHub, a chart by star-history.com

Other skills on ai-video-generator-claude.

More skills from other plugins.

prompt-lookup

prompt-lookup

Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use…

@gh-f@gh-fInstall Skill
ppt-master

ppt-master

AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable…

@hugohe3@hugohe3Install Skill
morph-ppt

morph-ppt

Use this skill when the user wants a .pptx with smooth cross-slide animation — PowerPoint Morph transitions, Keynote-style…

officecli12d33k
@iofficeai@iofficeaiInstall Skill

Questions about 05-faceless-channel.

Which coding agents can use 05-faceless-channel?
05-faceless-channel installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.