aiskillstore/marketplace / skills/101-skills/ai-avatar-video
ai-avatar-video
VerifiedCreate AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.4 KB |
| skill-report.json | config | 64.9 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-12T09:45:58.132Z",
"slug": "101-skills-ai-avatar-video",
"source_url": "https://github.com/101-skills/skills/tree/main/tools/video/ai-avatar-video/",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "64ee37e59a7c425d592f24db7b733b9934b9ef025b1e1ff06f6e2d3c703eb224",
"tree_hash": "70f78fe157b0ea8bc79439517f6d4422d95ed9acc70bbb35b084cb87013a36c1",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "ai-avatar-video",
"description": "Create talking-head and AI avatar videos with inference.sh models, built-in speech, lip synchronization, dubbing, and multi-presenter workflows.",
"summary": "Build AI presenter videos from portraits, scripts, or recorded audio.",
"icon": "📦",
"version": "1.0.2",
"author": "101-skills",
"license": "MIT",
"category": "design",
"tags": [
"ai-avatar",
"talking-head",
"lip-sync",
"text-to-speech",
"video-generation"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network"
]
},
"security_audit": {
"risk_level": "high",
"is_blocked": false,
"safe_to_publish": false,
"analysis_status": "ok",
"summary": "Most detections are Markdown backticks, code fences, placeholder media URLs, or documentation links rather than executable backticks or suspicious destinations. Real risks remain in third-party package installation, remote media processing, shell command construction, remote image loading, and synthetic testimonial workflows without consent safeguards.",
"remediation": [
{
"issue": "User-provided scripts and media references are embedded in shell-quoted JSON examples.",
"suggestion": "Write input to a temporary JSON file with a structured serializer, then pass the file without shell interpolation.",
"severity": "high"
},
{
"issue": "Testimonial and multi-presenter examples lack consent, disclosure, and likeness safeguards.",
"suggestion": "Require authorization for every likeness and voice, prohibit deceptive endorsements, and label synthetic media in published outputs.",
"severity": "high"
},
{
"issue": "Portraits, audio, video, and scripts are processed by external inference services.",
"suggestion": "Request explicit approval before upload and warn users about provider retention, privacy, pricing, and regional compliance.",
"severity": "medium"
},
{
"issue": "The skill recommends unpinned package installation and mutable remote installation instructions.",
"suggestion": "Pin package versions and source revisions, publish integrity hashes, and avoid loading installation guidance from a moving branch.",
"severity": "medium"
},
{
"issue": "The introductory image is loaded from an external host.",
"suggestion": "Bundle or proxy the image through the marketplace to prevent third-party requests during skill browsing.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 7,
"line_end": 7
},
{
"file": "SKILL.md",
"line_start": 17,
"line_end": 17
},
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 28
},
{
"file": "SKILL.md",
"line_start": 28,
"line_end": 36
},
{
"file": "SKILL.md",
"line_start": 36,
"line_end": 37
},
{
"file": "SKILL.md",
"line_start": 37,
"line_end": 38
},
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 39
},
{
"file": "SKILL.md",
"line_start": 39,
"line_end": 55
},
{
"file": "SKILL.md",
"line_start": 55,
"line_end": 63
},
{
"file": "SKILL.md",
"line_start": 63,
"line_end": 67
},
{
"file": "SKILL.md",
"line_start": 67,
"line_end": 76
},
{
"file": "SKILL.md",
"line_start": 76,
"line_end": 80
},
{
"file": "SKILL.md",
"line_start": 80,
"line_end": 85
},
{
"file": "SKILL.md",
"line_start": 85,
"line_end": 91
},
{
"file": "SKILL.md",
"line_start": 91,
"line_end": 104
},
{
"file": "SKILL.md",
"line_start": 104,
"line_end": 108
},
{
"file": "SKILL.md",
"line_start": 108,
"line_end": 113
},
{
"file": "SKILL.md",
"line_start": 113,
"line_end": 119
},
{
"file": "SKILL.md",
"line_start": 119,
"line_end": 124
},
{
"file": "SKILL.md",
"line_start": 124,
"line_end": 128
},
{
"file": "SKILL.md",
"line_start": 128,
"line_end": 133
},
{
"file": "SKILL.md",
"line_start": 133,
"line_end": 139
},
{
"file": "SKILL.md",
"line_start": 139,
"line_end": 152
},
{
"file": "SKILL.md",
"line_start": 152,
"line_end": 158
},
{
"file": "SKILL.md",
"line_start": 158,
"line_end": 172
},
{
"file": "SKILL.md",
"line_start": 172,
"line_end": 178
},
{
"file": "SKILL.md",
"line_start": 178,
"line_end": 194
},
{
"file": "SKILL.md",
"line_start": 194,
"line_end": 206
},
{
"file": "SKILL.md",
"line_start": 206,
"line_end": 218
},
{
"file": "SKILL.md",
"line_start": 218,
"line_end": 235
},
{
