Skip to content
Content
Skill

/04-course-promo

Generate online course and coaching program promotional video prompts for Seedance 2.0 on Higgsfield. Use for course trailers, coaching ads, educational content promos, masterclass teasers, webinar promotions, or any educational product video. Triggers on course, coaching,

From plugin
ai-video-generator-claude
32210 skills
Install
$ npx -y skills add rediumvex/ai-video-generator-claude --skill 04-course-promo --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/04-course-promo

Context preview

The summary Claude sees to decide when to auto-load this skill.

Generate online course and coaching program promotional video prompts for Seedance 2.0 on Higgsfield. Use for course trailers, coaching ads, educational content promos, masterclass teasers, webinar promotions, or any educational product video. Triggers on course, coaching,

SKILL.md

04-course-promo.SKILL.md
name: seedance-course-promo
description: Generate online course and coaching program promotional video prompts for Seedance 2.0 on Higgsfield. Use for course trailers, coaching ads, educational content promos, masterclass teasers, webinar promotions, or any educational product video. Triggers on course, coaching, masterclass, webinar, tutorial, education, teaching, training, class, program, academy.

Course Promo — Educational Product Video Prompts

---

Seedance 2.0 Input Specifications

Seedance 2.0 accepts multi-modal inputs and produces short-form cinematic video output. Before writing any prompt, confirm the assets available:

**Image inputs** — up to 9 images

  • Reference the first image as `@material[image1]`, second as `@material[image2]`, and so on
  • Use for: instructor headshots, course mockups, student result screenshots, before/after photos, slide previews, community screenshots, device mockups showing the course platform

**Video inputs** — up to 3 short video clips

  • Reference as `@material[video1]`, `@material[video2]`, `@material[video3]`
  • Use for: existing testimonial clips, talking-head snippets, screen recordings of the course interface, b-roll of the instructor in action

**Audio inputs** — up to 3 audio files

  • Reference as `@material[audio1]`, `@material[audio2]`, `@material[audio3]`
  • Use for: background music track, voiceover narration, sound effects layer

**Output specs**

  • Duration: 4–15 seconds per generation
  • Resolution: 720p
  • Aspect ratios: 9:16 (Reels/TikTok/Shorts), 16:9 (YouTube/Webinar landing), 1:1 (Feed)
  • Chaining multiple generations creates a full 30–90 second promo sequence

**Prompt length sweet spot:** 120–250 words per generation. Too short = generic output. Too long = model ignores later instructions.

---

Asset Checklist Before Writing Any Prompt

Before generating a prompt, answer these questions:

  • [ ] What is the course/program name and price point?
  • [ ] What is the primary platform (Instagram, YouTube, Facebook, email)?
  • [ ] What is the video duration target?
  • [ ] What assets are available? (List all images, videos, audio files with their @material tags)
  • [ ] Who is the target student? (One sentence description of their current painful state)
  • [ ] What is the single transformation promise? (One sentence: "Go from X to Y in Z time")
  • [ ] What is the CTA action? (Register, buy, apply, watch, join — pick one)
  • [ ] Is there a deadline or urgency element? (Enrollment closing, live event date, bonus expiring)

---

Philosophy

Every course promo follows one arc:

`Hook (tension/curiosity) → Evidence (authority/social proof) → Transformation (the future state) → CTA (one clear next step)`

---

2-Second Hook Patterns

The hook is the first 2 seconds of the video. It must work without sound. Design it visually before writing anything else.

| Hook Pattern | Visual Signal | Emotional Mechanism | Best For | |---|---|---|---| | **The Knowledge Gap** | Split screen: wrong way (frustrated, messy desk, error screen) vs. right way (clean, confident, results visible) | Curiosity + mild anxiety relief | Skill-based courses, coding, design, marketing | | **The Transformation Promise** | Single subject, before posture vs. after posture in rapid cut — slouched scrolling phone → standing confident, phone showing income notification | Hope + aspiration | Coaching programs, fitness, business, mindset | | **The Exclusive Access** | Camera slowly pushes through a half-open door into a warmly lit room with a whiteboard full of insider frameworks — the viewer is being let in | Intrigue + belonging | Masterclasses, premium memberships, inner circles | | **The Social Proof Flash** | Rapid montage of 4–6 results cards or testimonial stills, each on screen for 12 frames — too fast to read fully but pattern-registers as "many people succeeded" | FOMO + credibility | Established courses with a results library | | **The Authority Reveal** | Close-up of hands writing a key framework on paper or whiteboard, camera slowly pulls back to reveal the instructor's confident face | Respect + curiosity | Expert-led programs, consulting, high-ticket coaching | | **The Relatable Struggle** | Single frame of a person staring at a blinking cursor, overflowing inbox, or blank spreadsheet — paused in the moment before the breakthrough | Empathy + identification | Any course solving a specific frustrating problem |

**Hook construction rule:** Write the hook shot description first. If you cannot describe it in one sentence that would make sense to a stranger, it is not specific enough.

---

Visual Style Templates

Template A — The Classroom Cinematic

**Mood:** Warm, expert, aspirational. Feels like a premium Netflix documentary about a genius teacher.

**Core visual grammar:**

  • Deep focus on the instructor, soft bokeh on background bookshelves or whiteboards
  • Color grade: warm tones, slightly desaturated highlights, rich shadow detail (not crushed blacks)
  • Camera movement: slow push-in on instructor face during key points; static wide during environment reveals
  • Text overlays: clean serif or geometric sans, large single words, white with subtle drop shadow
  • Transitions: hard cuts within sequences, slow dissolves between sections

**When to use:** High-ticket coaching (>$1,000), professional skill courses (law, finance, medicine), executive education

**Input pairing:** Works best with `@material[image1]` as an instructor headshot + `@material[image2]` as a bookshelf or office environment

---

Template B — The Screen-to-Reality

**Mood:** Kinetic, modern, "I can do this." Bridges the gap between the digital learning environment and the real-world outcome.

**Core visual grammar:**

  • Split-plane composition: one half shows course interface/screen, other half shows the real-world application
  • Color grade: cooler, higher contrast, punchy highlights — feels like a tech product ad
  • Camera movement: fast parallax on split-plane elements, snapp
Read more
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.

Get the whole plugin
Stats
323
Stars
43
Forks
Maintained
Maintenance
Python
Language
MIT
License
2mo ago
Last commit
3mo ago
Created

Repo: rediumvex/ai-video-generator-claude

Other skills on ai-video-generator-claude.