ai-avatar-video
Create AI Avatar Talking-Head Videos
Creating avatar videos from portraits, scripts, or audio requires choosing the right model and inputs. This skill routes requests to RunComfy avatar models and prepares the matching CLI workflow.
Stop for confirmation before installing.
Review the plan and obtain explicit user consent before changing files.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "ai-avatar-video" from https://skillstore.io/skills/doany-ai-ai-avatar-video.md and its manifest at https://skillstore.io/api/skills/doany-ai-ai-avatar-video/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "ai-avatar-video". A portrait URL and a clean voiceover file for a vertical product introduction.
Expected outcome:
The skill selects OmniHuman, requests the portrait and audio inputs, adds a consent reminder, and outlines the expected generated video output.
Using "ai-avatar-video". A short script with no recorded voiceover and a request for a talking presenter.
Expected outcome:
The skill selects HappyHorse, keeps the spoken line explicit, adds voice tone guidance, and recommends a short clip length.
Using "ai-avatar-video". A stylized mascot image with a provided audio track.
Expected outcome:
The skill selects Wan 2-2 Animate, treats the character as illustrated media, and focuses the plan on full-body synchronized motion.
Security Audit
High RiskStatic hits were Markdown code spans, documentation links, placeholder asset URLs, and disclosed CLI token storage, not executable backtick code or hidden file access. The substantive concerns are dual-use synthetic media and third-party processing of voice and likeness data, which require consent and privacy controls. No prompt injection attempt was found in the skill text.
Confirmed security concerns (2)
Risk Factors
⚙️ External commands (50)
🌐 Network access (31)
📁 Filesystem access (2)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/doany-ai-ai-avatar-video/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/doany-ai-ai-avatar-video?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/doany-ai-ai-avatar-video?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doany-ai-ai-avatar-video/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/doany-ai-ai-avatar-video.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
doany-ai. (2026). ai-avatar-video security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/doany-ai-ai-avatar-video/audits/6BibTeX citation
@techreport{doany-ai-doany-ai-ai-avatar-video-2026,
author = {doany-ai},
title = {ai-avatar-video security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/doany-ai-ai-avatar-video/audits/6},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "ai-avatar-video security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
- name: "doany-ai"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/doany-ai-ai-avatar-video/audits/6"
identifiers:
- type: other
value: "skillstore:doany-ai-ai-avatar-video:audit:6"
description: "Skillstore immutable audit report identifier"
Compare variants
11 installable variantsEach author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
runcomfy-com-ai-avatar-video
2026-08-21
inference-sh-skills-ai-avatar-video
2026-08-21
infsh-skills-ai-avatar-video
2026-08-21
inference-skills-ai-avatar-video
2026-08-21
skills-shell-ai-avatar-video
2026-08-21
halt-catch-fire-ai-avatar-video
2026-08-21
qu-skills-ai-avatar-video
2026-08-21
agentspace-so-ai-avatar-video
2026-08-21
doany-ai-ai-avatar-video
2026-08-21
inference-sh-ai-avatar-video
2026-08-21
101-skills-ai-avatar-video
2026-08-21
Skillstore Score
Why this score Evidence Confidence: MediumWhat You Can Build
Produce Product Presenter Clips
Turn a brand-approved portrait and voiceover into short vertical videos for demos or social posts.
Create Training Narrators
Match a presenter image with lesson audio to create consistent explainers across a course.
Animate Stylized Characters
Choose a character animation route for mascots, illustrated hosts, or concept videos with spoken lines.
Try These Prompts
Create a 10-second vertical avatar video from this portrait URL and this voiceover URL. Use the simplest RunComfy route and list the required inputs.
I have a written script but no audio file. Compare the avatar routes and prepare the best RunComfy generation plan for a short presenter clip.
Use the same approved presenter portrait with three voiceover URLs. Plan separate avatar videos for English, Spanish, and French with consistent framing.
Create a cinematic avatar scene using a subject reference image, a reference audio track, and a warm studio look. Select the best model and explain the motion cues.
Best Practices
- Use only voices and likenesses where you have clear permission.
- Provide clean voice audio and a well-framed portrait for stronger lip sync.
- Keep spoken clips short, then combine clips for longer narratives.
Avoid
- Do not generate real-person videos without consent or clear authorization.
- Do not place secrets, private tokens, or sensitive data inside prompts or media URLs.
- Do not use a cinematic multi-reference route for a simple portrait plus audio task.