{"id":"3c301c02-19d3-41fd-8a0b-339a9ab8413d","shortId":"Rtk3Hp","kind":"skill","title":"video-generation","tagline":"End-to-end AI video production through the Hyper MCP — text-to-video and image-to-video generation (Sora, Veo, Seedance), scene chaining, video analysis, transcription, subtitles, TikTok / karaoke captions, voiceover (TTS), audio mixing, clipping, stitching, and text overlays. Us","description":"# Video Generation & Editing\n\nGuide for generating, editing, analyzing, and post-processing videos using AI models and FFmpeg-backed tools exposed through the Hyper MCP.\n\n## Requirements\n\nThis skill assumes the [Hyper MCP](https://app.hyperfx.ai/mcp) is connected to your agent so the tools below are available. The underlying providers (OpenAI Sora, Google Veo, ByteDance Seedance, OpenAI TTS, transcription, etc.) are configured under your Hyper integrations.\n\n## Tool surface\n\n| Group | Tools |\n|-------|-------|\n| Generation | `generate_video`, `sora_remix_video`, `sora_delete_video` |\n| Analysis | `analyze_video`, `capture_video_frame`, `transcribe_video` |\n| Subtitles & captions | `generate_subtitles`, `burn_subtitles`, `burn_highlighted_captions` |\n| Audio | `text_to_speech`, `add_audio_to_video` |\n| Editing | `clip_video`, `stitch_videos`, `overlay_text` |\n\n## Out of scope\n\n- Image generation, ad creative composition, brand extraction — use `image-generation` or `ad-creative-generation`.\n- Posting finished videos to social platforms — use `tiktok`, `instagram`, or `linkedin`.\n- Running paid video campaigns — use `google-ads`, `meta-ads`, `tiktok-ads`.\n\n## Available Tools\n\n| Tool | Purpose | Runs in Background |\n|------|---------|-------------------|\n| `generate_video` | Generate video from text / image prompt | Yes |\n| `sora_remix_video` | Modify existing Sora video | Yes |\n| `sora_delete_video` | Delete a Sora video | No |\n| `capture_video_frame` | Extract frame as image | No |\n| `analyze_video` | Watch and understand video content | No |\n| `transcribe_video` | Extract audio transcript | No |\n| `generate_subtitles` | Create SRT / VTT subtitle file | No |\n| `burn_subtitles` | Burn subtitles onto video | Yes |\n| `burn_highlighted_captions` | TikTok / karaoke-style word-by-word captions | Yes |\n| `text_to_speech` | Generate voiceover audio from text | No |\n| `add_audio_to_video` | Add / replace audio track on video | Yes |\n| `clip_video` | Extract a time segment from video | Yes |\n| `stitch_videos` | Concatenate multiple clips | Yes |\n| `overlay_text` | Add text / titles to video | Yes |\n\n## Video Understanding\n\nYou can **watch and analyze any video** using `analyze_video`. This sends the video to a multimodal AI that sees both visual and audio content.\n\n### When to use `analyze_video`\n\n- After generating a video: check if it matches your intent\n- Before stitching: verify scene consistency across clips\n- Quality review: check for glitches, character drift, lighting issues\n- Content understanding: \"what happens in this video?\"\n\n### Analysis Types\n\n```python\nanalyze_video(file_id=\"...\", analysis_type=\"general\")\nanalyze_video(file_id=\"...\", analysis_type=\"quality_review\")\nanalyze_video(file_id=\"...\", analysis_type=\"scene_breakdown\")\nanalyze_video(file_id=\"...\", question=\"Does this match: [original prompt]?\")\n```\n\n### Self-Review Workflow\n\nAlways review generated videos before delivering to the user:\n\n```python\nresult = generate_video(prompt=\"...