"file": "SKILL.md",
"line_start": 235,
"line_end": 235
},
{
"file": "SKILL.md",
"line_start": 241,
"line_end": 259
},
{
"file": "SKILL.md",
"line_start": 259,
"line_end": 261
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 11,
"line_end": 11
},
{
"file": "SKILL.md",
"line_start": 13,
"line_end": 13
},
{
"file": "SKILL.md",
"line_start": 17,
"line_end": 17
},
{
"file": "SKILL.md",
"line_start": 24,
"line_end": 24
},
{
"file": "SKILL.md",
"line_start": 57,
"line_end": 57
},
{
"file": "SKILL.md",
"line_start": 69,
"line_end": 69
},
{
"file": "SKILL.md",
"line_start": 82,
"line_end": 82
},
{
"file": "SKILL.md",
"line_start": 83,
"line_end": 83
},
{
"file": "SKILL.md",
"line_start": 110,
"line_end": 110
},
{
"file": "SKILL.md",
"line_start": 111,
"line_end": 111
},
{
"file": "SKILL.md",
"line_start": 121,
"line_end": 121
},
{
"file": "SKILL.md",
"line_start": 122,
"line_end": 122
},
{
"file": "SKILL.md",
"line_start": 130,
"line_end": 130
},
{
"file": "SKILL.md",
"line_start": 131,
"line_end": 131
},
{
"file": "SKILL.md",
"line_start": 149,
"line_end": 149
},
{
"file": "SKILL.md",
"line_start": 160,
"line_end": 160
},
{
"file": "SKILL.md",
"line_start": 169,
"line_end": 169
},
{
"file": "SKILL.md",
"line_start": 210,
"line_end": 210
},
{
"file": "SKILL.md",
"line_start": 265,
"line_end": 265
},
{
"file": "SKILL.md",
"line_start": 266,
"line_end": 266
},
{
"file": "SKILL.md",
"line_start": 267,
"line_end": 267
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:7:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 7,
"line_end": 7,
"snippet": "> **Install the belt CLI skill:** `npx skills add belt-sh/cli`"
},
{
"id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 17,
"line_end": 17,
"snippet": "> Requires inference.sh CLI (`belt`). [Install instructions](https://raw.githubusercontent.com/infer"
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 19,
"line_end": 28,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 28,
"line_end": 36,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 36,
"line_end": 37,
"snippet": "| **P-Video-Avatar** | `pruna/p-video-avatar` | **Best overall: speed, cost, quality, control** | **"
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 37,
"line_end": 38,
"snippet": "| OmniHuman 1.5 | `bytedance/omnihuman-1-5` | Multi-character, audio-driven | No |"
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 38,
"line_end": 39,
"snippet": "| Fabric 1.0 | `falai/fabric-1-0` | Image talks with lipsync | Yes |"
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 39,
"line_end": 55,
"snippet": "| PixVerse Lipsync | `falai/pixverse-lipsync` | Highly realistic lipsync | No |"
},
{
"id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 55,
"line_end": 63,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 63,
"line_end": 67,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 67,
"line_end": 76,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 76,
"line_end": 80,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 80,
"line_end": 85,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 85,
"line_end": 91,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 91,
"line_end": 104,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:104:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 104,
"line_end": 108,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 108,
"line_end": 113,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:113:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 113,
"line_end": 119,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 119,
"line_end": 124,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:124:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 124,
"line_end": 128,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:128:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 128,
"line_end": 133,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:133:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 133,
"line_end": 139,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 139,
"line_end": 152,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:152:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 152,
"line_end": 158,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:158:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 158,
"line_end": 172,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:172:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 172,
"line_end": 178,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:178:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 178,
"line_end": 194,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:194:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 194,
