[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J78360DTFVVK1CWTDSXCEF":3,"skill-same:01M6J78360DTFVVK1CWTDSXCEF":81},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6J78360DTFVVK1CWTDSXCEF","video-editing",null,"AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.","onfire7777\u002Funiversal-ai-skills-library","onfire7777","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F240866566?v=4","01M6HZJCF2QEW8DY7HE1JDKGK2","Jake B","01M6HZJCKK8SEXKN76V9SGKZ12",17,"MIT","https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"Video","video editing","editing","edit","full pipeline","for","video content","cut","ffmpeg","full","elevenlabs","build","use","workflows","capture","fal","polish","Remotion","pipeline","create","2026-11-10 10:12:30",false,"---\nname: video-editing\ndescription: AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.\n---\n\n# Video Editing\n\nAI-assisted editing for real footage. Not generation from prompts. Editing existing video fast.\n\n## When to Activate\n\n- User wants to edit, cut, or structure video footage\n- Turning long recordings into short-form content\n- Building vlogs, tutorials, or demo videos from raw capture\n- Adding overlays, subtitles, music, or voiceover to existing video\n- Reframing video for different platforms (YouTube, TikTok, Instagram)\n- User says \"edit video\", \"cut this footage\", \"make a vlog\", or \"video workflow\"\n\n## Core Thesis\n\nAI video editing is useful when you stop asking it to create the whole video and start using it to compress, structure, and augment real footage. The value is not generation. The value is compression.\n\n## The Pipeline\n\n```\nScreen Studio \u002F raw footage\n  → Claude \u002F Codex\n  → FFmpeg\n  → Remotion\n  → ElevenLabs \u002F fal.ai\n  → Descript or CapCut\n```\n\nEach layer has a specific job. Do not skip layers. Do not try to make one tool do everything.\n\n## Layer 1: Capture (Screen Studio \u002F Raw Footage)\n\nCollect the source material:\n- **Screen Studio**: polished screen recordings for app demos, coding sessions, browser workflows\n- **Raw camera footage**: vlog footage, interviews, event recordings\n- **Desktop capture via VideoDB**: session recording with real-time context (see `videodb` skill)\n\nOutput: raw files ready for organization.\n\n## Layer 2: Organization (Claude \u002F Codex)\n\nUse Claude Code or Codex to:\n- **Transcribe and label**: generate transcript, identify topics and themes\n- **Plan structure**: decide what stays, what gets cut, what order works\n- **Identify dead sections**: find pauses, tangents, repeated takes\n- **Generate edit decision list**: timestamps for cuts, segments to keep\n- **Scaffold FFmpeg and Remotion code**: generate the commands and compositions\n\n```\nExample prompt:\n\"Here's the transcript of a 4-hour recording. Identify the 8 strongest segments\nfor a 24-minute vlog. Give me FFmpeg cut commands for each segment.\"\n```\n\nThis layer is about structure, not final creative taste.\n\n## Layer 3: Deterministic Cuts (FFmpeg)\n\nFFmpeg handles the boring but critical work: splitting, trimming, concatenating, and preprocessing.\n\n### Extract segment by timestamp\n\n```bash\nffmpeg -i raw.mp4 -ss 00:12:30 -to 00:15:45 -c copy segment_01.mp4\n```\n\n### Batch cut from edit decision list\n\n```bash\n#!