\", model=\"veo-3.1-generate-preview\")\nreview = analyze_video(file_id=\"video_file_id\", analysis_type=\"quality_review\")\n# If issues found, regenerate with adjustments. If quality is good, proceed to editing.\n```\n\n## Script Planning\n\nFor longer, cohesive videos, plan the FULL SCRIPT before generating:\n\n### 1. Scene Breakdown\n- **Scenes:** break story into segments\n  - Sora: 4 / 8 / 12 seconds per scene\n  - Veo: 4-8 seconds per scene\n  - Seedance: 4-15 seconds per scene (native audio with lip-sync)\n- **Camera:** shot type (wide, close-up, tracking), angles, movement\n- **Transitions:** how each scene connects to the next\n- **Consistency:** character descriptions, color palette, visual style\n\n## Scene Chaining Technique\n\nTo create seamless multi-scene videos:\n\n### Scene 1 (text-to-video)\n\n```python\ngenerate_video(prompt=\"...\", model=\"veo-3.1-generate-preview\")\n```\n\n### Scene 2+ (image-to-video)\n\n```python\ncapture_video_frame(video_file_id=\"scene1_file_id\", frame_position=\"last\")\ngenerate_video(prompt=\"continuation: ...\", image_file_id=\"captured_frame_id\")\n```\n\nRepeat: extract last frame → generate next scene.\n\n### Stitching Scenes Together\n\nAfter generating all scenes, combine them:\n\n```python\nstitch_videos(video_file_ids=[\"scene1_id\", \"scene2_id\", \"scene3_id\"])\n\nstitch_videos(\n    video_file_ids=[\"scene1_id\", \"scene2_id\", \"scene3_id\"],\n    transition=\"crossfade\",\n    crossfade_duration=0.5,\n)\n```\n\n## Subtitle / Caption Workflow\n\n### Full pipeline: Video → Transcript → Subtitles → Burned Video\n\n```python\ntranscript = transcribe_video(file_id=\"video_file_id\")\n\nsubs = generate_subtitles(file_id=\"video_file_id\", transcript=transcript, format=\"srt\")\n\nburn_subtitles(\n    video_file_id=\"video_file_id\",\n    subtitle_file_id=subs.file_id,\n    style=\"bold_outline\",\n    position=\"bottom\",\n)\n```\n\n### Subtitle Styles\n\n| Style | Effect |\n|-------|--------|\n| `default` | Plain white text |\n| `bold_outline` | Bold white with black outline (recommended) |\n| `shadow` | White text with drop shadow |\n| `box` | White text on semi-transparent black box |\n\n## Text Overlays\n\nAdd titles, lower-thirds, CTAs, and other graphics:\n\n```python\noverlay_text(\n    video_file_id=\"video_file_id\",\n    overlays=[\n        {\n            \"text\": \"Episode 1: The Beginning\",\n            \"start_time\": 0.0,\n            \"end_time\": 3.0,\n            \"position\": \"center\",\n            \"font_size\": 48,\n            \"color\": \"white\",\n            \"background\": \"black@0.5\",\n        },\n        {\n            \"text\": \"Subscribe for more!\",\n            \"start_time\": 10.0,\n            \"end_time\": 14.0,\n            \"position\": \"bottom-right\",\n            \"font_size\": 28,\n        },\n    ],\n)\n```\n\n### Overlay Positions\n\n`top`, `bottom`, `center`, `top-left`, `top-right`, `bottom-left`, `bottom-right`\n\n## Voiceover / Narration\n\nGenerate natural-sounding voiceover with TTS and add it to any video:\n\n```python\naudio = text_to_speech(\n    text=\"Welcome to our product. Here's how it works...