"line_end": 206,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:206:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 206,
"line_end": 218,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:218:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 218,
"line_end": 235,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:235:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 235,
"line_end": 235,
"snippet": "- Generate portraits with `pruna/p-image` using `9:16` aspect ratio for vertical videos"
},
{
"id": "external_commands:SKILL.md:241:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 241,
"line_end": 259,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:259:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 259,
"line_end": 261,
"snippet": "```"
},
{
"id": "network:SKILL.md:11:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 11,
"line_end": 11,
"snippet": "Create AI avatars and talking head videos via [inference.sh](https://inference.sh) CLI."
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 13,
"line_end": 13,
"snippet": ". [Install instructions](https://raw.githubusercontent.com/infer"
},
{
"id": "network:SKILL.md:24:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 24,
"line_end": 24,
"snippet": "\"image\": \"https://portrait.jpg\","
},
{
"id": "network:SKILL.md:57:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 57,
"line_end": 57,
"snippet": "\"image\": \"https://portrait.jpg\","
},
{
"id": "network:SKILL.md:69:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 69,
"line_end": 69,
"snippet": "\"image\": \"https://portrait.jpg\","
},
{
"id": "network:SKILL.md:82:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 82,
"line_end": 82,
"snippet": "\"image\": \"https://portrait.jpg\","
},
{
"id": "network:SKILL.md:83:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 83,
"line_end": 83,
"snippet": "\"audio\": \"https://speech.mp3\""
},
{
"id": "network:SKILL.md:110:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 110,
"line_end": 110,
"snippet": "\"image_url\": \"https://portrait.jpg\","
},
{
"id": "network:SKILL.md:111:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 111,
"line_end": 111,
"snippet": "\"audio_url\": \"https://speech.mp3\""
},
{
"id": "network:SKILL.md:121:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 121,
"line_end": 121,
"snippet": "\"image_url\": \"https://face.jpg\","
},
{
"id": "network:SKILL.md:122:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 122,
"line_end": 122,
"snippet": "\"audio_url\": \"https://audio.mp3\""
},
{
"id": "network:SKILL.md:130:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 130,
"line_end": 130,
"snippet": "\"image_url\": \"https://portrait.jpg\","
},
{
"id": "network:SKILL.md:131:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 131,
"line_end": 131,
"snippet": "\"audio_url\": \"https://speech.mp3\""
},
{
"id": "network:SKILL.md:149:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 149,
"line_end": 149,
"snippet": "\"image_url\": \"https://presenter-photo.jpg\","
},
{
"id": "network:SKILL.md:160:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 160,
"line_end": 160,
"snippet": "belt app run infsh/fast-whisper-large-v3 --input '{\"audio_url\": \"https://video.mp4\"}' > transcript.j"
},
{
"id": "network:SKILL.md:169:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 169,
"line_end": 169,
"snippet": "\"video_url\": \"https://original-video.mp4\","
},
{
"id": "network:SKILL.md:210:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 210,
"line_end": 210,
"snippet": "\\\"image\\\": \\\"https://portrait.jpg\\\","
},
{
"id": "network:SKILL.md:265:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 265,
"line_end": 265,
"snippet": "- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI"
},
{
"id": "network:SKILL.md:266:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 266,
"line_end": 266,
"snippet": "- [Content Pipeline Example](https://inference.sh/docs/examples/content-pipeline) - Building media w"
},
{
"id": "network:SKILL.md:267:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 267,
"line_end": 267,
"snippet": "- [Streaming Results](https://inference.sh/docs/api/sdk/streaming) - Real-time progress updates"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:7:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.96,
"reason": "The line explicitly directs users to execute npx against a third-party package source. This performs package resolution and installation without a pinned version.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:17:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks only format the belt executable name in Markdown. This line does not execute a shell command."
