Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rediumvex/ai-video-generator-claude --skill 09-ai-avatargit clone --depth 1 https://github.com/rediumvex/ai-video-generator-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rediumvex/ai-video-generator-claude/09-ai-avatar)<a href="https://agentmods.dev/skills/rediumvex/ai-video-generator-claude/09-ai-avatar"><img src="https://agentmods.dev/badge/skills/rediumvex/ai-video-generator-claude/09-ai-avatar/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rediumvex/ai-video-generator-claude/09-ai-avatar"><img src="https://agentmods.dev/badge/skills/rediumvex/ai-video-generator-claude/09-ai-avatar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.05416 |
| Opus 5 | $0.00044 | $0.02708 |
| Sonnet 5 | $0.00018 | $0.01083 |
| Haiku 4.5 | $0.00009 | $0.00542 |
Grade A, and why
seedance-ai-avatar scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 436 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Avatar — Digital Persona Video Prompts
A complete system for crafting Seedance 2.0 prompts on Higgsfield that feature AI avatars, digital personas, virtual presenters, and synthetic characters as the primary subject. This skill covers everything from photorealistic digital humans to stylized 3D characters, including hook patterns, environment design, camera work, lighting, and audio direction.
1. Input Specs
Before generating prompts, gather the following from the user:
Character definition
- Avatar style: photorealistic human / stylized 3D / 2D animated / abstract-geometric
- Gender presentation, approximate age, and visual identity descriptors (if applicable)
- Skin tone, hair, wardrobe notes, or reference aesthetics
- Personality register: corporate, playful, authoritative, futuristic, warm
Content purpose
- Use case: product demo, brand spokesperson, educational content, virtual influencer post, sales video, onboarding clip
- Platform destination: Instagram Reel, YouTube, LinkedIn, TikTok, website hero
- Desired emotional response: trust, excitement, curiosity, aspiration
Technical requirements
- Clip duration: 2–4 sec / 6–10 sec / 15–30 sec
- Aspect ratio: 9:16 vertical / 16:9 landscape / 1:1 square
- Motion intensity: static with subtle animation / active gestures / high-energy movement
Brand constraints
- Color palette or forbidden colors
- Brand keywords or phrases the avatar should embody visually
- Any style references (films, games, other AI avatars)
2. Philosophy — Why AI Avatars Are the Future of Scalable Content
The uncanny valley problem — and how to avoid it
The uncanny valley is the psychological discomfort triggered when a synthetic human looks almost real but falls short in ways the brain cannot consciously articulate. Eyes that do not quite track. Skin that lacks micro-texture. Movement that is smooth but wrong. The brain pattern-matches to illness, deception, or death.
There are two reliable exits from the uncanny valley:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 436 lines · 88 tokens per session scan A 8e4cf8252dab
seedance-ai-avatar is a skill published in the GitHub repository rediumvex/ai-video-generator-claude (361 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 5,416 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
remotion-motion-graphics
Create and edit professional motion graphics videos with Remotion (React-based video). Use this skill EVERY time the user wants to create a video, edit a video, animate something, build an intro/outro/logo animation, make a Reel/Short/promo/launch video, add text animations or captions to footage, composite images and…
director-cinematography
A guide to visual storytelling for video, covering shot sizes, composition, camera movement, lighting, focus range, color temperature, and lens characteristics. It also explains how to turn these choices into video prompts.
writer-screenwriter
A professional screenwriting guide based on methods associated with Lawrence Kasdan and Tony Gilroy. It covers story structure, scenes, dialogue, quality checks, and formats for films and series.
director-art-design
A prompt-writing guide for generating character-setting and scene images with a consistent visual style and recurring character details.
workbench-storyboard-planner
A Chinese-language storyboarding planner that turns a story into a structured shot plan. A storyboard maps each scene or camera shot, including its duration, characters, setting, props, style, references, and prompts.
director-action
A guide to staging non-combat action scenes such as parkour, chases, climbing, stunts, and falls. It covers movement vocabulary, interaction with the environment, pacing, FPV chase shots, and physical constraints.