\",\n    voice=\"nova\",\n    model=\"tts-1\",\n)\n\nadd_audio_to_video(\n    video_file_id=\"video_id\",\n    audio_file_id=audio.file_id,\n    mode=\"replace\",\n)\n\nadd_audio_to_video(\n    video_file_id=\"video_id\",\n    audio_file_id=audio.file_id,\n    mode=\"mix\",\n    audio_volume=0.8,\n)\n```\n\n### Available Voices\n\n`alloy`, `ash`, `coral`, `echo`, `fable`, `nova` (recommended), `onyx`, `sage`, `shimmer`\n\n## Highlighted Captions (TikTok / Reels Style)\n\nAdd word-by-word highlighted captions that light up as spoken:\n\n```python\nburn_highlighted_captions(\n    video_file_id=\"video_id\",\n    style=\"tiktok\",\n    highlight_color=\"#3B82F6\",\n    base_color=\"white\",\n    words_per_group=3,\n    position=\"center\",\n)\n\nburn_highlighted_captions(\n    video_file_id=\"video_id\",\n    style=\"karaoke\",\n    highlight_color=\"yellow\",\n    base_color=\"white\",\n    background=\"black@0.6\",\n    words_per_group=4,\n    position=\"bottom\",\n)\n```\n\n## Video Clipping\n\nExtract segments from longer videos:\n\n```python\nclip_video(\n    video_file_id=\"long_video_id\",\n    start_time=45.0,\n    end_time=60.0,\n)\n```\n\n## UGC / TikTok Production Workflow\n\nComplete workflow for producing UGC-style content:\n\n1. **Script:** plan scenes, dialogue, and visual style\n2. **Generate:** create each scene with `generate_video`\n3. **Review:** use `analyze_video` to check each scene for quality\n4. **Chain:** extract last frames with `capture_video_frame`, generate next scenes\n5. **Stitch:** combine all scenes with `stitch_videos`\n6. **Narrate:** generate voiceover with `text_to_speech` + `add_audio_to_video`\n7. **Caption:** add TikTok-style captions with `burn_highlighted_captions`\n8. **Overlay:** add titles / CTAs with `overlay_text`\n9. **Final review:** use `analyze_video` on the final video for quality check\n\n### Example: Narrated UGC Video\n\n```python\ngenerate_video(prompt=\"...\", model=\"veo-3.1-generate-preview\")\n\naudio = text_to_speech(text=\"Your narration script here...\", voice=\"nova\")\n\nadd_audio_to_video(video_file_id=\"generated_video_id\", audio_file_id=audio.file_id)\n\nburn_highlighted_captions(video_file_id=\"narrated_video_id\", style=\"tiktok\")\n```\n\n### Example: Podcast to Short-Form Clips\n\n```python\ntranscript = transcribe_video(file_id=\"podcast_video_id\")\n\nanalysis = analyze_video(\n    file_id=\"podcast_video_id\",\n    question=\"Identify the 3 most memorable / quotable moments with timestamps\",\n    analysis_type=\"scene_breakdown\",\n)\n\nclip_video(video_file_id=\"podcast_video_id\", start_time=120.0, end_time=150.0)\nclip_video(video_file_id=\"podcast_video_id\", start_time=340.0, end_time=365.0)\n\nstitch_videos(video_file_ids=[\"clip1_id\", \"clip2_id\"])\n\nburn_highlighted_captions(video_file_id=\"stitched_id\", style=\"tiktok\")\n```\n\n## Prompt Structure\n\nEach scene prompt should include:\n\n- \"Continuation of previous scene\" (for scenes 2+)\n- Consistent character / setting descriptions\n- Specific action for this segment\n- Camera movement direction\n\n## Control Principles (most important)\n\n- Treat API params as the **container** and prompt text as the **content**:\n  - `model`, `size` / `aspect_ratio`, and `duration_seconds` must be set explicitly in the tool call.\n  - Do not expect prose like \"make it longer\" or \"make it vertical\" to override API parameters.\n- Use detail for control, brevity for exploration:\n  - Short prompts give more creative variation.\n  - Detailed prompts improve consistency and shot control.\n- Iterate in small steps:\n  - Change one major variable at a time (camera, lighting, action, or palette).\n  - Keep what works fixed and only modify the target dimension.