},
{
"id": "external_commands:SKILL.md:19:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "The fenced example instructs execution of belt login and a remote model invocation. These are intentional external commands that authenticate and submit media generation inputs.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:28:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a Markdown code-fence delimiter followed by explanatory text and a model table. It is not Ruby or shell backtick execution."
},
{
"id": "external_commands:SKILL.md:36:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format the pruna/p-video-avatar model identifier inside a Markdown table. No command is executed."
},
{
"id": "external_commands:SKILL.md:37:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format the bytedance/omnihuman-1-5 model identifier. This is documentation, not executable backtick syntax."
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format the falai/fabric-1-0 model identifier. The Markdown table does not invoke a shell."
},
{
"id": "external_commands:SKILL.md:39:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The range contains a formatted model identifier, comparison tables, prose, and an opening code fence. None executes through Markdown backticks."
},
{
"id": "external_commands:SKILL.md:55:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "The fenced block directs execution of belt app run with portrait and speech inputs. This is genuine external command usage for remote video generation.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:63:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The detected backticks are Markdown fence delimiters around prose. The range itself contains no executable command."
},
{
"id": "external_commands:SKILL.md:67:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "The fenced block instructs belt to invoke a remote avatar model with style and speech inputs. This is intended external command execution.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:76:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This range contains closing and opening Markdown fences plus explanatory prose. It does not contain an external command."
},
{
"id": "external_commands:SKILL.md:80:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "The example executes belt app run and submits portrait and audio references to a remote model. It is real external command usage.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:85:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The backticks are Markdown fence markers around headings and prose. No command appears in the detected range."
},
{
"id": "external_commands:SKILL.md:91:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "The workflow runs two belt model commands to generate a portrait and avatar video. These are genuine remote command invocations.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:104:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This range contains a closing Markdown fence, headings, and an opening fence. It does not execute a command."
},
{
"id": "external_commands:SKILL.md:108:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "The block invokes the OmniHuman application through belt with image and audio references. This is intentional external command execution.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:113:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The range consists of a Markdown fence, explanatory text, headings, and another fence. It contains no command."
},
{
"id": "external_commands:SKILL.md:119:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "The example invokes the Fabric application through belt using image and audio inputs. It is real external command execution.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:124:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The detected syntax is a Markdown fence surrounding headings and prose. No external command is present in this range."
},
{
"id": "external_commands:SKILL.md:128:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "The fenced block runs the PixVerse lip-sync model through belt. This is genuine external command execution against a remote service.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:133:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This range contains a closing code fence, headings, prose, and an opening fence. Markdown delimiters do not execute commands."
},
{
"id": "external_commands:SKILL.md:139:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.98,
"reason": "The workflow executes text-to-speech and avatar applications through belt and redirects output to a local file. These are real shell operations.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:152:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The detected range is Markdown fence syntax and explanatory text. It does not include a command invocation."
},
{
"id": "external_commands:SKILL.md:158:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.98,
"reason": "The dubbing workflow runs transcription, speech, and lip-sync applications and redirects two outputs to files. These are genuine external and filesystem-affecting commands.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:172:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This range contains a closing Markdown fence, headings, prose, and an opening fence. It does not execute backticks."
},
{
"id": "external_commands:SKILL.md:178:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.98,
"reason": "The UGC workflow executes image and avatar generation applications through belt. These are intentional remote commands using generated content inputs.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:194:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The range contains a closing fence, descriptive lists, headings, and an opening fence. No command appears before the range ends."
