Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
10 Claude skills that generate studio-quality AI video prompts for Seedance 2.0 on Higgsfield. Viral hooks, SaaS demos, personal brand, faceless content, luxury aesthetic & more.
| Date | Stars |
|---|---|
| 2026-07-24 | 295 |
| 2026-07-25 | 296 |
| 2026-07-28 | 300 |
| 2026-07-30 | 300 |
| 2026-07-31 | 302 |
| 2026-08-06 | 302 |
Today
— stars today
This week
+2 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.67%/day
<img width="1080" height="1350" alt="telegram-cloud-document-4-5974547813680291996" src="https://github.com/user-attachments/assets/d3ebcec5-91ec-4e4e-9117-8774f5e8b34d" /> # AI Video Generator — Claude Skill > **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. Paste into Higgsfield, get studio-quality video. **This is the actual skill set I use to generate every AI video for [@theromanknox](https://instagram.com/theromanknox) (280K+ followers).** Not templates. Not "try this prompt." The real production pipeline — copied straight from my `~/.claude/skills/`. --- ## What it does You give it a concept — "10s product launch video, dark UI, minimal" — and it gives you back: - **Complete Seedance 2.0 prompt** — 15-25 lines, paste-ready, with timestamps for every second - **2-second hook engineering** — 10+ scroll-stopping patterns per style (pattern interrupt, curiosity gap, dopamine trigger) - **Camera movement direction** — 15+ techniques with exact phrasing Seedance 2.0 understands (dolly, orbit, whip pan, snap zoom, rack focus) - **Lighting & mood presets** — three-point, neon contrast, silhouette, golden hour, practical lights - **Sound design layers** — ambient + impact + music + voice, synced to visual beats - **Platform optimization** — TikTok, Instagram Reels, YouTube Shorts, LinkedIn — aspect ratio, safe zones, loop potential - **Material references** — tells you exactly where to use `@image1`, `@video1`, `@audio1` One idea in, finished video prompt out. --- ## The 10 skills ### For views | # | Skill | What it generates | |---|---|---| | 01 | **Viral Hook** | Scroll-stopping openers — pattern interrupts, curiosity loops, dopamine triggers | | 05 | **Faceless Channel** | No face, no camera content for YouTube, TikTok, Reels | | 10 | **Podcast Visual** | Turns any audio clip into cinematic video — kills the audiogram | ### For business | # | Skill | What it generates | |---|---|---| | 02 | **SaaS Launch** | Product videos that look like an Apple keynote | | 04 | **Course Promo** | Trailers that sell out coaching programs and courses | | 08 | **Testimonial Story** | Social proof videos that actually convert | ### For brand | # | Skill | What it generates | |---|---|---| | 03 | **Personal Brand** | Founder authority content on autopilot | | 06 | **Luxury Aesthetic** | Chanel-level video for any brand, zero budget | | 07 | **Before-After** | Transformation reveals that get saved and shared | | 09 | **AI Avatar** | Digital persona content at scale | --- ## Why "write me a cool video" doesn't work Most people write 2-line prompts and get generic output. Seedance 2.0 is a precision engine — it responds to specific camera language, lighting terminology, and timing breakdowns. Vague input = vague output. These skills solve that by encoding three things into every prompt: 1. **The physics of attention** — the first 2 seconds determine if 50% of viewers bounce or 90% stay. Every prompt opens with a hook engineered for retention. 2. **Cinematic vocabulary** — Seedance 2.0 understands "dolly forward 3 feet, f/1.4, rack focus from foreground to background" better than "make it look cinematic." 3. **Sound-visual sync** — every audio element (bass hit, whoosh, ASMR texture, silence) is timestamped to a visual beat. Sound is 50% of the hook. The result: prompts that produce studio-quality video instead of generic AI slop. --- ## Install ```bash # Clone into your Claude skills folder cd ~/.claude/skills git clone https://github.com/rediumvex/ai-video-generator-claude.git ai-video-generator ``` Or if you use gstack: ```bash cd ~/.claude/skills/gstack git clone https://github.com/rediumvex/ai-video-generator-claude.git ai-video-generator ``` Restart Claude Code. Each skill inside `skills/` is now available.
Excerpt of 6,443 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:7e2950492a6d1de3, topic:prompt-engineering, readme:prompt engineering
matched fp:7e2950492a6d1de3, topic:video-generation