\n\n## Key Parameters\n\n| Parameter | Description |\n|-----------|-------------|\n| `image_file_id` | Use for image-to-video (scene continuity) |\n| `capture_video_frame` | Extract frames with `position=\"last\"` \\| `\"first\"` \\| `\"middle\"` |\n| `size` | For Sora only. One of: `\"720x1280\"`, `\"1280x720\"`, `\"1024x1792\"`, `\"1792x1024\"` |\n| `aspect_ratio` | For Veo only. One of: `\"16:9\"` or `\"9:16\"` |\n| `duration_seconds` | Sora: 4, 8, or 12 seconds only. Veo: 4-8 seconds |\n\n## Important Input Rules\n\n- Use exact values accepted by the tool schema. Do not send aliases like `landscape`, `portrait`, `720p`, or `1080p`.\n- For Sora, prefer `size` and do not send `aspect_ratio`.\n- For Veo, prefer `aspect_ratio` and do not send `size`.\n- For Seedance, use `aspect_ratio` and optionally `resolution`. Do not pass `size`.\n- Keep the same `size` / `aspect_ratio` across chained scenes for continuity.\n\n## Model Selection Guide\n\n**When the user mentions a specific model name, always use that model.** Map user requests to the correct `model` parameter:\n\n| User says | `model` parameter |\n|-----------|-------------------|\n| \"use seedance\", \"seedance video\" | `\"seedance-2\"` |\n| \"fast seedance\" | `\"seedance-2-fast\"` |\n| \"use sora\", \"sora video\" | `\"sora-2\"` |\n| \"sora pro\" | `\"sora-2-pro\"` |\n| \"use veo\", \"veo video\" | `\"veo-3.1-generate-preview\"` |\n| \"fast veo\" | `\"veo-3.1-fast-generate-preview\"` |\n\n## Model-Specific Parameter Matrix\n\n- **Sora models (`sora-2`, `sora-2-pro`)**\n  - Allowed sizing parameter: `size`\n  - Allowed `size` values: `\"720x1280\"`, `\"1280x720\"`, `\"1024x1792\"`, `\"1792x1024\"`\n  - Do not pass `aspect_ratio`\n  - Practical default pair: `\"1280x720\"` or `\"720x1280\"`\n- **Veo models (`veo-3.1-generate-preview`, `veo-3.1-fast-generate-preview`)**\n  - Allowed sizing parameter: `aspect_ratio`\n  - Allowed `aspect_ratio` values: `\"16:9\"`, `\"9:16\"`\n  - Do not pass `size`\n- **Seedance models (`seedance-2`, `seedance-2-fast`)**\n  - Allowed sizing parameters: `aspect_ratio` and `resolution`\n  - Allowed `aspect_ratio` values: `\"16:9\"`, `\"9:16\"`, `\"1:1\"`, `\"4:3\"`, `\"3:4\"`\n  - Allowed `resolution` values: `\"480p\"`, `\"720p\"`\n  - Supports `generate_audio=true` for native audio with lip-sync\n  - Do not pass `size`\n\n## Duration Limits\n\n- **Sora:** 4, 8, or 12 seconds per generation. Use scene chaining + `stitch_videos` for longer videos.\n- **Veo:** 4, 5, 6, 7, or 8 seconds per generation.\n- **Seedance:** 4-15 seconds per generation (most flexible). Supports `generate_audio=true` for native audio with lip-sync.\n\n## High-Control Prompt Template\n\nUse this structure when you want predictable output:\n\n```text\nStyle/Tone: [realistic, cinematic, animation, documentary, etc.]\nSubject/World: [who/what is in frame, key visual anchors]\nCamera: [shot size + angle + movement]\nLighting/Palette: [light direction + 3-5 color anchors]\nAction Beats:\n- [beat 1 with timing/count]\n- [beat 2 with timing/count]\n- [beat 3 with timing/count]\nAudio/Dialogue: [short lines or ambient cues]\nConstraints: [no logos/brands, no text overlays, etc.]\n```\n\n## Best Practices\n\n1. **Review before delivering:** always use `analyze_video` to check your output.\n2. **Maintain visual consistency:** use the same character descriptions, lighting, and style across all scenes.\n3. **Plan transitions:** design the end of each scene to flow into the next.\n4. **Batch similar scenes:** generate scenes with similar settings together.\n5. **Review before chaining:** check each scene before using its last frame for the next.\n6. **Use single-variable iteration:** remix / regenerate by changing one variable at a time.