},
{
"id": "external_commands:SKILL.md:206:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.98,
"reason": "The block uses a shell loop, variable expansion, and repeated belt invocations. This is genuine shell execution, although the documented voice list is fixed.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:218:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The range is documentation with lists and inline model formatting after a closed code block. It contains no executable shell statement."
},
{
"id": "external_commands:SKILL.md:235:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Backticks format a model identifier and aspect ratio in prose. They are not command substitution or executable syntax."
},
{
"id": "external_commands:SKILL.md:241:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.97,
"reason": "The block recommends several npx package installation commands from external repositories without pinned revisions. Executing them introduces package supply-chain risk.",
"severity": "medium"
},
{
"id": "external_commands:SKILL.md:259:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "The detected backticks close a Markdown fence and format a fixed belt store-listing command. The fixed read-only example has no command injection vector."
},
{
"id": "network:SKILL.md:11:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a normal hyperlink to the documented service homepage. It does not transmit secrets or trigger a request by itself."
},
{
"id": "network:SKILL.md:13:hardcoded-url",
"verdict": "confirmed",
"confidence": 0.94,
"reason": "The Markdown image references an externally hosted cloud asset. Rendering the documentation can contact that host and disclose client request metadata.",
"severity": "low"
},
{
"id": "network:SKILL.md:17:hardcoded-url",
"verdict": "confirmed",
"confidence": 0.91,
"reason": "The install link loads raw instructions from a mutable main branch on GitHub. Following mutable remote guidance creates a limited supply-chain and content-change risk.",
"severity": "low"
},
{
"id": "network:SKILL.md:24:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The portrait URL is an obvious placeholder inside an input example. It is not a live destination or evidence of data exfiltration."
},
{
"id": "network:SKILL.md:57:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The portrait URL is placeholder documentation for a user-supplied media location. No suspicious fixed endpoint is present."
},
{
"id": "network:SKILL.md:69:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The portrait URL is a placeholder within a model input example. It does not identify an operational external recipient."
},
{
"id": "network:SKILL.md:82:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The portrait URL is a placeholder showing the expected input type. It is not a hardcoded production destination."
},
{
"id": "network:SKILL.md:83:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The speech URL is a placeholder showing where user-provided audio belongs. It does not point to a real collection endpoint."
},
{
"id": "network:SKILL.md:110:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The portrait URL is placeholder data in an OmniHuman example. It is not a suspicious or live hardcoded endpoint."
},
{
"id": "network:SKILL.md:111:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The speech URL is placeholder data in a documented input object. No actual destination is encoded."
},
{
"id": "network:SKILL.md:121:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The face URL is a placeholder for user media in the Fabric example. It is not evidence of an outbound request to a fixed recipient."
},
{
"id": "network:SKILL.md:122:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The audio URL is a placeholder for user media. It does not identify a real external service or exfiltration target."
},
{
"id": "network:SKILL.md:130:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The portrait URL is placeholder input for the PixVerse example. It is not an operational hardcoded destination."
},
{
"id": "network:SKILL.md:131:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The speech URL is placeholder input for a lip-sync model. No suspicious fixed host is used."
},
{
"id": "network:SKILL.md:149:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The presenter photo URL is an illustrative placeholder. It is not a real remote collection endpoint."
},
{
"id": "network:SKILL.md:160:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The video URL is placeholder input in a transcription workflow. The remote-processing risk is contextual, not caused by this literal destination."
},
{
"id": "network:SKILL.md:169:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The original video URL is a placeholder in a dubbing example. It does not point to a live hardcoded recipient."
},
{
"id": "network:SKILL.md:210:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "The escaped portrait URL is placeholder text inside a batch example. It is not an actual external destination."
},
{
"id": "network:SKILL.md:265:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a standard documentation link to the service's app-running guide. It does not transmit user data."