\u002Fbin\u002Fbash\n# cuts.txt: start,end,label\nwhile IFS=, read -r start end label; do\n  ffmpeg -i raw.mp4 -ss \"$start\" -to \"$end\" -c copy \"segments\u002F${label}.mp4\"\ndone \u003C cuts.txt\n```\n\n### Concatenate segments\n\n```bash\n# Create file list\nfor f in segments\u002F*.mp4; do echo \"file '$f'\"; done > concat.txt\nffmpeg -f concat -safe 0 -i concat.txt -c copy assembled.mp4\n```\n\n### Create proxy for faster editing\n\n```bash\nffmpeg -i raw.mp4 -vf \"scale=960:-2\" -c:v libx264 -preset ultrafast -crf 28 proxy.mp4\n```\n\n### Extract audio for transcription\n\n```bash\nffmpeg -i raw.mp4 -vn -acodec pcm_s16le -ar 16000 audio.wav\n```\n\n### Normalize audio levels\n\n```bash\nffmpeg -i segment.mp4 -af loudnorm=I=-16:TP=-1.5:LRA=11 -c:v copy normalized.mp4\n```\n\n## Layer 4: Programmable Composition (Remotion)\n\nRemotion turns editing problems into composable code. Use it for things that traditional editors make painful:\n\n### When to use Remotion\n\n- Overlays: text, images, branding, lower thirds\n- Data visualizations: charts, stats, animated numbers\n- Motion graphics: transitions, explainer animations\n- Composable scenes: reusable templates across videos\n- Product demos: annotated screenshots, UI highlights\n\n### Basic Remotion composition\n\n```tsx\nimport { AbsoluteFill, Sequence, Video, useCurrentFrame } from \"remotion\";\n\nexport const VlogComposition: React.FC = () => {\n  const frame = useCurrentFrame();\n\n  return (\n    \u003CAbsoluteFill>\n      {\u002F* Main footage *\u002F}\n      \u003CSequence from={0} durationInFrames={300}>\n        \u003CVideo src=\"\u002Fsegments\u002Fintro.mp4\" \u002F>\n      \u003C\u002FSequence>\n\n      {\u002F* Title overlay *\u002F}\n      \u003CSequence from={30} durationInFrames={90}>\n        \u003CAbsoluteFill style={{\n          justifyContent: \"center\",\n          alignItems: \"center\",\n        }}>\n          \u003Ch1 style={{\n            fontSize: 72,\n            color: \"white\",\n            textShadow: \"2px 2px 8px rgba(0,0,0,0.8)\",\n          }}>\n            The AI Editing Stack\n          \u003C\u002Fh1>\n        \u003C\u002FAbsoluteFill>\n      \u003C\u002FSequence>\n\n      {\u002F* Next segment *\u002F}\n      \u003CSequence from={300} durationInFrames={450}>\n        \u003CVideo src=\"\u002Fsegments\u002Fdemo.mp4\" \u002F>\n      \u003C\u002FSequence>\n    \u003C\u002FAbsoluteFill>\n  );\n};\n```\n\n### Render output\n\n```bash\nnpx remotion render src\u002Findex.ts VlogComposition output.mp4\n```\n\nSee the [Remotion docs](https:\u002F\u002Fwww.remotion.dev\u002Fdocs) for detailed patterns and API reference.\n\n## Layer 5: Generated Assets (ElevenLabs \u002F fal.ai)\n\nGenerate only what you need. Do not generate the whole video.\n\n### Voiceover with ElevenLabs\n\n```python\nimport os\nimport requests\n\nresp = requests.post(\n    f\"https:\u002F\u002Fapi.elevenlabs.io\u002Fv1\u002Ftext-to-speech\u002F{voice_id}\",\n    headers={\n        \"xi-api-key\": os.environ[\"ELEVENLABS_API_KEY\"],\n        \"Content-Type\": \"application\u002Fjson\"\n    },\n    json={\n        \"text\": \"Your narration text here\",\n        \"model_id\": \"eleven_turbo_v2_5\",\n        \"voice_settings\": {\"stability\": 0.5, \"similarity_boost\": 0.75}\n    }\n)\nwith open(\"voiceover.mp3\", \"wb\") as f:\n    f.write(resp.content)\n```\n\n### Music and SFX with fal.ai\n\nUse the `fal-ai-media` skill for:\n- Background music generation\n- Sound effects (ThinkSound model for video-to-audio)\n- Transition sounds\n\n### Generated visuals with fal.ai\n\nUse for insert shots, thumbnails, or b-roll that doesn't exist:\n```\ngenerate(model_name: \"fal-ai\u002Fnano-banana-pro\", input: {\n  \"prompt\": \"professional thumbnail for tech vlog, dark background, code on screen\",\n  \"image_size\": \"landscape_16_9\"\n})\n```\n\n### VideoDB generative audio\n\nIf VideoDB is configured:\n```python\nvoiceover = coll.generate_voice(text=\"Narration here\", voice=\"alloy\")\nmusic = coll.generate_music(prompt=\"lo-fi background for coding vlog\", duration=120)\nsfx = coll.generate_sound_effect(prompt=\"subtle whoosh transition\")\n```\n\n## Layer 6: Final Polish (Descript \u002F CapCut)\n\nThe last layer is human. Use a traditional editor for:\n- **Pacing**: adjust cuts that feel too fast or slow\n- **Captions**: auto-generated, then manually cleaned\n- **Color grading**: basic correction and mood\n- **Final audio mix**: balance voice, music, and SFX levels\n- **Export**: platform-specific formats and quality settings\n\nThis is where taste lives. AI clears the repetitive work. You make the final calls.\n\n## Social Media Reframing\n\nDifferent platforms need different aspect ratios:\n\n| Platform | Aspect Ratio | Resolution |\n|----------|-------------|------------|\n| YouTube | 16:9 | 1920x1080 |\n| TikTok \u002F Reels | 9:16 | 1080x1920 |\n| Instagram Feed | 1:1 | 1080x1080 |\n| X \u002F Twitter | 16:9 or 1:1 | 1280x720 or 720x720 |\n\n### Reframe with FFmpeg\n\n```bash\n# 16:9 to 9:16 (center crop)\nffmpeg -i input.mp4 -vf \"crop=ih*9\u002F16:ih,scale=1080:1920\" vertical.mp4\n\n# 16:9 to 1:1 (center crop)\nffmpeg -i input.mp4 -vf \"crop=ih:ih,scale=1080:1080\" square.mp4\n```\n\n### Reframe with VideoDB\n\n```python\n# Smart reframe (AI-guided subject tracking)\nreframed = video.reframe(start=0, end=60, target=\"vertical\", mode=ReframeMode.smart)\n```\n\n## Scene Detection and Auto-Cut\n\n### FFmpeg scene detection\n\n```bash\n# Detect scene changes (threshold 0.3 = moderate sensitivity)\nffmpeg -i input.mp4 -vf \"select='gt(scene,0.3)',showinfo\" -vsync vfr -f null - 2>&1 | grep showinfo\n```\n\n### Silence detection for auto-cut\n\n```bash\n# Find silent segments (useful for cutting dead air)\nffmpeg -i input.mp4 -af silencedetect=noise=-30dB:d=2 -f null - 2>&1 | grep silence\n```\n\n### Highlight extraction\n\nUse Claude to analyze transcript + scene timestamps:\n```\n\"Given this transcript with timestamps and these scene change points,\nidentify the 5 most engaging 30-second clips for social media.\"\n```\n\n## What Each Tool Does Best\n\n| Tool | Strength | Weakness |\n|------|----------|----------|\n| Claude \u002F Codex | Organization, planning, code generation | Not the creative taste layer |\n| FFmpeg | Deterministic cuts, batch processing, format conversion | No visual editing UI |\n| Remotion | Programmable overlays, composable scenes, reusable templates | Learning curve for non-devs |\n| Screen Studio | Polished screen recordings immediately | Only screen capture |\n| ElevenLabs | Voice, narration, music, SFX | Not the center of the workflow |\n| Descript \u002F CapCut | Final pacing, captions, polish | Manual, not automatable |\n\n## Key Principles\n\n1. **Edit, don't generate.** This workflow is for cutting real footage, not creating from prompts.\n2. **Structure before style.** Get the story right in Layer 2 before touching anything visual.\n3. **FFmpeg is the backbone.** Boring but critical. Where long footage becomes manageable.\n4. **Remotion for repeatability.** If you'll do it more than once, make it a Remotion component.\n5. **Generate selectively.** Only use AI generation for assets that don't exist, not for everything.\n6. **Taste is the last layer.** AI clears repetitive work. You make the final creative calls.\n\n## Related Skills\n\n- `fal-ai-media` — AI image, video, and audio generation\n- `videodb` — Server-side video processing, indexing, and streaming\n- `content-engine` — Platform-native content distribution\n","# Video Editing\n\nAI-assisted editing for real footage. Not generation from prompts. Editing existing video fast.\n\n## When to Activate\n\n- User wants to edit, cut, or structure video footage\n- Turning long recordings into short-form content\n- Building vlogs, tutorials, or demo videos from raw capture\n- Adding overlays, subtitles, music, or voiceover to existing video\n- Reframing video for different platforms (YouTube, TikTok, Instagram)\n- User says \"edit video\", \"cut this footage\", \"make a vlog\", or \"video workflow\"\n\n## Core Thesis\n\nAI video editing is useful when you stop asking it to create the whole video and start using it to compress, structure, and augment real footage. The value is not generation. The value is compression.\n\n## The Pipeline\n\n```\nScreen Studio \u002F raw footage\n  → Claude \u002F Codex\n  → FFmpeg\n  → Remotion\n  → ElevenLabs \u002F fal.ai\n  → Descript or CapCut\n```\n\nEach layer has a specific job. Do not skip layers. Do not try to make one tool do everything.\n\n## Layer 1: Capture (Screen Studio \u002F Raw Footage)\n\nCollect the source material:\n- **Screen Studio**: polished screen recordings for app demos, coding sessions, browser workflows\n- **Raw camera footage**: vlog footage, interviews, event recordings\n- **Desktop capture via VideoDB**: session recording with real-time context (see `videodb` skill)\n\nOutput: raw files ready for organization.\n\n## Layer 2: Organization (Claude \u002F Codex)\n\nUse Claude Code or Codex to:\n- **Transcribe and label**: generate transcript, identify topics and themes\n- **Plan structure**: decide what stays, what gets cut, what order works\n- **Identify dead sections**: find pauses, tangents, repeated takes\n- **Generate edit decision list**: timestamps for cuts, segments to keep\n- **Scaffold FFmpeg and Remotion code**: generate the commands and compositions\n\n```\nExample prompt:\n\"Here's the transcript of a 4-hour recording. Identify the 8 strongest segments\nfor a 24-minute vlog. Give me FFmpeg cut commands for each segment.\"\n```\n\nThis layer is about structure, not final creative taste.\n\n## Layer 3: Deterministic Cuts (FFmpeg)\n\nFFmpeg handles the boring but critical work: splitting, trimming, concatenating, and preprocessing.\n\n### Extract segment by timestamp\n\n```bash\nffmpeg -i raw.mp4 -ss 00:12:30 -to 00:15:45 -c copy segment_01.mp4\n```\n\n### Batch cut from edit decision list\n\n```bash\n#!\u002Fbin\u002Fbash\n# cuts.txt: start,end,label\nwhile IFS=, read -r start end label; do\n  ffmpeg -i raw.mp4 -ss \"$start\" -to \"$end\" -c copy \"segments\u002F${label}.mp4\"\ndone \u003C cuts.txt\n```\n\n### Concatenate segments\n\n```bash\n# Create file list\nfor f in segments\u002F*.mp4; do echo \"file '$f'\"; done > concat.txt\nffmpeg -f concat -safe 0 -i concat.txt -c copy assembled.mp4\n```\n\n### Create proxy for faster editing\n\n```bash\nffmpeg -i raw.mp4 -vf \"scale=960:-2\" -c:v libx264 -preset ultrafast -crf 28 proxy.mp4\n```\n\n### Extract audio for transcription\n\n```bash\nffmpeg -i raw.mp4 -vn -acodec pcm_s16le -ar 16000 audio.wav\n```\n\n### Normalize audio levels\n\n```bash\nffmpeg -i segment.mp4 -af loudnorm=I=-16:TP=-1.5:LRA=11 -c:v copy normalized.mp4\n```\n\n## Layer 4: Programmable Composition (Remotion)\n\nRemotion turns editing problems into composable code. Use it for things that traditional editors make painful:\n\n### When to use Remotion\n\n- Overlays: text, images, branding, lower thirds\n- Data visualizations: charts, stats, animated numbers\n- Motion graphics: transitions, explainer animations\n- Composable scenes: reusable templates across videos\n- Product demos: annotated screenshots, UI highlights\n\n### Basic Remotion composition\n\n```tsx\nimport { AbsoluteFill, Sequence, Video, useCurrentFrame } from \"remotion\";\n\nexport const VlogComposition: React.FC = () => {\n  const frame = useCurrentFrame();\n\n  return (\n    \u003CAbsoluteFill>\n      {\u002F* Main footage *\u002F}\n      \u003CSequence from={0} durationInFrames={300}>\n        \u003CVideo src=\"\u002Fsegments\u002Fintro.mp4\" \u002F>\n      \u003C\u002FSequence>\n\n      {\u002F* Title overlay *\u002F}\n      \u003CSequence from={30} durationInFrames={90}>\n        \u003CAbsoluteFill style={{\n          justifyContent: \"center\",\n          alignItems: \"center\",\n        }}>\n          \u003Ch1 style={{\n            fontSize: 72,\n            color: \"white\",\n            textShadow: \"2px 2px 8px rgba(0,0,0,0.8)\",\n          }}>\n            The AI Editing Stack\n          \u003C\u002Fh1>\n        \u003C\u002FAbsoluteFill>\n      \u003C\u002FSequence>\n\n      {\u002F* Next segment *\u002F}\n      \u003CSequence from={300} durationInFrames={450}>\n        \u003CVideo src=\"\u002Fsegments\u002Fdemo.mp4\" \u002F>\n      \u003C\u002FSequence>\n    \u003C\u002FAbsoluteFill>\n  );\n};\n```\n\n### Render output\n\n```bash\nnpx remotion render src\u002Findex.ts VlogComposition output.mp4\n```\n\nSee the [Remotion docs](https:\u002F\u002Fwww.remotion.dev\u002Fdocs) for detailed patterns and API reference.\n\n## Layer 5: Generated Assets (ElevenLabs \u002F fal.ai)\n\nGenerate only what you need. Do not generate the whole video.\n\n### Voiceover with ElevenLabs\n\n```python\nimport os\nimport requests\n\nresp = requests.post(\n    f\"https:\u002F\u002Fapi.elevenlabs.io\u002Fv1\u002Ftext-to-speech\u002F{voice_id}\",\n    headers={\n        \"xi-api-key\": os.environ[\"ELEVENLABS_API_KEY\"],\n        \"Content-Type\": \"application\u002Fjson\"\n    },\n    json={\n        \"text\": \"Your narration text here\",\n        \"model_id\": \"eleven_turbo_v2_5\",\n        \"voice_settings\": {\"stability\": 0.5, \"similarity_boost\": 0.75}\n    }\n)\nwith open(\"voiceover.mp3\", \"wb\") as f:\n    f.write(resp.content)\n```\n\n### Music and SFX with fal.ai\n\nUse the `fal-ai-media` skill for:\n- Background music generation\n- Sound effects (ThinkSound model for video-to-audio)\n- Transition sounds\n\n### Generated visuals with fal.ai\n\nUse for insert shots, thumbnails, or b-roll that doesn't exist:\n```\ngenerate(model_name: \"fal-ai\u002Fnano-banana-pro\", input: {\n  \"prompt\": \"professional thumbnail for tech vlog, dark background, code on screen\",\n  \"image_size\": \"landscape_16_9\"\n})\n```\n\n### VideoDB generative audio\n\nIf VideoDB is configured:\n```python\nvoiceover = coll.generate_voice(text=\"Narration here\", voice=\"alloy\")\nmusic = coll.generate_music(prompt=\"lo-fi background for coding vlog\", duration=120)\nsfx = coll.generate_sound_effect(prompt=\"subtle whoosh transition\")\n```\n\n## Layer 6: Final Polish (Descript \u002F CapCut)\n\nThe last layer is human. Use a traditional editor for:\n- **Pacing**: adjust cuts that feel too fast or slow\n- **Captions**: auto-generated, then manually cleaned\n- **Color grading**: basic correction and mood\n- **Final audio mix**: balance voice, music, and SFX levels\n- **Export**: platform-specific formats and quality settings\n\nThis is where taste lives. AI clears the repetitive work. You make the final calls.\n\n## Social Media Reframing\n\nDifferent platforms need different aspect ratios:\n\n| Platform | Aspect Ratio | Resolution |\n|----------|-------------|------------|\n| YouTube | 16:9 | 1920x1080 |\n| TikTok \u002F Reels | 9:16 | 1080x1920 |\n| Instagram Feed | 1:1 | 1080x1080 |\n| X \u002F Twitter | 16:9 or 1:1 | 1280x720 or 720x720 |\n\n### Reframe with FFmpeg\n\n```bash\n# 16:9 to 9:16 (center crop)\nffmpeg -i input.mp4 -vf \"crop=ih*9\u002F16:ih,scale=1080:1920\" vertical.mp4\n\n# 16:9 to 1:1 (center crop)\nffmpeg -i input.mp4 -vf \"crop=ih:ih,scale=1080:1080\" square.mp4\n```\n\n### Reframe with VideoDB\n\n```python\n# Smart reframe (AI-guided subject tracking)\nreframed = video.reframe(start=0, end=60, target=\"vertical\", mode=ReframeMode.smart)\n```\n\n## Scene Detection and Auto-Cut\n\n### FFmpeg scene detection\n\n```bash\n# Detect scene changes (threshold 0.3 = moderate sensitivity)\nffmpeg -i input.mp4 -vf \"select='gt(scene,0.3)',showinfo\" -vsync vfr -f null - 2>&1 | grep showinfo\n```\n\n### Silence detection for auto-cut\n\n```bash\n# Find silent segments (useful for cutting dead air)\nffmpeg -i input.mp4 -af silencedetect=noise=-30dB:d=2 -f null - 2>&1 | grep silence\n```\n\n### Highlight extraction\n\nUse Claude to analyze transcript + scene timestamps:\n```\n\"Given this transcript with timestamps and these scene change points,\nidentify the 5 most engaging 30-second clips for social media.\"\n```\n\n## What Each Tool Does Best\n\n| Tool | Strength | Weakness |\n|------|----------|----------|\n| Claude \u002F Codex | Organization, planning, code generation | Not the creative taste layer |\n| FFmpeg | Deterministic cuts, batch processing, format conversion | No visual editing UI |\n| Remotion | Programmable overlays, composable scenes, reusable templates | Learning curve for non-devs |\n| Screen Studio | Polished screen recordings immediately | Only screen capture |\n| ElevenLabs | Voice, narration, music, SFX | Not the center of the workflow |\n| Descript \u002F CapCut | Final pacing, captions, polish | Manual, not automatable |\n\n## Key Principles\n\n1. **Edit, don't generate.** This workflow is for cutting real footage, not creating from prompts.\n2. **Structure before style.** Get the story right in Layer 2 before touching anything visual.\n3. **FFmpeg is the backbone.** Boring but critical. Where long footage becomes manageable.\n4. **Remotion for repeatability.** If you'll do it more than once, make it a Remotion component.\n5. **Generate selectively.** Only use AI generation for assets that don't exist, not for everything.\n6. **Taste is the last layer.** AI clears repetitive work. You make the final creative calls.\n\n## Related Skills\n\n- `fal-ai-media` — AI image, video, and audio generation\n- `videodb` — Server-side video processing, indexing, and streaming\n- `content-engine` — Platform-native content distribution\n",{"name":5,"description":7},"main","2a76bf42ce5c860adf8d0f3fcf3f6804109ac65b","skills\u002Fvideo-editing",0,"https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library","https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fwiki","https:\u002F\u002Fgithub.com\u002Fonfire7777","trying to create something actually useful","2026-09-11 13:25:26",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add onfire7777\u002Funiversal-ai-skills-library --skill video-editing",{"tool":67,"command":68},"bunx","bunx skills add onfire7777\u002Funiversal-ai-skills-library --skill video-editing",{"tool":70,"command":71},"pnpm","pnpm dlx skills add onfire7777\u002Funiversal-ai-skills-library --skill video-editing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002FSKILL.md",true,[75],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"agents\u002Fopenai.yaml","REFERENCE","参考文档",255,"https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-editing\u002Fagents\u002Fopenai.yaml",[82,109,118,128,148,164],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":97,"publishedAt":47},"01M6J7MPK8ZE9VQJR4KK6ZMZJQ","zyte-api-automation","Automate Zyte API tasks via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fblob\u002Fmain\u002Fskills\u002Fzyte-api-automation\u002FSKILL.md",[88,91,92],{"categoryNo":89,"categoryName":90,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[98,99,100,32,101,102,103,104,105,106,107,108],"automation","api","zyte api automation","MCP","via","composio","automate","first","Tools","search","tasks",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":116,"publishedAt":47},"01M6J7MK45K2ZZ0EWTP1N6SZ7F","zylvie-automation","Automate Zylvie tasks via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fblob\u002Fmain\u002Fskills\u002Fzylvie-automation\u002FSKILL.md",[115],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[98,117,101,108,32,102,103,104,105,106,107],"zylvie automation",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":125,"publishedAt":47},"01M6J7MGDCVZ3YCXGEAPR5V3MS","zoominfo-automation","Automate Zoominfo tasks via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fblob\u002Fmain\u002Fskills\u002Fzoominfo-automation\u002FSKILL.md",[124],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[126,127,98,104,103,106,102,108,32,107,101,105],"zoominfo","zoominfo automation",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":135,"publishedAt":47},"01M6J7MDK48N09B7C6H9TCPY9A","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[134],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[136,137,138,139,140,141,142,143,144,39,145,146,147],"zoom out","zoom","perspective","code","re","you","with","understand","it","context","how","true",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":47},"01M6J7MAD47Q9A55AK3EXS914H","zoho-mail-automation","Automate Zoho Mail tasks via Rube MCP (Composio): email sending, folders, labels, and mailbox management. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fblob\u002Fmain\u002Fskills\u002Fzoho-mail-automation\u002FSKILL.md",[154],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[156,157,158,159,98,160,107,108,101,106,161,32,102,162,103,163,104,105],"mail","zoho mail automation","zoho","zoho mail","email","labels","mailbox","management",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":174,"publishedAt":47},"01M6J7M76HTWPP8TRWWCDS42NB","zoho-invoice-automation","Automate Zoho Invoice tasks via Rube MCP (Composio): invoices, estimates, expenses, clients, and payment tracking. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fonfire7777\u002Funiversal-ai-skills-library\u002Fblob\u002Fmain\u002Fskills\u002Fzoho-invoice-automation\u002FSKILL.md",[170,171],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":172,"categoryName":173,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000040","财务",[175,98,158,176,101,102,32,177,178,179,103,180,181,104,105,106,107,108],"invoice","zoho invoice automation","invoices","expenses","clients","payment","tracking"]