\n7. **Add captions for accessibility:** use the subtitle pipeline for all UGC content.","tags":["video","generation","marketing","skills","hyperfx-ai","agent-skills","ai-agent","claude","claude-code","claude-skills","codex","cursor"],"capabilities":["skill","source-hyperfx-ai","skill-video-generation","topic-agent-skills","topic-ai-agent","topic-claude","topic-claude-code","topic-claude-skills","topic-codex","topic-cursor","topic-google-ads","topic-hermes","topic-marketing","topic-mcp","topic-meta-ads"],"categories":["marketing-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/hyperfx-ai/marketing-skills/video-generation","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add hyperfx-ai/marketing-skills","source_repo":"https://github.com/hyperfx-ai/marketing-skills","install_from":"skills.sh"}},"qualityScore":"0.462","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 24 github stars · SKILL.md body (13,193 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:05:17.660Z","embedding":null,"createdAt":"2026-05-07T13:06:44.599Z","updatedAt":"2026-05-18T19:05:17.660Z","lastSeenAt":"2026-05-18T19:05:17.660Z","tsv":"'-1':836 '-15':512,1661 '-2':1485,1489,1496,1500,1527,1529,1586,1588 '-3.1':448,569,1084,1507,1514,1556,1561 '-5':1715 '-8':506,1387 '/mcp)':82 '0.0':754 '0.5':645,767 '0.6':942 '0.8':871 '1':489,558,749,983,1605,1606,1721,1747 '10.0':774 '1024x1792':1362,1540 '1080p':1409 '12':500,1382,1637 '120.0':1173 '1280x720':1361,1539,1550 '14.0':777 '150.0':1176 '16':1371,1375,1575,1578,1601,1604 '1792x1024':1363,1541 '2':574,991,1223,1725,1759 '28':784 '3':921,999,1152,1608,1609,1714,1729,1774 '3.0':757 '340.0':1187 '365.0':1190 '3b82f6':914 '4':498,505,511,946,1010,1379,1386,1607,1610,1634,1650,1660,1788 '45.0':967 '48':762 '480p':1614 '5':1022,1651,1798 '6':1030,1652,1813 '60.0':970 '7':1042,1653,1828 '720p':1407,1615 '720x1280':1360,1538,1552 '8':499,1053,1380,1635,1655 '9':1061,1372,1374,1576,1577,1602,1603 'accept':1395 'access':1832 'across':374,1448,1771 'action':1229,1316,1718 'ad':163,174,195,198,201 'ad-creative-gener':173 'add':147,293,297,321,728,812,837,853,889,1038,1044,1055,1099,1829 'adjust':469 'agent':87 'ai':8,61,346 'alias':1403 'allow':1531,1535,1566,1571,1590,1597,1611 'alloy':874 'alway':432,1464,1751 'ambient':1736 'analysi':31,126,392,399,406,414,460,1141,1159 'analyz':54,127,242,333,337,357,395,402,410,418,453,1002,1065,1142,1753 'anchor':1705,1717 'angl':530,1709 'anim':1695 'api':1241,1281 'app.hyperfx.ai':81 'app.hyperfx.ai/mcp)':80 'ash':875 'aspect':1254,1364,1418,1423,1433,1446,1545,1569,1572,1593,1598 'assum':76 'audio':39,143,148,253,289,294,299,352,517,818,838,846,854,862,869,1039,1088,1100,1109,1618,1622,1669,1673 'audio.file':849,865,1112 'audio/dialogue':1732 'avail':93,202,872 'back':66 'background':208,765,940 'base':915,937 'batch':1789 'beat':1719,1720,1724,1728 'begin':751 'best':1745 'black':708,724,766,941 'bold':691,703,705 'bottom':694,780,788,797,800,948 'bottom-left':796 'bottom-right':779,799 'box':717,725 'brand':166 'break':493 'breakdown':417,491,1162 'breviti':1287 'burn':138,140,264,266,271,654,677,902,924,1050,1114,1200 'byted':101 'call':1266 'camera':522,1233,1314,1706 'campaign':191 'caption':36,135,142,273,282,647,885,895,904,926,1043,1048,1052,1116,1202,1830 'captur':129,234,580,599,1016,1344 'center':759,789,923 'chain':29,548,1011,1449,1643,1801 'chang':1307,1822 'charact':381,541,1225,1766 'check':363,378,1005,1073,1756,1802 'cinemat':1694 'clip':41,152,304,317,375,950,957,1131,1163,1177 'clip1':1196 'clip2':1198 'close':527 'close-up':526 'cohes':481 'color':543,763,913,916,935,938,1716 'combin':616,1024 'complet':975 'composit':165 'concaten':315 'configur':108 'connect':84,536 'consist':373,540,1224,1299,1762 'constraint':1738 'contain':1245 'content':248,353,385,982,1251,1840 'continu':595,1217,1343,1452 'control':1236,1286,1302,1680 'coral':876 'correct':1473 'creat':258,551,993 'creativ':164,175,1294 'crossfad':642,643 'ctas':733,1057 'cue':1737 'default':699,1548 'delet':124,227,229 'deliv':437,1750 'descript':542,1227,1332,1767 'design':1777 'detail':1284,1296 'dialogu':987 'dimens':1328 'direct':1235,1713 'documentari':1696 'drift':382 'drop':715 'durat':644,1257,1376,1631 'echo':877 'edit':49,53,151,476 'effect':698 'end':5,7,755,775,968,1174,1188,1779 'end-to-end':4 'episod':748 'etc':106,1697,1744 'exact':1393 'exampl':1074,1125 'exist':222 'expect':1269 'explicit':1262 'explor':1289 'expos':68 'extract':167,237,252,306,603,951,1012,1347 'fabl':878 'fast':1486,1490,1511,1516,1563,1589 'fast-generate-preview':1515,1562 'ffmpeg':65 'ffmpeg-back':64 'file':262,397,404,412,420,455,458,584,587,597,622,633,660,663,668,671,680,683,686,741,744,842,847,858,863,906,928,960,1104,1110,1118,1136,1144,1166,1180,1194,1204,1334 'final':1062,1069 'finish':178 'first':1352 'fix':1322 'flexibl':1666 'flow':1784 'font':760,782 'form':1130 'format':675 'found':466 'frame':131,236,238,582,589,600,605,1014,1018,1346,1348,1702,1809 'full':485,649 'general':401 'generat':3,24,48,52,117,118,136,162,171,176,209,211,256,287,360,434,443,450,488,564,571,592,606,613,666,804,992,997,1019,1032,1079,1086,1106,1509,1517,1558,1564,1617,1640,1658,1664,1668,1792 'generate-preview':449,570,1085,1508,1557 'give':1292 'glitch':380 'good':473 'googl':99,194 'google-ad':193 'graphic':736 'group':115,920,945 'guid':50,1455 'happen':388 'high':1679 'high-control':1678 'highlight':141,272,884,894,903,912,925,934,1051,1115,1201 'hyper':13,71,78,111 'id':398,405,413,421,456,459,585,588,598,601,623,625,627,629,634,636,638,640,661,664,669,672,681,684,687,689,742,745,843,845,848,850,859,861,864,866,907,909,929,931,961,964,1105,1108,1111,1113,1119,1122,1137,1140,1145,1148,1167,1170,1181,1184,1195,1197,1199,1205,1207,1335 'identifi':1150 'imag':21,161,170,215,240,576,596,1333,1339 'image-gener':169 'image-to-video':20,575,1338 'import':1239,1389 'improv':1298 'includ':1216 'input':1390 'instagram':185 'integr':112 'intent':368 'issu':384,465 'iter':1303,1818 'karaok':35,276,933 'karaoke-styl':275 'keep':1319,1442 'key':1329,1703 'landscap':1405 'last':591,604,1013,1351,1808 'left':792,798 'light':383,897,1315,1712,1768 'lighting/palette':1711 'like':1271,1404 'limit':1632 'line':1734 'linkedin':187 'lip':520,1625,1676 'lip-sync':519,1624,1675 'logos/brands':1740 'long':962 'longer':480,954,1274,1647 'lower':731 'lower-third':730 'maintain':1760 'major':1309 'make':1272,1276 'map':1468 'match':366,425 'matrix':1523 'mcp':14,72,79 'memor':1154 'mention':1459 'meta':197 'meta-ad':196 'middl':1353 'mix':40,868 'mode':851,867 'model':62,446,567,834,1082,1252,1453,1462,1467,1474,1478,1520,1525,1554,1584 'model-specif':1519 'modifi':221,1325 'moment':1156 'movement':531,1234,1710 'multi':554 'multi-scen':553 'multimod':345 'multipl':316 'must':1259 'name':1463 'narrat':803,1031,1075,1094,1120 'nativ':516,1621,1672 'natur':806 'natural-sound':805 'next':539,607,1020,1787,1812 'nova':833,879,1098 'one':1308,1358,1369,1823 'onto':268 'onyx':881 'openai':97,103 'option':1436 'origin':426 'outlin':692,704,709 'output':1690,1758 'overlay':45,156,319,727,738,746,785,1054,1059,1743 'overrid':1280 'paid':189 'pair':1549 'palett':544,1318 'param':1242 'paramet':1282,1330,1331,1475,1479,1522,1533,1568,1592 'pass':1440,1544,1581,1629 'per':502,508,514,919,944,1639,1657,1663 'pipelin':650,1836 'plain':700 'plan':478,483,985,1775 'platform':182 'podcast':1126,1138,1146,1168,1182 'portrait':1406 'posit':590,693,758,778,786,922,947,1350 'post':57,177 'post-process':56 'practic':1547,1746 'predict':1689 'prefer':1412,1422 'preview':451,572,1087,1510,1518,1559,1565 'previous':1219 'principl':1237 'pro':1498,1501,1530 'proceed':474 'process':58 'produc':978 'product':10,826,973 'prompt':216,427,445,566,594,1081,1210,1214,1247,1291,1297,1681 'prose':1270 'provid':96 'purpos':205 'python':394,441,563,579,618,656,737,817,901,956,1078,1132 'qualiti':376,408,462,471,1009,1072 'question':422,1149 'quotabl':1155 'ratio':1255,1365,1419,1424,1434,1447,1546,1570,1573,1594,1599 'realist':1693 'recommend':710,880 'reel':887 'regener':467,1820 'remix':121,219,1819 'repeat':602 'replac':298,852 'request':1470 'requir':73 'resolut':1437,1596,1612 'result':442 'review':377,409,430,433,452,463,1000,1063,1748,1799 'right':781,795,801 'rule':1391 'run':188,206 'sage':882 'say':1477 'scene':28,372,416,490,492,503,509,515,535,547,555,557,573,608,610,615,986,995,1007,1021,1026,1161,1213,1220,1222,1342,1450,1642,1773,1782,1791,1793,1804 'scene1':586,624,635 'scene2':626,637 'scene3':628,639 'schema':1399 'scope':160 'script':477,486,984,1095 'seamless':552 'second':501,507,513,1258,1377,1383,1388,1638,1656,1662 'see':348 'seedanc':27,102,510,1431,1481,1482,1484,1487,1488,1583,1585,1587,1659 'segment':309,496,952,1232 'select':1454 'self':429 'self-review':428 'semi':722 'semi-transpar':721 'send':340,1402,1417,1428 'set':1226,1261,1796 'shadow':711,716 'shimmer':883 'short':1129,1290,1733 'short-form':1128 'shot':523,1301,1707 'similar':1790,1795 'singl':1816 'single-vari':1815 'size':761,783,1253,1354,1413,1429,1441,1445,1532,1534,1536,1567,1582,1591,1630,1708 'skill':75 'skill-video-generation' 'small':1305 'social':181 'sora':25,98,120,123,218,223,226,231,497,1356,1378,1411,1492,1493,1495,1497,1499,1524,1526,1528,1633 'sound':807 'source-hyperfx-ai' 'specif':1228,1461,1521 'speech':146,286,821,1037,1091 'spoken':900 'srt':259,676 'start':752,772,965,1171,1185 'step':1306 'stitch':42,154,313,370,609,619,630,1023,1028,1191,1206,1644 'stori':494 'structur':1211,1685 'style':277,546,690,696,697,888,910,932,981,990,1047,1123,1208,1770 'style/tone':1692 'sub':665 'subject/world':1698 'subs.file':688 'subscrib':769 'subtitl':33,134,137,139,257,261,265,267,646,653,667,678,685,695,1835 'support':1616,1667 'surfac':114 'sync':521,1626,1677 'target':1327 'techniqu':549 'templat':1682 'text':16,44,144,157,214,284,291,320,322,560,702,713,719,726,739,747,768,819,822,1035,1060,1089,1092,1248,1691,1742 'text-to-video':15,559 'third':732 'tiktok':34,184,200,274,886,911,972,1046,1124,1209 'tiktok-ad':199 'tiktok-styl':1045 'time':308,753,756,773,776,966,969,1172,1175,1186,1189,1313,1827 'timestamp':1158 'timing/count':1723,1727,1731 'titl':323,729,1056 'togeth':611,1797 'tool':67,90,113,116,203,204,1265,1398 'top':787,791,794 'top-left':790 'top-right':793 'topic-agent-skills' 'topic-ai-agent' 'topic-claude' 'topic-claude-code' 'topic-claude-skills' 'topic-codex' 'topic-cursor' 'topic-google-ads' 'topic-hermes' 'topic-marketing' 'topic-mcp' 'topic-meta-ads' 'track':300,529 'transcrib':132,250,658,1134 'transcript':32,105,254,652,657,673,674,1133 'transit':532,641,1776 'transpar':723 'treat':1240 'true':1619,1670 'tts':38,104,810,835 'type':393,400,407,415,461,524,1160 'ugc':971,980,1076,1839 'ugc-styl':979 'under':95 'understand':246,328,386 'us':46 'use':60,168,183,192,336,356,1001,1064,1283,1336,1392,1432,1465,1480,1491,1502,1641,1683,1752,1763,1806,1814,1833 'user':440,1458,1469,1476 'valu':1394,1537,1574,1600,1613 'variabl':1310,1817,1824 'variat':1295 'veo':26,100,447,504,568,1083,1367,1385,1421,1503,1504,1506,1512,1513,1553,1555,1560,1649 'verifi':371 'vertic':1278 'video':2,9,18,23,30,47,59,119,122,125,128,130,133,150,153,155,179,190,210,212,220,224,228,232,235,243,247,251,269,296,302,305,311,314,325,327,335,338,342,358,362,391,396,403,411,419,435,444,454,457,482,556,562,565,578,581,583,593,620,621,631,632,651,655,659,662,670,679,682,740,743,816,840,841,844,856,857,860,905,908,927,930,949,955,958,959,963,998,1003,1017,1029,1041,1066,1070,1077,1080,1102,1103,1107,1117,1121,1135,1139,1143,1147,1164,1165,1169,1178,1179,1183,1192,1193,1203,1341,1345,1483,1494,1505,1645,1648,1754 'video-gener':1 'visual':350,545,989,1704,1761 'voic':832,873,1097 'voiceov':37,288,802,808,1033 'volum':870 'vtt':260 'want':1688 'watch':244,331 'welcom':823 'white':701,706,712,718,764,917,939 'who/what':1699 'wide':525 'word':279,281,891,893,918,943 'word-by-word':278,890 'work':831,1321 'workflow':431,648,974,976 'yellow':936 'yes':217,225,270,283,303,312,318,326","prices":[{"id":"e929e0a0-59e6-4e0c-ac67-a85b2fc99693","listingId":"3c301c02-19d3-41fd-8a0b-339a9ab8413d","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"hyperfx-ai","category":"marketing-skills","install_from":"skills.sh"},"createdAt":"2026-05-07T13:06:44.599Z"}],"sources":[{"listingId":"3c301c02-19d3-41fd-8a0b-339a9ab8413d","source":"github","sourceId":"hyperfx-ai/marketing-skills/video-generation","sourceUrl":"https://github.com/hyperfx-ai/marketing-skills/tree/main/skills/video-generation","isPrimary":false,"firstSeenAt":"2026-05-07T13:06:44.599Z","lastSeenAt":"2026-05-18T19:05:17.660Z"}],"details":{"listingId":"3c301c02-19d3-41fd-8a0b-339a9ab8413d","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"hyperfx-ai","slug":"video-generation","github":{"repo":"hyperfx-ai/marketing-skills","stars":24,"topics":["agent-skills","ai-agent","claude","claude-code","claude-skills","codex","cursor","google-ads","hermes","marketing","mcp","meta-ads","openclaw","seo"],"license":"mit","html_url":"https://github.com/hyperfx-ai/marketing-skills","pushed_at":"2026-05-09T22:58:46Z","description":"Marketing skills for AI agents — paid ads, social media, SEO, competitor research, creative generation, email, analytics, and more. Powered by Hyper MCP.","skill_md_sha":"244cf40e0f3da8e1a2ccf0891fc43c8e9367e8ba","skill_md_path":"skills/video-generation/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/hyperfx-ai/marketing-skills/tree/main/skills/video-generation"},"layout":"multi","source":"github","category":"marketing-skills","frontmatter":{"name":"video-generation","description":"End-to-end AI video production through the Hyper MCP — text-to-video and image-to-video generation (Sora, Veo, Seedance), scene chaining, video analysis, transcription, subtitles, TikTok / karaoke captions, voiceover (TTS), audio mixing, clipping, stitching, and text overlays. Use when the user asks to generate a video, create UGC, scene-chain, add captions or subtitles, add narration, stitch clips, clip a podcast highlight, or do any AI video editing."},"skills_sh_url":"https://skills.sh/hyperfx-ai/marketing-skills/video-generation"},"updatedAt":"2026-05-18T19:05:17.660Z"}}