},
{
"id": "network:SKILL.md:266:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a standard documentation link for a content pipeline example. No secret or user content is embedded."
},
{
"id": "network:SKILL.md:267:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "This is a standard documentation link for streaming results. It is not a suspicious network destination."
}
],
"semantic_findings": [
{
"title": "Shell Injection Through Inline JSON Inputs",
"description": "User-controlled scripts and media values are placed inside shell-quoted JSON. Quotes or shell substitutions can alter commands when an agent inserts input without structured serialization.",
"severity": "high",
"locations": [
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 27
},
{
"file": "SKILL.md",
"line_start": 56,
"line_end": 62
},
{
"file": "SKILL.md",
"line_start": 209,
"line_end": 216
}
],
"confidence": 0.9,
"confidence_reasoning": "The examples directly embed text in single-quoted and double-quoted shell arguments without a JSON serializer. Generated scripts can contain quote or substitution characters."
},
{
"title": "External Processing of Potentially Sensitive Media",
"description": "The workflows send portraits, voice scripts, audio, and videos to remote inference applications. The skill provides no consent, retention, pricing, or privacy warning.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 27
},
{
"file": "SKILL.md",
"line_start": 80,
"line_end": 85
},
{
"file": "SKILL.md",
"line_start": 158,
"line_end": 171
}
],
"confidence": 0.97,
"confidence_reasoning": "Multiple belt app run examples submit media URLs and scripts to named remote models. No data-handling notice appears in the skill."
},
{
"title": "Deceptive Synthetic Testimonial Risk",
"description": "The skill generates testimonial-style UGC and multiple presenters without requiring likeness consent or synthetic-media disclosure. This can facilitate deceptive endorsements or impersonation.",
"severity": "high",
"locations": [
{
"file": "SKILL.md",
"line_start": 174,
"line_end": 193
},
{
"file": "SKILL.md",
"line_start": 204,
"line_end": 217
},
{
"file": "SKILL.md",
"line_start": 220,
"line_end": 227
}
],
"confidence": 0.94,
"confidence_reasoning": "The examples explicitly create product testimonials and several presenters, while the guidance contains no consent, disclosure, or impersonation restrictions."
}
],
"critical_findings": [],
"high_findings": [
{
"title": "Shell Injection Through Inline JSON Inputs",
"description": "User-controlled scripts and media values are placed inside shell-quoted JSON. Quotes or shell substitutions can alter commands when an agent inserts input without structured serialization.",
"locations": [
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 27
},
{
"file": "SKILL.md",
"line_start": 56,
"line_end": 62
},
{
"file": "SKILL.md",
"line_start": 209,
"line_end": 216
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "high",
"confidence": 0.9,
"confidence_reasoning": "The examples directly embed text in single-quoted and double-quoted shell arguments without a JSON serializer. Generated scripts can contain quote or substitution characters."
},
{
"title": "Deceptive Synthetic Testimonial Risk",
"description": "The skill generates testimonial-style UGC and multiple presenters without requiring likeness consent or synthetic-media disclosure. This can facilitate deceptive endorsements or impersonation.",
"locations": [
{
"file": "SKILL.md",
"line_start": 174,
"line_end": 193
},
{
"file": "SKILL.md",
"line_start": 204,
"line_end": 217
},
{
"file": "SKILL.md",
"line_start": 220,
"line_end": 227
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "high",
"confidence": 0.94,
"confidence_reasoning": "The examples explicitly create product testimonials and several presenters, while the guidance contains no consent, disclosure, or impersonation restrictions."
}
],
"medium_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "> **Install the belt CLI skill:** `npx skills add belt-sh/cli`",
"locations": [
{
"file": "SKILL.md",
"line_start": 7,
"line_end": 7
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.96,
"confidence_reasoning": "The line explicitly directs users to execute npx against a third-party package source. This performs package resolution and installation without a pinned version."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 19,
"line_end": 28
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "The fenced example instructs execution of belt login and a remote model invocation. These are intentional external commands that authenticate and submit media generation inputs."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 55,
"line_end": 63
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "The fenced block directs execution of belt app run with portrait and speech inputs. This is genuine external command usage for remote video generation."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 67,
"line_end": 76
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "The fenced block instructs belt to invoke a remote avatar model with style and speech inputs. This is intended external command execution."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 80,
"line_end": 85
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "The example executes belt app run and submits portrait and audio references to a remote model. It is real external command usage."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 91,
"line_end": 104
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "The workflow runs two belt model commands to generate a portrait and avatar video. These are genuine remote command invocations."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 108,
"line_end": 113
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "The block invokes the OmniHuman application through belt with image and audio references. This is intentional external command execution."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 119,
"line_end": 124
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "The example invokes the Fabric application through belt using image and audio inputs. It is real external command execution."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 128,
"line_end": 133
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "The fenced block runs the PixVerse lip-sync model through belt. This is genuine external command execution against a remote service."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 139,
"line_end": 152
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.98,
"confidence_reasoning": "The workflow executes text-to-speech and avatar applications through belt and redirects output to a local file. These are real shell operations."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 158,
"line_end": 172
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.98,
"confidence_reasoning": "The dubbing workflow runs transcription, speech, and lip-sync applications and redirects two outputs to files. These are genuine external and filesystem-affecting commands."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 178,
"line_end": 194
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.98,
"confidence_reasoning": "The UGC workflow executes image and avatar generation applications through belt. These are intentional remote commands using generated content inputs."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 206,
"line_end": 218
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.98,
"confidence_reasoning": "The block uses a shell loop, variable expansion, and repeated belt invocations. This is genuine shell execution, although the documented voice list is fixed."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 241,
"line_end": 259
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "The block recommends several npx package installation commands from external repositories without pinned revisions. Executing them introduces package supply-chain risk."
},
{
"title": "External Processing of Potentially Sensitive Media",
"description": "The workflows send portraits, voice scripts, audio, and videos to remote inference applications. The skill provides no consent, retention, pricing, or privacy warning.",
"locations": [
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 27
},
{
"file": "SKILL.md",
"line_start": 80,
"line_end": 85
},
{
"file": "SKILL.md",
"line_start": 158,
"line_end": 171
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.97,
"confidence_reasoning": "Multiple belt app run examples submit media URLs and scripts to named remote models. No data-handling notice appears in the skill."
}
],
"low_findings": [
{
"title": "Hardcoded URL",
"description": ". [Install instructions](https://raw.githubusercontent.com/infer",
"locations": [
{
"file": "SKILL.md",
"line_start": 17,
"line_end": 17
}
],
"review_kind": "capability",
"source_category": "network",
"source_severity": "low",
"confidence": 0.91,
"confidence_reasoning": "The install link loads raw instructions from a mutable main branch on GitHub. Following mutable remote guidance creates a limited supply-chain and content-change risk."
}
],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 268,
"audit_model": "codex",
"audited_at": "2026-07-12T09:45:58.132Z",
"agent_auto_install_policy": "confirmation_required",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Create AI Avatar and Talking Head Videos",
"value_statement": "Avatar video production often requires separate speech, animation, and lip-sync tools. This skill organizes inference.sh models into reusable presenter, dubbing, and UGC workflows.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"AI avatar video",
"talking head generator",
"lip sync video",
"virtual presenter",
"video dubbing",
"inference.sh",
"UGC video"
],
"actual_capabilities": [
"Generate talking-head videos from a portrait and written script with P-Video-Avatar.",
"Animate portraits from existing audio with P-Video-Avatar, OmniHuman, Fabric, or PixVerse.",
"Control voice, language, delivery style, scene direction, and output resolution.",
"Combine portrait generation, text-to-speech, transcription, translation, and lip synchronization.",
"Run batch presenter variants with different voices through shell workflows."
],
"limitations": [
"The skill requires the belt CLI, an authenticated inference.sh account, and access to remote models.",
"Model availability, pricing, speed, supported voices, and output quality can change.",
"Media inputs must be available through URLs accepted by the selected model.",
"The skill does not verify likeness rights, voice consent, advertising compliance, or synthetic-media disclosure."
],
"use_cases": [
{
"title": "Produce product explainers",
"description": "Turn an approved presenter portrait and concise script into a narrated product walkthrough.",
"target_user": "Marketing teams"
},
{
"title": "Localize training videos",
"description": "Transcribe a training video, translate its narration, generate speech, and synchronize the new audio.",
"target_user": "Learning designers"
},
{
"title": "Create character dialogue",
"description": "Animate an authorized character image with expressive speech for game scenes or interactive prototypes.",
"target_user": "Game developers"
}
],
"prompt_templates": [
{
"title": "Create a basic presenter",
"prompt": "Create a 720p talking-head video from [portrait URL]. Use this script: [script]. Choose a clear, neutral English voice.",
"scenario": "A first avatar video with built-in speech"
},
{
"title": "Direct voice and scene",
"prompt": "Create a 1080p presenter video from [portrait URL] and [script]. Use an enthusiastic voice and describe a professional studio setting.",
"scenario": "A styled product announcement"
},
{
"title": "Build a dubbing workflow",
"prompt": "Dub [video URL] into [language]. Transcribe, translate, generate approved speech, and synchronize it while preserving the original visual timing.",
"scenario": "Localized training or support content"
},
{
"title": "Generate approved presenter variants",
"prompt": "Create three disclosed synthetic presenter variants for [campaign]. Use authorized portraits, distinct voices, consistent messaging, and vertical 1080p output.",
"scenario": "An advanced multi-presenter campaign"
}
],
"output_examples": [
{
"input": "Create a neutral 720p presenter video from an authorized portrait and a 30-second onboarding script.",
"output": [
"Selected P-Video-Avatar for integrated speech and portrait animation.",
"Prepared a neutral English voice and 720p output.",
"Submitted the approved portrait and onboarding script for generation."
]
},
{
"input": "Dub an existing safety training video into Spanish using an approved replacement voice.",
"output": [
"Transcribed the source narration.",
"Prepared a Spanish translation for review.",
"Generated approved Spanish speech and synchronized it with the source video."
]
},
{
"input": "Create three disclosed vertical presenter variants for a product campaign.",
"output": [
"Prepared three authorized presenter and voice combinations.",
"Applied consistent campaign messaging and vertical framing.",
"Submitted three 1080p variants for generation."
]
}
],
"best_practices": [
"Use front-facing, well-lit portraits and clean audio for stable facial animation.",
"Confirm likeness, voice, script, and media rights before sending inputs to remote models.",
"Review generated speech, lip synchronization, claims, and disclosure labels before publication."
],
"anti_patterns": [
"Do not animate a real person without documented permission.",
"Do not embed unescaped user text directly inside shell-quoted input arguments.",
"Do not publish synthetic testimonials as genuine customer endorsements."
],
"faq": [
{
"question": "Which model should I try first?",
"answer": "The skill recommends P-Video-Avatar for integrated speech, style controls, and 720p or 1080p output."
},
{
"question": "Can I use recorded audio instead of text?",
"answer": "Yes. P-Video-Avatar and the listed lip-sync models accept audio URLs with compatible portrait inputs."
},
{
"question": "Can this skill dub an existing video?",
"answer": "Yes. The documented workflow combines transcription, translation, speech generation, and LatentSync."
},
{
"question": "Does the skill work without inference.sh?",
"answer": "No. It relies on the belt CLI, an authenticated account, and remotely hosted inference applications."
},
{
"question": "Does it guarantee model pricing or speed?",
"answer": "No. The document includes estimates, but providers can change prices, performance, availability, and limits."
},
{
"question": "What permissions are required for avatar media?",
"answer": "Obtain explicit rights for every likeness, voice, script, and source video. Add clear synthetic-media disclosures where required."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 268
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |