@autoaiai/aicut 0.1.11 → 0.1.13
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/MANUAL.md +94 -94
- package/package.json +1 -1
- package/skills/aicut-motion/SKILL.md +69 -3
- package/skills/aicut-motion/THIRD_PARTY_NOTICES.md +14 -0
- package/skills/aicut-motion/assets/atlas/lib/harness.js +116 -0
- package/skills/aicut-motion/assets/atlas/lib/sound.js +274 -0
- package/skills/aicut-motion/assets/atlas/styles/001-flat-vector-science/code.js +937 -0
- package/skills/aicut-motion/assets/atlas/styles/001-flat-vector-science/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/001-flat-vector-science/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/002-watercolor-wash/code.js +909 -0
- package/skills/aicut-motion/assets/atlas/styles/002-watercolor-wash/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/002-watercolor-wash/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/003-shadow-puppet-theatre/code.js +881 -0
- package/skills/aicut-motion/assets/atlas/styles/003-shadow-puppet-theatre/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/003-shadow-puppet-theatre/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/004-whiteboard-explainer/code.js +897 -0
- package/skills/aicut-motion/assets/atlas/styles/004-whiteboard-explainer/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/004-whiteboard-explainer/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/005-psychedelic-poster/code.js +814 -0
- package/skills/aicut-motion/assets/atlas/styles/005-psychedelic-poster/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/005-psychedelic-poster/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/006-tech-glow-explainer/code.js +990 -0
- package/skills/aicut-motion/assets/atlas/styles/006-tech-glow-explainer/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/006-tech-glow-explainer/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/007-papercraft-models/code.js +994 -0
- package/skills/aicut-motion/assets/atlas/styles/007-papercraft-models/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/007-papercraft-models/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/008-1940s-film-noir/code.js +792 -0
- package/skills/aicut-motion/assets/atlas/styles/008-1940s-film-noir/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/008-1940s-film-noir/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/009-manim-style-math/code.js +840 -0
- package/skills/aicut-motion/assets/atlas/styles/009-manim-style-math/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/009-manim-style-math/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/010-illuminated-manuscript/code.js +1126 -0
- package/skills/aicut-motion/assets/atlas/styles/010-illuminated-manuscript/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/010-illuminated-manuscript/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/011-editorial-essay-collage/code.js +854 -0
- package/skills/aicut-motion/assets/atlas/styles/011-editorial-essay-collage/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/011-editorial-essay-collage/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/012-bioluminescent-deep-sea/code.js +1124 -0
- package/skills/aicut-motion/assets/atlas/styles/012-bioluminescent-deep-sea/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/012-bioluminescent-deep-sea/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/013-product-launch-reveal/code.js +728 -0
- package/skills/aicut-motion/assets/atlas/styles/013-product-launch-reveal/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/013-product-launch-reveal/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/014-halftone-pop-panel/code.js +664 -0
- package/skills/aicut-motion/assets/atlas/styles/014-halftone-pop-panel/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/014-halftone-pop-panel/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/015-isometric-pastel/code.js +991 -0
- package/skills/aicut-motion/assets/atlas/styles/015-isometric-pastel/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/015-isometric-pastel/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/016-oscilloscope-vector-art/code.js +801 -0
- package/skills/aicut-motion/assets/atlas/styles/016-oscilloscope-vector-art/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/016-oscilloscope-vector-art/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/017-risograph-zine/code.js +692 -0
- package/skills/aicut-motion/assets/atlas/styles/017-risograph-zine/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/017-risograph-zine/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/018-claymation-set/code.js +756 -0
- package/skills/aicut-motion/assets/atlas/styles/018-claymation-set/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/018-claymation-set/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/019-neon-sign-at-night/code.js +922 -0
- package/skills/aicut-motion/assets/atlas/styles/019-neon-sign-at-night/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/019-neon-sign-at-night/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/020-kawaii-anime/code.js +852 -0
- package/skills/aicut-motion/assets/atlas/styles/020-kawaii-anime/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/020-kawaii-anime/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/021-ukiyo-e-woodblock/code.js +724 -0
- package/skills/aicut-motion/assets/atlas/styles/021-ukiyo-e-woodblock/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/021-ukiyo-e-woodblock/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/022-16-bit-pixel-odyssey/code.js +793 -0
- package/skills/aicut-motion/assets/atlas/styles/022-16-bit-pixel-odyssey/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/022-16-bit-pixel-odyssey/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/023-chalkboard-lesson/code.js +846 -0
- package/skills/aicut-motion/assets/atlas/styles/023-chalkboard-lesson/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/023-chalkboard-lesson/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/024-cut-paper-diorama/code.js +1008 -0
- package/skills/aicut-motion/assets/atlas/styles/024-cut-paper-diorama/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/024-cut-paper-diorama/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/025-cathedral-glass/code.js +680 -0
- package/skills/aicut-motion/assets/atlas/styles/025-cathedral-glass/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/025-cathedral-glass/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/026-editorial-chart/code.js +633 -0
- package/skills/aicut-motion/assets/atlas/styles/026-editorial-chart/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/026-editorial-chart/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/027-synthwave-outrun/code.js +757 -0
- package/skills/aicut-motion/assets/atlas/styles/027-synthwave-outrun/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/027-synthwave-outrun/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/028-origami-studio/code.js +828 -0
- package/skills/aicut-motion/assets/atlas/styles/028-origami-studio/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/028-origami-studio/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/029-linocut-relief-print/code.js +697 -0
- package/skills/aicut-motion/assets/atlas/styles/029-linocut-relief-print/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/029-linocut-relief-print/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/030-holographic-foil-card/code.js +687 -0
- package/skills/aicut-motion/assets/atlas/styles/030-holographic-foil-card/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/030-holographic-foil-card/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/031-voxel-diorama/code.js +727 -0
- package/skills/aicut-motion/assets/atlas/styles/031-voxel-diorama/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/031-voxel-diorama/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/032-sumi-e-ink-wash/code.js +903 -0
- package/skills/aicut-motion/assets/atlas/styles/032-sumi-e-ink-wash/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/032-sumi-e-ink-wash/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/033-etch-a-sketch-toy/code.js +662 -0
- package/skills/aicut-motion/assets/atlas/styles/033-etch-a-sketch-toy/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/033-etch-a-sketch-toy/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/034-cosmic-star-chart/code.js +951 -0
- package/skills/aicut-motion/assets/atlas/styles/034-cosmic-star-chart/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/034-cosmic-star-chart/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/035-punk-zine-collage/code.js +759 -0
- package/skills/aicut-motion/assets/atlas/styles/035-punk-zine-collage/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/035-punk-zine-collage/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/036-thermal-camera/code.js +738 -0
- package/skills/aicut-motion/assets/atlas/styles/036-thermal-camera/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/036-thermal-camera/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/037-engineering-blueprint/code.js +793 -0
- package/skills/aicut-motion/assets/atlas/styles/037-engineering-blueprint/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/037-engineering-blueprint/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/038-impasto-night/code.js +673 -0
- package/skills/aicut-motion/assets/atlas/styles/038-impasto-night/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/038-impasto-night/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/039-win95-desktop/code.js +907 -0
- package/skills/aicut-motion/assets/atlas/styles/039-win95-desktop/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/039-win95-desktop/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/040-low-poly-faceted/code.js +833 -0
- package/skills/aicut-motion/assets/atlas/styles/040-low-poly-faceted/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/040-low-poly-faceted/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/041-manga-page/code.js +845 -0
- package/skills/aicut-motion/assets/atlas/styles/041-manga-page/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/041-manga-page/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/042-wood-type-letterpress/code.js +496 -0
- package/skills/aicut-motion/assets/atlas/styles/042-wood-type-letterpress/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/042-wood-type-letterpress/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/043-light-painting/code.js +635 -0
- package/skills/aicut-motion/assets/atlas/styles/043-light-painting/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/043-light-painting/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/044-felt-patchwork/code.js +799 -0
- package/skills/aicut-motion/assets/atlas/styles/044-felt-patchwork/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/044-felt-patchwork/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/045-phosphor-terminal/code.js +547 -0
- package/skills/aicut-motion/assets/atlas/styles/045-phosphor-terminal/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/045-phosphor-terminal/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/046-glassmorphism-ui/code.js +592 -0
- package/skills/aicut-motion/assets/atlas/styles/046-glassmorphism-ui/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/046-glassmorphism-ui/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/047-tarot-card/code.js +768 -0
- package/skills/aicut-motion/assets/atlas/styles/047-tarot-card/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/047-tarot-card/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/048-transit-map/code.js +666 -0
- package/skills/aicut-motion/assets/atlas/styles/048-transit-map/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/048-transit-map/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/049-gouache-travel-poster/code.js +559 -0
- package/skills/aicut-motion/assets/atlas/styles/049-gouache-travel-poster/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/049-gouache-travel-poster/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/050-napkin-sketch/code.js +943 -0
- package/skills/aicut-motion/assets/atlas/styles/050-napkin-sketch/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/050-napkin-sketch/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/051-art-deco-foil/code.js +606 -0
- package/skills/aicut-motion/assets/atlas/styles/051-art-deco-foil/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/051-art-deco-foil/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/052-radiograph-on-lightbox/code.js +730 -0
- package/skills/aicut-motion/assets/atlas/styles/052-radiograph-on-lightbox/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/052-radiograph-on-lightbox/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/053-vaporwave/code.js +782 -0
- package/skills/aicut-motion/assets/atlas/styles/053-vaporwave/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/053-vaporwave/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/054-ebru-paper-marbling/code.js +504 -0
- package/skills/aicut-motion/assets/atlas/styles/054-ebru-paper-marbling/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/054-ebru-paper-marbling/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/055-isotype-pictograms/code.js +517 -0
- package/skills/aicut-motion/assets/atlas/styles/055-isotype-pictograms/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/055-isotype-pictograms/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/056-soft-3d-clay/code.js +713 -0
- package/skills/aicut-motion/assets/atlas/styles/056-soft-3d-clay/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/056-soft-3d-clay/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/057-cross-stitch-sampler/code.js +717 -0
- package/skills/aicut-motion/assets/atlas/styles/057-cross-stitch-sampler/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/057-cross-stitch-sampler/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/058-constructivist-propaganda/code.js +540 -0
- package/skills/aicut-motion/assets/atlas/styles/058-constructivist-propaganda/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/058-constructivist-propaganda/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/059-pocket-monochrome/code.js +524 -0
- package/skills/aicut-motion/assets/atlas/styles/059-pocket-monochrome/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/059-pocket-monochrome/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/060-botanical-plate/code.js +934 -0
- package/skills/aicut-motion/assets/atlas/styles/060-botanical-plate/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/060-botanical-plate/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/061-kinetic-type/code.js +690 -0
- package/skills/aicut-motion/assets/atlas/styles/061-kinetic-type/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/061-kinetic-type/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/062-byzantine-mosaic/code.js +612 -0
- package/skills/aicut-motion/assets/atlas/styles/062-byzantine-mosaic/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/062-byzantine-mosaic/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/063-y2k-liquid-chrome/code.js +666 -0
- package/skills/aicut-motion/assets/atlas/styles/063-y2k-liquid-chrome/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/063-y2k-liquid-chrome/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/064-sticky-note-wall/code.js +651 -0
- package/skills/aicut-motion/assets/atlas/styles/064-sticky-note-wall/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/064-sticky-note-wall/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/065-vintage-newsprint/code.js +656 -0
- package/skills/aicut-motion/assets/atlas/styles/065-vintage-newsprint/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/065-vintage-newsprint/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/066-hidden-line-wireframe/code.js +672 -0
- package/skills/aicut-motion/assets/atlas/styles/066-hidden-line-wireframe/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/066-hidden-line-wireframe/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/067-memphis-group/code.js +548 -0
- package/skills/aicut-motion/assets/atlas/styles/067-memphis-group/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/067-memphis-group/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/068-ballpoint-notebook/code.js +989 -0
- package/skills/aicut-motion/assets/atlas/styles/068-ballpoint-notebook/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/068-ballpoint-notebook/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/069-op-art-sphere/code.js +440 -0
- package/skills/aicut-motion/assets/atlas/styles/069-op-art-sphere/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/069-op-art-sphere/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/070-topographic-survey/code.js +895 -0
- package/skills/aicut-motion/assets/atlas/styles/070-topographic-survey/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/070-topographic-survey/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/071-pointillist-afternoon/code.js +563 -0
- package/skills/aicut-motion/assets/atlas/styles/071-pointillist-afternoon/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/071-pointillist-afternoon/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/072-vector-arcade-1980/code.js +627 -0
- package/skills/aicut-motion/assets/atlas/styles/072-vector-arcade-1980/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/072-vector-arcade-1980/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/073-patent-drawing/code.js +1096 -0
- package/skills/aicut-motion/assets/atlas/styles/073-patent-drawing/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/073-patent-drawing/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/074-bauhaus-poster/code.js +595 -0
- package/skills/aicut-motion/assets/atlas/styles/074-bauhaus-poster/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/074-bauhaus-poster/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/075-bitmap-paint-doodle/code.js +665 -0
- package/skills/aicut-motion/assets/atlas/styles/075-bitmap-paint-doodle/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/075-bitmap-paint-doodle/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/076-nail-thread-string-art/code.js +645 -0
- package/skills/aicut-motion/assets/atlas/styles/076-nail-thread-string-art/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/076-nail-thread-string-art/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/077-ridgeline/code.js +436 -0
- package/skills/aicut-motion/assets/atlas/styles/077-ridgeline/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/077-ridgeline/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/078-sketchbook-graphite/code.js +1237 -0
- package/skills/aicut-motion/assets/atlas/styles/078-sketchbook-graphite/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/078-sketchbook-graphite/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/079-teletext-page/code.js +622 -0
- package/skills/aicut-motion/assets/atlas/styles/079-teletext-page/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/079-teletext-page/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/080-silkscreen-grid/code.js +524 -0
- package/skills/aicut-motion/assets/atlas/styles/080-silkscreen-grid/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/080-silkscreen-grid/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/081-guilloch-security-print/code.js +689 -0
- package/skills/aicut-motion/assets/atlas/styles/081-guilloch-security-print/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/081-guilloch-security-print/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/082-ascii-demoscene/code.js +574 -0
- package/skills/aicut-motion/assets/atlas/styles/082-ascii-demoscene/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/082-ascii-demoscene/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/083-international-typographic-style/code.js +469 -0
- package/skills/aicut-motion/assets/atlas/styles/083-international-typographic-style/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/083-international-typographic-style/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/084-flow-field/code.js +531 -0
- package/skills/aicut-motion/assets/atlas/styles/084-flow-field/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/084-flow-field/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/085-macpaint-1984/code.js +675 -0
- package/skills/aicut-motion/assets/atlas/styles/085-macpaint-1984/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/085-macpaint-1984/style.json +13 -0
- package/skills/aicut-motion/assets/atlas/styles/086-multi-scale-truchet/code.js +609 -0
- package/skills/aicut-motion/assets/atlas/styles/086-multi-scale-truchet/poster.jpg +0 -0
- package/skills/aicut-motion/assets/atlas/styles/086-multi-scale-truchet/style.json +13 -0
- package/skills/aicut-motion/references/motion-delivery.md +55 -0
- package/skills/aicut-motion/references/style-index.json +690 -0
- package/skills/aicut-motion/references/style-research.md +73 -0
- package/skills/aicut-motion/references/style-selection.md +71 -0
- package/skills/aicut-motion/scripts/atlas-viewer.html +195 -0
- package/skills/aicut-motion/scripts/atlas.mjs +109 -0
- package/studio/server/fetch-github.mjs +14 -3
- package/studio/server/server.mjs +40 -3
- package/studio/server/skill-summaries.mjs +60 -0
- package/studio/server/skills.mjs +121 -7
- package/studio/server/styles-store.mjs +235 -0
- package/studio/server/template-posters.mjs +2 -2
- package/studio/server/templates-page.mjs +93 -93
- package/studio/server/templates.mjs +32 -7
- package/studio/ui/dist/assets/ExportCenter-DasulhAv.js +1 -0
- package/studio/ui/dist/assets/SettingsModal-BZw0Hz2_.js +2 -0
- package/studio/ui/dist/assets/es-C8XPZARI.js +1 -0
- package/studio/ui/dist/assets/index-BjJVmBzB.js +1623 -0
- package/studio/ui/dist/assets/index-C3BfKZFO.css +1 -0
- package/studio/ui/dist/assets/ja-BeNkdaEj.js +1 -0
- package/studio/ui/dist/assets/ko-DcTVhdzK.js +1 -0
- package/studio/ui/dist/assets/zh-CN-Cg51ctbL.js +1 -0
- package/studio/ui/dist/index.html +2 -2
- package/skills/30x-web-to-video/SKILL.md +0 -421
- package/skills/30x-web-to-video/examples/INDEX.md +0 -26
- package/skills/30x-web-to-video/references/animations.md +0 -539
- package/skills/30x-web-to-video/references/audio.md +0 -256
- package/skills/30x-web-to-video/references/components.md +0 -340
- package/skills/30x-web-to-video/references/lottie.md +0 -174
- package/skills/30x-web-to-video/references/visual-effects.md +0 -157
- package/skills/30x-web-to-video/remotion-best-practices/rules/audio.md +0 -169
- package/skills/30x-web-to-video/remotion-best-practices/rules/calculate-metadata.md +0 -134
- package/skills/30x-web-to-video/remotion-best-practices/rules/charts.md +0 -120
- package/skills/30x-web-to-video/remotion-best-practices/rules/compositions.md +0 -154
- package/skills/30x-web-to-video/remotion-best-practices/rules/ffmpeg.md +0 -38
- package/skills/30x-web-to-video/remotion-best-practices/rules/fonts.md +0 -152
- package/skills/3d-asset-generation/SKILL.md +0 -142
- package/skills/action-fight-prompt/SKILL.md +0 -136
- package/skills/action-fight-prompt/references/camera-and-impact.md +0 -64
- package/skills/action-fight-prompt/references/example-15s-duel.md +0 -59
- package/skills/action-fight-prompt/references/scene-patterns.md +0 -80
- package/skills/ad-creative-video/SKILL.md +0 -205
- package/skills/ad-creative-video/references/batch-ad-pipeline.md +0 -289
- package/skills/ad-creative-video/references/platform-specs.md +0 -72
- package/skills/after-effects/SKILL.md +0 -123
- package/skills/after-effects/references/export-recipes.md +0 -168
- package/skills/after-effects/references/expression-library.md +0 -184
- package/skills/after-effects/references/expressions.md +0 -134
- package/skills/after-effects/references/performance-triage.md +0 -138
- package/skills/after-effects/references/project-hygiene.md +0 -188
- package/skills/ai-media-quality-review/SKILL.md +0 -72
- package/skills/ai-product-video/SKILL.md +0 -296
- package/skills/ai-product-video/references/aesthetic-rules.md +0 -177
- package/skills/ai-product-video/references/final-review.md +0 -110
- package/skills/ai-product-video/references/guided-free-creation.md +0 -194
- package/skills/ai-product-video/references/music-beat-sync.md +0 -219
- package/skills/ai-product-video/references/pipeline.md +0 -392
- package/skills/ai-product-video/references/sequences/promo-energy-arc.md +0 -50
- package/skills/ai-product-video/references/shots/ATTRIBUTION.md +0 -65
- package/skills/ai-product-video/references/shots/camera/basic-3d-scene.md +0 -37
- package/skills/ai-product-video/references/shots/camera/crash-zoom-punch.md +0 -39
- package/skills/ai-product-video/references/shots/camera/cursor-flyover.md +0 -38
- package/skills/ai-product-video/references/shots/camera/depth-layer-moves.md +0 -40
- package/skills/ai-product-video/references/shots/camera/graze-face-tour.md +0 -57
- package/skills/anidoodle/SKILL.md +0 -185
- package/skills/anidoodle/references/anatomy.md +0 -91
- package/skills/anidoodle/references/backends-and-adapters.md +0 -82
- package/skills/anidoodle/references/camera.md +0 -148
- package/skills/anidoodle/references/craft-bar.md +0 -72
- package/skills/anidoodle/references/determinism-and-contract.md +0 -46
- package/skills/anidoodle/references/formats.md +0 -121
- package/skills/anidoodle/references/motion-grammar.md +0 -234
- package/skills/anidoodle/references/music/compose.md +0 -388
- package/skills/anidoodle/references/music/sound-design.md +0 -245
- package/skills/anidoodle/references/music/sounds-licenses.md +0 -69
- package/skills/anidoodle/references/music/styles/lofi-electronic.md +0 -112
- package/skills/anidoodle/references/music/styles/music-box.md +0 -57
- package/skills/animated-component-libraries/SKILL.md +0 -820
- package/skills/animated-component-libraries/references/customization_guide.md +0 -699
- package/skills/animated-component-libraries/references/magic_ui_components.md +0 -422
- package/skills/animated-component-libraries/references/react_bits_components.md +0 -587
- package/skills/animated-infographic/SKILL.md +0 -211
- package/skills/animated-infographic/references/sequenced-infographic.md +0 -286
- package/skills/appshot-core/SKILL.md +0 -872
- package/skills/article-highlights/SKILL.md +0 -151
- package/skills/avatar-mix/SKILL.md +0 -301
- package/skills/bang-motion/SKILL.md +0 -583
- package/skills/bang-motion/references/ae-bridge-higgsfield.md +0 -160
- package/skills/bang-motion/references/anti-ppt.md +0 -110
- package/skills/bang-motion/references/architecture.md +0 -188
- package/skills/bang-motion/references/explainer.md +0 -579
- package/skills/bang-motion/references/kartun-panggung.md +0 -221
- package/skills/bang-motion/references/opener-konsep.md +0 -817
- package/skills/bang-motion/references/roadmap.md +0 -85
- package/skills/bang-motion/references/techniques.md +0 -690
- package/skills/beat-sync-edit/SKILL.md +0 -148
- package/skills/book-video-factory/SKILL.md +0 -139
- package/skills/book-video-factory/references/first-run.md +0 -50
- package/skills/book-video-factory/references/paper-collage-explainer.md +0 -127
- package/skills/book-video-factory/references/quality-gates.md +0 -87
- package/skills/book-video-production/SKILL.md +0 -211
- package/skills/brag/SKILL.md +0 -195
- package/skills/brag/references/audio.md +0 -312
- package/skills/brag/references/step-1-inspect.md +0 -125
- package/skills/brag/references/step-2-plan.md +0 -234
- package/skills/brag/references/step-3-compose.md +0 -199
- package/skills/brag/references/step-4-deliver.md +0 -141
- package/skills/brag/references/tones.md +0 -231
- package/skills/brand-setup/SKILL.md +0 -228
- package/skills/brewreel/SKILL.md +0 -491
- package/skills/brewreel/docs/broll.en.md +0 -252
- package/skills/brewreel/docs/broll.md +0 -252
- package/skills/brewreel/docs/custom-shot.en.md +0 -66
- package/skills/brewreel/docs/custom-shot.md +0 -103
- package/skills/brewreel/docs/faq.en.md +0 -90
- package/skills/brewreel/docs/faq.md +0 -90
- package/skills/brewreel/docs/features.en.md +0 -157
- package/skills/brewreel/docs/features.md +0 -157
- package/skills/brewreel/docs/gallery.en.md +0 -44
- package/skills/brewreel/docs/gallery.md +0 -44
- package/skills/brewreel/docs/how-it-works.en.md +0 -64
- package/skills/brewreel/docs/how-it-works.md +0 -64
- package/skills/caption-animation/SKILL.md +0 -216
- package/skills/caption-animation/references/word-timed-captions.md +0 -254
- package/skills/cartcut-editing/SKILL.md +0 -615
- package/skills/cartcut-editing/references/html-typography.md +0 -277
- package/skills/cassette-video-edit/SKILL.md +0 -129
- package/skills/ccvideo/SKILL.md +0 -264
- package/skills/chekhov-dramaturgy/SKILL.md +0 -367
- package/skills/chekhov-dramaturgy/reference.md +0 -375
- package/skills/chengfeng-check-updates/SKILL.md +0 -283
- package/skills/cinematic-product-promo-skill/SKILL.md +0 -295
- package/skills/cinematic-product-promo-skill/references/aesthetic-rules.md +0 -187
- package/skills/cinematic-product-promo-skill/references/final-review.md +0 -116
- package/skills/cinematic-product-promo-skill/references/guided-free-creation.md +0 -199
- package/skills/cinematic-product-promo-skill/references/jianying-export.md +0 -183
- package/skills/cinematic-product-promo-skill/references/music-beat-sync.md +0 -257
- package/skills/cinematic-product-promo-skill/references/pipeline.md +0 -393
- package/skills/cinematic-product-promo-skill/references/sequences/promo-energy-arc.md +0 -50
- package/skills/cinematic-product-promo-skill/references/shots/ATTRIBUTION.md +0 -65
- package/skills/cinematic-product-promo-skill/references/shots/camera/basic-3d-scene.md +0 -37
- package/skills/cinematic-product-promo-skill/references/shots/camera/crash-zoom-punch.md +0 -39
- package/skills/cinematic-product-promo-skill/references/shots/camera/cursor-flyover.md +0 -38
- package/skills/cinematic-product-promo-skill/references/shots/camera/depth-layer-moves.md +0 -40
- package/skills/claude-gif/SKILL.md +0 -211
- package/skills/claude-gif/references/gif-optimization.md +0 -209
- package/skills/claude-gif/references/perfect-loops.md +0 -295
- package/skills/claude-gif/references/platform-specs.md +0 -138
- package/skills/claude-gif/references/prompt-engineering.md +0 -211
- package/skills/claude-gif/references/remotion-gif.md +0 -560
- package/skills/codex-video-pipeline/SKILL.md +0 -213
- package/skills/codex-video-pipeline/examples/ai-meeting-notes/INPUT.md +0 -10
- package/skills/codex-video-pipeline/examples/ai-meeting-notes/expected/action-list.md +0 -22
- package/skills/codex-video-pipeline/references/captions.md +0 -39
- package/skills/codex-video-pipeline/references/cover-system.md +0 -72
- package/skills/codex-video-pipeline/references/cross-platform.md +0 -77
- package/skills/codex-video-pipeline/references/example-run.md +0 -54
- package/skills/codex-video-pipeline/references/first-run.md +0 -130
- package/skills/codex-video-pipeline/references/project-contract.md +0 -54
- package/skills/codex-video-pipeline/references/quality-gates.md +0 -44
- package/skills/codex-video-pipeline/references/research-and-script.md +0 -50
- package/skills/collage-broll-explainers/SKILL.md +0 -429
- package/skills/create-onboarding-video/SKILL.md +0 -233
- package/skills/cs-shotcraft-skill/SKILL.md +0 -218
- package/skills/cs-shotcraft-skill/references/aesthetic-rules.md +0 -207
- package/skills/cs-shotcraft-skill/references/camera-table.md +0 -88
- package/skills/cs-shotcraft-skill/references/engineering.md +0 -132
- package/skills/cs-shotcraft-skill/references/final-review.md +0 -118
- package/skills/cs-shotcraft-skill/references/guided-free-creation.md +0 -199
- package/skills/cs-shotcraft-skill/references/jianying-export.md +0 -183
- package/skills/cs-shotcraft-skill/references/music-beat-sync.md +0 -257
- package/skills/cs-shotcraft-skill/references/pipeline.md +0 -408
- package/skills/cs-shotcraft-skill/references/product-machine.md +0 -56
- package/skills/cs-shotcraft-skill/references/sequences/promo-energy-arc.md +0 -50
- package/skills/cs-shotcraft-skill/references/shots/ATTRIBUTION.md +0 -65
- package/skills/cs-shotcraft-skill/references/shots/camera/basic-3d-scene.md +0 -37
- package/skills/cut-video/SKILL.md +0 -387
- package/skills/cyxj-hyperframes-overlay/SKILL.md +0 -75
- package/skills/cyxj-remotion-evolve/SKILL.md +0 -123
- package/skills/cyxj-remotion-evolve-vibe-motion/SKILL.md +0 -123
- package/skills/demo-video-creation-skill/SKILL.md +0 -152
- package/skills/demo-video-creation-skill/references/capture-workflow.md +0 -74
- package/skills/demo-video-creation-skill/references/qc-checklist.md +0 -61
- package/skills/demo-video-creation-skill/references/remotion-ffmpeg.md +0 -94
- package/skills/demo-video-creation-skill/references/storytelling.md +0 -86
- package/skills/demo-video-creation-skill/references/visual-system.md +0 -83
- package/skills/demoday/SKILL.md +0 -148
- package/skills/develop-premiere-pro-mcp/SKILL.md +0 -131
- package/skills/diagram-animation/SKILL.md +0 -200
- package/skills/diagram-animation/references/diagram-and-chart-recipes.md +0 -218
- package/skills/diagram-tour/SKILL.md +0 -287
- package/skills/diagram-tour/examples/agent-architecture/agent-architecture-tour.md +0 -78
- package/skills/docvideoer/SKILL.md +0 -139
- package/skills/draftcut/SKILL.md +0 -104
- package/skills/draftcut/docs/agent-bootstrap.md +0 -64
- package/skills/draftcut/docs/approvals.md +0 -45
- package/skills/draftcut/docs/audio-first-migration.md +0 -35
- package/skills/draftcut/docs/configuration.md +0 -54
- package/skills/draftcut/docs/getting-started.md +0 -63
- package/skills/draftcut/docs/harness-case-study.en.md +0 -23
- package/skills/draftcut/docs/harness-case-study.md +0 -47
- package/skills/draftcut/references/01-plan.md +0 -30
- package/skills/draftcut/references/03-deliver.md +0 -26
- package/skills/draftcut/references/04-reference-theme-prompt.md +0 -7
- package/skills/draftcut/references/05-social-loudness.md +0 -58
- package/skills/draftcut/references/06-modern-components.md +0 -72
- package/skills/easyedit/SKILL.md +0 -66
- package/skills/erduo-broll-loop-engineering/SKILL.md +0 -136
- package/skills/erduo-broll-loop-engineering/references/animation-craft.md +0 -208
- package/skills/erduo-broll-loop-engineering/references/first-run-onboarding.md +0 -107
- package/skills/erduo-broll-loop-engineering/references/handoff-template.md +0 -70
- package/skills/erduo-broll-loop-engineering/references/motion-layout-lint.md +0 -122
- package/skills/erduo-broll-loop-engineering/references/parent-review-checklist.md +0 -171
- package/skills/erduo-broll-loop-engineering/references/prompt-first-workflow.md +0 -322
- package/skills/erduo-broll-loop-engineering/references/remotion-backend.md +0 -334
- package/skills/erduo-broll-loop-engineering/references/runtime/remotion-hyperframes-map.md +0 -76
- package/skills/erduo-broll-loop-engineering/references/runtime/runtime-contract.md +0 -174
- package/skills/erduo-broll-loop-engineering/references/runtime/runtime-selection.md +0 -135
- package/skills/erduo-broll-loop-engineering/references/shotcraft/remotion-sources/SOURCE.md +0 -7
- package/skills/erduo-broll-loop-engineering/references/shotcraft/upstream-attribution.md +0 -65
- package/skills/explainer-assets/SKILL.md +0 -98
- package/skills/explainer-video/SKILL.md +0 -146
- package/skills/framewright/SKILL.md +0 -324
- package/skills/framewright/references/audio.md +0 -230
- package/skills/framewright/references/guide.md +0 -276
- package/skills/framewright/references/painting.md +0 -425
- package/skills/framewright/references/photo.md +0 -75
- package/skills/framewright/references/questionnaire.md +0 -115
- package/skills/framewright/references/styles.md +0 -388
- package/skills/framewright/references/troubleshooting.md +0 -119
- package/skills/framewright/references/world.md +0 -215
- package/skills/gbro-collage-broll/SKILL.md +0 -435
- package/skills/gbro-collage-info/SKILL.md +0 -135
- package/skills/gbro-collage-info/references/motion-grammar.md +0 -66
- package/skills/gbro-collage-info/references/production.md +0 -67
- package/skills/gbro-collage-info/references/style-system.md +0 -38
- package/skills/gemini-tts/SKILL.md +0 -208
- package/skills/gemini-tts/references/prompting-guide.md +0 -169
- package/skills/gen/SKILL.md +0 -282
- package/skills/ghost-editor/SKILL.md +0 -437
- package/skills/ghost-editor/docs/HOW-IT-WORKS.md +0 -82
- package/skills/ghost-editor/docs/PLAYBOOK.md +0 -139
- package/skills/ghost-editor/docs/THIRD_PARTY/audio.md +0 -17
- package/skills/ghost-editor/docs/THIRD_PARTY/audioqa.md +0 -13
- package/skills/ghost-editor/docs/THIRD_PARTY/captions.md +0 -20
- package/skills/ghost-editor/docs/THIRD_PARTY/fonts.md +0 -17
- package/skills/ghost-editor/docs/THIRD_PARTY/kinetic.md +0 -22
- package/skills/ghost-editor/docs/THIRD_PARTY/looks.md +0 -22
- package/skills/ghost-editor/docs/THIRD_PARTY/matte.md +0 -20
- package/skills/ghost-editor/docs/THIRD_PARTY/models.md +0 -11
- package/skills/ghost-editor/docs/THIRD_PARTY/runtime.md +0 -13
- package/skills/ghost-editor/docs/THIRD_PARTY/shaders.md +0 -15
- package/skills/git-story-film/SKILL.md +0 -220
- package/skills/git-story-film/examples/raven-story/FONTS.md +0 -8
- package/skills/git-story-film/examples/raven-story/OUTLINE.md +0 -93
- package/skills/git-story-film/references/craft.md +0 -148
- package/skills/git-story-film/references/directing.md +0 -185
- package/skills/git-story-film/references/forms.md +0 -150
- package/skills/git-story-film/references/production.md +0 -150
- package/skills/git-story-film/references/story.md +0 -137
- package/skills/git-story-film/references/text-and-fonts.md +0 -90
- package/skills/guizang-product-video-skill/SKILL.md +0 -96
- package/skills/guizang-product-video-skill/references/audio-and-qa.md +0 -113
- package/skills/guizang-product-video-skill/references/audio-sourcing.md +0 -80
- package/skills/guizang-product-video-skill/references/case-study.md +0 -63
- package/skills/guizang-product-video-skill/references/component-pipeline.md +0 -86
- package/skills/guizang-product-video-skill/references/cover.md +0 -43
- package/skills/guizang-product-video-skill/references/direction.md +0 -91
- package/skills/guizang-product-video-skill/references/onboarding.md +0 -98
- package/skills/guizang-product-video-skill/references/repo-and-style.md +0 -44
- package/skills/guizang-product-video-skill/references/review.md +0 -38
- package/skills/guizang-product-video-skill/references/starter.md +0 -168
- package/skills/guizang-product-video-skill/references/story-and-copy.md +0 -88
- package/skills/guizang-product-video-skill/references/visual-vocabulary.md +0 -78
- package/skills/guofeng-paper-video/SKILL.md +0 -159
- package/skills/guofeng-paper-video/style/design.md +0 -43
- package/skills/guofeng-paper-video/style/palette.md +0 -21
- package/skills/guofeng-paper-video/style/prompts/01-/345/210/206/351/225/234/350/241/250.md +0 -19
- package/skills/guofeng-paper-video/style/prompts/02-/347/224/237/346/210/220/347/272/270/347/211/207.md +0 -37
- package/skills/guofeng-paper-video/style/prompts/03-/351/205/215/351/237/263/350/204/232/346/234/254.md +0 -27
- package/skills/guofeng-paper-video/style//345/210/206/351/225/234/344/270/216/345/233/276/345/261/202/350/247/204/350/214/203.md +0 -67
- package/skills/guofeng-paper-video/style//347/272/270/347/211/207/347/264/240/346/235/220/350/247/204/350/214/203.md +0 -29
- package/skills/hand-drawn-explainer-video-nikola/SKILL.md +0 -113
- package/skills/hand-drawn-explainer-video-nikola/docs/ARCHITECTURE.md +0 -18
- package/skills/hand-drawn-explainer-video-nikola/docs/CONFIGURATION.md +0 -22
- package/skills/hand-drawn-explainer-video-nikola/docs/STYLES.md +0 -28
- package/skills/hand-drawn-explainer-video-nikola/docs/TROUBLESHOOTING.md +0 -35
- package/skills/hand-drawn-explainer-video-nikola/examples/program-animation/skill-demo/DESIGN.md +0 -24
- package/skills/hand-drawn-explainer-video-nikola/references/automation-workflow.md +0 -67
- package/skills/hand-drawn-explainer-video-nikola/references/output-example.md +0 -79
- package/skills/hand-drawn-explainer-video-nikola/references/preflight-and-recovery.md +0 -49
- package/skills/hand-drawn-explainer-video-nikola/references/style-guide.md +0 -82
- package/skills/hand-drawn-explainer-video-nikola/references/style-selection-and-updates.md +0 -39
- package/skills/hand-drawn-explainer-video-nikola/references/upstream-whiteboard-review.md +0 -30
- package/skills/hand-drawn-explainer-video-nikola/references/voiceover.md +0 -37
- package/skills/hbg-life-simulation/SKILL.md +0 -285
- package/skills/hbg-life-simulation/references/image-generation.md +0 -53
- package/skills/hbg-life-simulation/references/local-account-api.md +0 -112
- package/skills/hbg-life-simulation/references/opening-system.md +0 -45
- package/skills/hbg-life-simulation/references/project-spec.md +0 -62
- package/skills/hbg-life-simulation/references/render-and-qa.md +0 -107
- package/skills/hbg-life-simulation/references/storyboarding.md +0 -69
- package/skills/hbg-life-simulation/references/style-system.md +0 -80
- package/skills/hbg-life-simulation/references/visual-system.md +0 -44
- package/skills/heygen-avatar/SKILL.md +0 -489
- package/skills/heygen-avatar/references/asset-routing.md +0 -86
- package/skills/heygen-avatar/references/avatar-creation.md +0 -181
- package/skills/heygen-avatar/references/troubleshooting.md +0 -137
- package/skills/heytea-doodle-poster/SKILL.md +0 -132
- package/skills/heytea-doodle-poster/references/desktop-pet-character-modes.md +0 -103
- package/skills/heytea-doodle-poster/references/desktop-pet-environment.md +0 -122
- package/skills/heytea-doodle-poster/references/desktop-pet-pack.md +0 -106
- package/skills/heytea-doodle-poster/references/desktop-pet-workflow.md +0 -264
- package/skills/heytea-doodle-poster/references/evaluation.md +0 -246
- package/skills/heytea-doodle-poster/references/lettering-guide.md +0 -213
- package/skills/heytea-doodle-poster/references/mixed-media-style-guide.md +0 -101
- package/skills/heytea-doodle-poster/references/monster-poster-workflow.md +0 -56
- package/skills/heytea-doodle-poster/references/style-guide.md +0 -412
- package/skills/heytea-doodle-poster-hosted/SKILL.md +0 -132
- package/skills/heytea-doodle-poster-hosted/references/desktop-pet-character-modes.md +0 -103
- package/skills/heytea-doodle-poster-hosted/references/desktop-pet-environment.md +0 -122
- package/skills/heytea-doodle-poster-hosted/references/desktop-pet-pack.md +0 -106
- package/skills/heytea-doodle-poster-hosted/references/desktop-pet-workflow.md +0 -264
- package/skills/heytea-doodle-poster-hosted/references/evaluation.md +0 -246
- package/skills/heytea-doodle-poster-hosted/references/lettering-guide.md +0 -213
- package/skills/heytea-doodle-poster-hosted/references/mixed-media-style-guide.md +0 -101
- package/skills/heytea-doodle-poster-hosted/references/monster-poster-workflow.md +0 -56
- package/skills/heytea-doodle-poster-hosted/references/style-guide.md +0 -412
- package/skills/html2video/SKILL.md +0 -290
- package/skills/html2video/references/cjk-type.md +0 -173
- package/skills/html2video/references/editorial.md +0 -145
- package/skills/html2video/references/narration.md +0 -111
- package/skills/html2video/references/pitfalls.md +0 -238
- package/skills/html2video/references/shots.md +0 -198
- package/skills/html2video/references/storyboard.md +0 -323
- package/skills/hyperdirector/SKILL.md +0 -202
- package/skills/hyperdirector/docs/audio-workflow.md +0 -160
- package/skills/hyperdirector/docs/audio-workflow.zh-CN.md +0 -244
- package/skills/hyperdirector/docs/brand-kit-setup.md +0 -322
- package/skills/hyperdirector/docs/brand-kit-setup.zh-CN.md +0 -277
- package/skills/hyperdirector/docs/cursor-development-notes.md +0 -474
- package/skills/hyperdirector/docs/faq.md +0 -285
- package/skills/hyperdirector/docs/faq.zh-CN.md +0 -198
- package/skills/hyperdirector/docs/first-video.md +0 -320
- package/skills/hyperdirector/docs/first-video.zh-CN.md +0 -265
- package/skills/hyperdirector/docs/installation.md +0 -254
- package/skills/hyperdirector/docs/installation.zh-CN.md +0 -222
- package/skills/hyperdirector/docs/quickstart.md +0 -203
- package/skills/hyperframes/SKILL.md +0 -117
- package/skills/hyperframes/references/captions.md +0 -46
- package/skills/hyperframes/references/film.md +0 -48
- package/skills/hyperframes/references/format.md +0 -158
- package/skills/hyperframes/references/look.md +0 -69
- package/skills/hyperframes/references/motion.md +0 -95
- package/skills/hyperframes/references/overlays.md +0 -39
- package/skills/hyperframes/references/review.md +0 -51
- package/skills/hyperframes/references/runtimes.md +0 -69
- package/skills/hyperframes/references/skill-lifecycle.md +0 -49
- package/skills/hyperframes/references/sound.md +0 -43
- package/skills/hyperframes/references/spec.md +0 -76
- package/skills/hyperframes/references/story.md +0 -103
- package/skills/hyperframes-motion-director/SKILL.md +0 -920
- package/skills/hyperframes-motion-director/references/asset-choreography-and-render-qa.md +0 -185
- package/skills/hyperframes-motion-director/references/audio-sync.md +0 -83
- package/skills/hyperframes-motion-director/references/design-engineering.md +0 -156
- package/skills/hyperframes-motion-director/references/gsap-choreography.md +0 -202
- package/skills/hyperframes-motion-director/references/hyperframes-stability.md +0 -99
- package/skills/hyperframes-motion-director/references/imagegen-asset-pipeline.md +0 -227
- package/skills/hyperframes-motion-director/references/motion-background-system.md +0 -165
- package/skills/hyperframes-motion-director/references/motion-craft.md +0 -182
- package/skills/hyperframes-motion-director/references/premium-product-promo.md +0 -287
- package/skills/hyperframes-motion-director/references/text-over-background-layout.md +0 -221
- package/skills/hyperframes-motion-director/references/visual-standard.md +0 -174
- package/skills/hyperframes-motion-director/references/workflow.md +0 -320
- package/skills/hypit/SKILL.md +0 -367
- package/skills/hypit/references/creation/brief.md +0 -93
- package/skills/hypit/references/creation/script-and-time.md +0 -259
- package/skills/hypit/references/creation/transformations.md +0 -143
- package/skills/hypit/references/playbooks/craft/b-roll.md +0 -94
- package/skills/hypit/references/playbooks/craft/caption-tracking.md +0 -126
- package/skills/hypit/references/playbooks/craft/captions.md +0 -253
- package/skills/hypit/references/playbooks/craft/generated-dependencies.md +0 -38
- package/skills/hypit/references/playbooks/craft/graphic-compositions.md +0 -85
- package/skills/hypit/references/playbooks/craft/motion-graphics.md +0 -68
- package/skills/hypit/references/playbooks/craft/screen-demonstrations.md +0 -51
- package/skills/hypit/references/playbooks/craft/sound-mix.md +0 -70
- package/skills/hypit/references/playbooks/formats/narration-led-demo.md +0 -87
- package/skills/image/SKILL.md +0 -153
- package/skills/image/references/characters.md +0 -86
- package/skills/image/references/creative-direction.md +0 -137
- package/skills/image/references/de-slop.md +0 -95
- package/skills/image/references/dimensional.md +0 -88
- package/skills/image/references/editing.md +0 -112
- package/skills/image/references/golden-rules.md +0 -198
- package/skills/image/references/gpt-image.md +0 -228
- package/skills/image/references/models.md +0 -78
- package/skills/image/references/multi-panel.md +0 -354
- package/skills/image/references/nano-banana.md +0 -150
- package/skills/image/references/patterns/character-design.md +0 -150
- package/skills/image/references/patterns/ecommerce.md +0 -124
- package/skills/image-smixs/SKILL.md +0 -153
- package/skills/image-smixs/references/characters.md +0 -86
- package/skills/image-smixs/references/creative-direction.md +0 -137
- package/skills/image-smixs/references/de-slop.md +0 -95
- package/skills/image-smixs/references/dimensional.md +0 -88
- package/skills/image-smixs/references/editing.md +0 -112
- package/skills/image-smixs/references/golden-rules.md +0 -198
- package/skills/image-smixs/references/gpt-image.md +0 -228
- package/skills/image-smixs/references/models.md +0 -78
- package/skills/image-smixs/references/multi-panel.md +0 -354
- package/skills/image-smixs/references/nano-banana.md +0 -150
- package/skills/image-smixs/references/patterns/character-design.md +0 -150
- package/skills/image-smixs/references/patterns/ecommerce.md +0 -124
- package/skills/image-story-video-wizard/SKILL.md +0 -148
- package/skills/image-story-video-wizard/docs/ARTICLE_ALIGNMENT.md +0 -29
- package/skills/image-story-video-wizard/references/host-routing.md +0 -44
- package/skills/image-story-video-wizard/references/state-schema.md +0 -79
- package/skills/image-story-video-wizard/references/workflow.md +0 -203
- package/skills/image-story-video-wizard/references/writing-and-review.md +0 -60
- package/skills/ip-as-logo/SKILL.md +0 -151
- package/skills/ip-as-logo-s1dashu/SKILL.md +0 -151
- package/skills/jtxvideo-skill/SKILL.md +0 -337
- package/skills/kinetic-reel/SKILL.md +0 -140
- package/skills/kinetic-reel/examples/work-reel-26/STORYBOARD.md +0 -51
- package/skills/kinetic-reel/references/sound.md +0 -40
- package/skills/kinetic-reel/references/style-guide.md +0 -79
- package/skills/knowledge-explainer-skill/SKILL.md +0 -149
- package/skills/knowledge-explainer-skill/examples/ai_video_3steps.md +0 -61
- package/skills/knowledge-explainer-skill/examples/algorithm_bubble.md +0 -20
- package/skills/knowledge-explainer-skill/examples/before_after_demo.md +0 -38
- package/skills/knowledge-explainer-skill/examples/cta_outro.md +0 -11
- package/skills/knowledge-explainer-skill/examples/double_pendulum.md +0 -20
- package/skills/knowledge-explainer-skill/examples/paper_fold.md +0 -20
- package/skills/knowledge-explainer-skill/examples/script.md +0 -40
- package/skills/lanshu-create-ai-presenter-video/SKILL.md +0 -253
- package/skills/lanshu-create-ai-presenter-video/references/editing.md +0 -67
- package/skills/lanshu-create-ai-presenter-video/references/generation.md +0 -94
- package/skills/lanshu-create-ai-presenter-video/references/qa-recovery.md +0 -83
- package/skills/lanshu-create-ai-presenter-video/references/styled-explainer.md +0 -189
- package/skills/laoxu-video-script/SKILL.md +0 -117
- package/skills/laoxu-video-script/references/cases.md +0 -305
- package/skills/laoxu-video-script/references/de-ai.md +0 -32
- package/skills/laoxu-video-script/references/diagnostics.md +0 -67
- package/skills/laoxu-video-script/references/format.md +0 -62
- package/skills/laoxu-video-script/references/formulas.md +0 -43
- package/skills/laoxu-video-script/references/method.md +0 -115
- package/skills/laoxu-video-script/references/motifs-and-lines.md +0 -829
- package/skills/laoxu-video-script/references/persona.md +0 -38
- package/skills/laoxu-video-script/references/qihao-path.md +0 -35
- package/skills/laoxu-video-script/references/qihao-xinfa.md +0 -39
- package/skills/laoxu-video-script/references/redlines.md +0 -26
- package/skills/lemo-opuscar/SKILL.md +0 -67
- package/skills/lipnardo/SKILL.md +0 -308
- package/skills/lipnardo/examples/batch-personalized.md +0 -44
- package/skills/lipnardo/examples/photo-to-avatar-pipeline.md +0 -56
- package/skills/lipnardo/examples/single-video.md +0 -44
- package/skills/lipnardo/references/avatar-types.md +0 -42
- package/skills/lipnardo/references/credit-costs.md +0 -39
- package/skills/lipnardo/references/error-codes.md +0 -66
- package/skills/lipnardo/references/heygen-api-reference.md +0 -416
- package/skills/ll-video-decomposer/SKILL.md +0 -105
- package/skills/ll-video-decomposer/references/audiovisual-analysis-guide.md +0 -44
- package/skills/ll-video-decomposer/references/evidence-and-confidence-rules.md +0 -41
- package/skills/ll-video-decomposer/references/multi-video-comparison-template.md +0 -48
- package/skills/ll-video-decomposer/references/single-video-report-template.md +0 -47
- package/skills/ll-video-decomposer/references/tool-discovery-workflow.md +0 -30
- package/skills/ll-video-decomposer/references/transcription-routing.md +0 -65
- package/skills/ll-video-decomposer/references/video-acquisition-workflow.md +0 -30
- package/skills/ltx2-video/SKILL.md +0 -193
- package/skills/ltx2-video/references/mode_ux.md +0 -293
- package/skills/make-ai-short/SKILL.md +0 -130
- package/skills/make-blender-education-video/SKILL.md +0 -247
- package/skills/make-blender-education-video/references/evidence-and-explanation.md +0 -62
- package/skills/make-blender-education-video/references/github-workflow-discovery.md +0 -55
- package/skills/make-blender-education-video/references/production-workflow.md +0 -62
- package/skills/make-blender-education-video/references/story-patterns.md +0 -65
- package/skills/make-blender-education-video/references/visual-quality.md +0 -82
- package/skills/manage-storyboard-projects/SKILL.md +0 -128
- package/skills/manim-composer/SKILL.md +0 -176
- package/skills/manim-composer/references/narrative-patterns.md +0 -125
- package/skills/manim-composer/references/scene-examples.md +0 -216
- package/skills/manim-composer/references/visual-techniques.md +0 -223
- package/skills/manim-composer/templates/scenes-template.md +0 -147
- package/skills/monet-ai-editor-monet/SKILL.md +0 -367
- package/skills/motion-graphics/SKILL.md +0 -206
- package/skills/motion-graphics/references/craft.md +0 -136
- package/skills/motion-graphics/references/engine.md +0 -130
- package/skills/motion-graphics/references/export.md +0 -67
- package/skills/motion-graphics/references/physics.md +0 -100
- package/skills/motion-graphics/references/verify.md +0 -124
- package/skills/motion-video/SKILL.md +0 -133
- package/skills/motion-video/references/audio-and-beat-sync.md +0 -109
- package/skills/motion-video/references/composition-contract.md +0 -107
- package/skills/motion-video/references/production-pipeline.md +0 -147
- package/skills/motion-video/references/style-comic-spiderverse.md +0 -87
- package/skills/motion-video/references/style-glass-keynote.md +0 -69
- package/skills/motion-video-maker/SKILL.md +0 -1452
- package/skills/motion-video-maker/reference/components.md +0 -451
- package/skills/motion-video-maker/reference/workflow.md +0 -190
- package/skills/motioncraft/SKILL.md +0 -221
- package/skills/motioncraft/references/animation-system.md +0 -57
- package/skills/motioncraft/references/assets-and-licensing.md +0 -21
- package/skills/motioncraft/references/customization.md +0 -52
- package/skills/motioncraft/references/gpu-cloud-render.md +0 -15
- package/skills/motioncraft/references/music.md +0 -43
- package/skills/motioncraft/references/phase1-planning-and-preview.md +0 -74
- package/skills/motioncraft/references/phase2-timeline-audio.md +0 -33
- package/skills/motioncraft/references/phase3-pixel-review.md +0 -13
- package/skills/motioncraft/references/phase4-templates.md +0 -30
- package/skills/motioncraft/references/preflight.md +0 -27
- package/skills/motioncraft/references/qa.md +0 -53
- package/skills/motioncraft/references/reference-analysis.md +0 -37
- package/skills/narrator-ai-cli/SKILL.md +0 -256
- package/skills/narrator-ai-cli/references/magic-video.md +0 -205
- package/skills/narrator-ai-cli/references/operations.md +0 -230
- package/skills/narrator-ai-cli/references/resources.md +0 -126
- package/skills/narrator-ai-cli/references/workflows.md +0 -332
- package/skills/newcut-video-clipping/SKILL.md +0 -194
- package/skills/newcut-video-clipping/references/examples.md +0 -59
- package/skills/newcut-video-clipping/references/provider-config.md +0 -110
- package/skills/newcut-video-clipping/references/quality-check.md +0 -35
- package/skills/newcut-video-clipping/references/semantic-plan.md +0 -65
- package/skills/notes-to-video/SKILL.md +0 -476
- package/skills/openchatcut/SKILL.md +0 -100
- package/skills/openchatcut/references/editing-workflow.md +0 -54
- package/skills/openchatcut/references/getting-started.md +0 -106
- package/skills/openchatcut/references/known-errors.md +0 -62
- package/skills/openstoryline-install/SKILL.md +0 -228
- package/skills/orca-motion/SKILL.md +0 -100
- package/skills/orca-motion/references/api.md +0 -100
- package/skills/orca-motion/references/integration.md +0 -59
- package/skills/orca-motion/references/kinetic-type.md +0 -59
- package/skills/orca-motion/references/principles.md +0 -76
- package/skills/package-talking-head-video/SKILL.md +0 -90
- package/skills/package-talking-head-video/docs/EXAMPLES.md +0 -18
- package/skills/package-talking-head-video/docs/TROUBLESHOOTING.md +0 -29
- package/skills/package-talking-head-video/docs/USAGE.md +0 -83
- package/skills/package-talking-head-video/docs/superpowers/plans/2026-08-08-multicolor-center-speaker.md +0 -144
- package/skills/package-talking-head-video/docs/superpowers/plans/2026-08-08-semantic-template-system-v2.md +0 -1099
- package/skills/package-talking-head-video/docs/superpowers/specs/2026-08-08-multicolor-center-speaker-design.md +0 -154
- package/skills/package-talking-head-video/docs/superpowers/specs/2026-08-08-semantic-template-system-v2-design.md +0 -365
- package/skills/package-talking-head-video/examples/auto-editing-0/GATE_A.md +0 -56
- package/skills/package-talking-head-video/examples/auto-editing-0/GATE_D.md +0 -8
- package/skills/package-talking-head-video/examples/auto-editing-0/QA_REPORT.md +0 -34
- package/skills/package-talking-head-video/references/director-rules.md +0 -29
- package/skills/package-talking-head-video/references/motion-and-illustration.md +0 -25
- package/skills/paper-cut/SKILL.md +0 -164
- package/skills/paper-cut/references/asset-spec.md +0 -47
- package/skills/paper-cut/references/audio-and-chatcut.md +0 -26
- package/skills/paper-cut/references/hyperframes-assembly.md +0 -47
- package/skills/paper-cut/references/image-led-production.md +0 -65
- package/skills/paper-cut/references/storyboard-schema.md +0 -48
- package/skills/paper-cut/references/workflow.md +0 -39
- package/skills/personal-ip-brand-intro/SKILL.md +0 -216
- package/skills/personal-ip-brand-intro/references/intake-schema.md +0 -79
- package/skills/personal-ip-brand-intro/references/music-upload-workflow.md +0 -40
- package/skills/personal-ip-brand-intro/references/originality-rules.md +0 -42
- package/skills/personal-ip-brand-intro/references/qa-checklist.md +0 -60
- package/skills/personal-ip-brand-intro/references/rhythm-routing.md +0 -41
- package/skills/personal-ip-brand-intro/references/storyboard-contract.md +0 -42
- package/skills/pixel2motion/SKILL.md +0 -279
- package/skills/pixel2motion/references/html-delivery-template.md +0 -42
- package/skills/pixel2motion/references/motion-personality.md +0 -109
- package/skills/pixel2motion/references/reveal-patterns.md +0 -163
- package/skills/pixel2motion/references/ribbon-fitting.md +0 -90
- package/skills/pixel2motion/references/twelve-principles-for-logos.md +0 -116
- package/skills/premiere-batch-delivery/SKILL.md +0 -71
- package/skills/premiere-pro-mcp/SKILL.md +0 -161
- package/skills/promo-creator-skills/SKILL.md +0 -209
- package/skills/promo-creator-skills/references/mureka_prompt_guide.md +0 -251
- package/skills/promo-creator-skills/references/product_promo_bgm_prompting.md +0 -100
- package/skills/promo-video/SKILL.md +0 -408
- package/skills/qisi-video-remix/SKILL.md +0 -134
- package/skills/qisi-video-remix/examples/creative-plan.md +0 -133
- package/skills/qisi-video-remix/references/delivery-guide.md +0 -63
- package/skills/reel-video/SKILL.md +0 -237
- package/skills/remotion-ad-video/SKILL.md +0 -252
- package/skills/remotion-ad-video/references/ad-aesthetic-qa.md +0 -60
- package/skills/remotion-ad-video/references/ad-brief-contract.md +0 -235
- package/skills/remotion-ad-video/references/ad-exemplars.md +0 -186
- package/skills/remotion-ad-video/references/ad-intake.md +0 -54
- package/skills/remotion-ad-video/references/asset-harvest.md +0 -56
- package/skills/remotion-ad-video/references/audio-caption-system.md +0 -202
- package/skills/remotion-ad-video/references/concept-contract.md +0 -128
- package/skills/remotion-ad-video/references/creative-direction.md +0 -146
- package/skills/remotion-ad-video/references/fast-test-workflow.md +0 -86
- package/skills/remotion-ad-video/references/game-ad-patterns.md +0 -75
- package/skills/remotion-ad-video/references/hyperframes-output.md +0 -90
- package/skills/remotion-ad-video/references/industry-angle-library.md +0 -71
- package/skills/remotion-ads/SKILL.md +0 -278
- package/skills/remotion-ads/references/ad-copywriting.md +0 -229
- package/skills/remotion-ads/references/animations.md +0 -693
- package/skills/remotion-ads/references/brand-config-template.md +0 -355
- package/skills/remotion-ads/references/captions.md +0 -529
- package/skills/remotion-ads/references/carousels.md +0 -580
- package/skills/remotion-ads/references/components.md +0 -897
- package/skills/remotion-ads/references/copy-frameworks.md +0 -144
- package/skills/remotion-ads/references/formats.md +0 -436
- package/skills/remotion-ads/references/gemini-tts.md +0 -473
- package/skills/remotion-ads/references/html-in-canvas.md +0 -555
- package/skills/remotion-ads/references/local-assets.md +0 -543
- package/skills/remotion-ads/references/music.md +0 -656
- package/skills/remotion-code-motion-explainer/SKILL.md +0 -178
- package/skills/remotion-code-motion-explainer/references/code-motion-design.md +0 -86
- package/skills/remotion-code-motion-explainer/references/motion-production-patterns.md +0 -93
- package/skills/remotion-code-motion-explainer/references/production-and-qc.md +0 -99
- package/skills/remotion-code-motion-explainer/references/reference-reconstruction.md +0 -48
- package/skills/remotion-code-motion-explainer/references/ui-motion-shot-library.md +0 -62
- package/skills/remotion-motion-graphics/SKILL.md +0 -169
- package/skills/remotion-motion-graphics/references/patterns.md +0 -355
- package/skills/remotion-motion-graphics/references/polish.md +0 -102
- package/skills/remotion-motion-graphics/references/scaffold.md +0 -144
- package/skills/remotion-motion-graphics/references/traps.md +0 -152
- package/skills/remotion-resemble-ai/SKILL.md +0 -879
- package/skills/remotion-resemble-ai/rules/resemble-captions.md +0 -350
- package/skills/remotion-resemble-ai/rules/resemble-remotion-integration.md +0 -305
- package/skills/remotion-resemble-ai/rules/resemble-setup.md +0 -284
- package/skills/remotion-resemble-ai/rules/resemble-streaming-tts.md +0 -225
- package/skills/remotion-resemble-ai/rules/resemble-sync-tts.md +0 -239
- package/skills/remotion-resemble-ai/rules/resemble-voices.md +0 -213
- package/skills/remotion-resemble-ai/rules/visual-animations.md +0 -567
- package/skills/riffkit/SKILL.md +0 -196
- package/skills/riffkit/examples/any-look-styles.md +0 -11
- package/skills/riffkit/examples/faceless-and-auto.md +0 -16
- package/skills/riffkit/examples/localize-spanish.md +0 -18
- package/skills/riffkit/examples/tiktok-shop-product.md +0 -22
- package/skills/riffkit/references/anchor.md +0 -62
- package/skills/riffkit/references/api.md +0 -806
- package/skills/riffkit/references/details.md +0 -153
- package/skills/riffkit/references/errors.md +0 -69
- package/skills/riffkit/references/intents.md +0 -29
- package/skills/saas-motion-video/SKILL.md +0 -71
- package/skills/script-to-video/SKILL.md +0 -2627
- package/skills/shorts/SKILL.md +0 -372
- package/skills/shorts/references/caption-styles.md +0 -105
- package/skills/shorts/references/platform-specs.md +0 -149
- package/skills/shorts/references/remotion-patterns.md +0 -180
- package/skills/shorts/references/scoring-rubric.md +0 -106
- package/skills/smart-video-editor/SKILL.md +0 -327
- package/skills/smart-video-editor/docs/FONTS.md +0 -57
- package/skills/story-telling/SKILL.md +0 -222
- package/skills/story-telling/rules/composition.md +0 -130
- package/skills/story-telling/rules/images.md +0 -119
- package/skills/story-telling/rules/models.md +0 -98
- package/skills/story-telling/rules/narration.md +0 -87
- package/skills/story-telling/rules/pitfalls.md +0 -140
- package/skills/story-telling/rules/story-formats.md +0 -108
- package/skills/story-telling/rules/story-json.md +0 -143
- package/skills/story-telling/rules/voices.md +0 -114
- package/skills/story-telling/rules/workflow.md +0 -105
- package/skills/story-to-handdrawn-video/SKILL.md +0 -216
- package/skills/story-to-handdrawn-video/references/asset-workflow.md +0 -24
- package/skills/story-to-handdrawn-video/references/reference-style-workflow.md +0 -27
- package/skills/su-card-to-video/SKILL.md +0 -103
- package/skills/talking-head-video-pipeline/SKILL.md +0 -224
- package/skills/talking-head-video-pipeline/examples/prompts.md +0 -217
- package/skills/talking-head-video-pipeline/references/asr-adapters.md +0 -51
- package/skills/talking-head-video-pipeline/references/caption-workflow.md +0 -53
- package/skills/talking-head-video-pipeline/references/export-recipes.md +0 -78
- package/skills/talking-head-video-pipeline/references/layout-safety.md +0 -49
- package/skills/talking-head-video-pipeline/references/video-use-integration.md +0 -71
- package/skills/talking-head-video-pipeline/references/workflows/captions.md +0 -52
- package/skills/talking-head-video-pipeline/references/workflows/design.md +0 -77
- package/skills/talking-head-video-pipeline/references/workflows/doctor.md +0 -51
- package/skills/talking-head-video-pipeline/references/workflows/export.md +0 -50
- package/skills/talking-head-video-pipeline/references/workflows/init.md +0 -51
- package/skills/talking-head-video-pipeline/references/workflows/learn.md +0 -36
- package/skills/text-to-lottie/SKILL.md +0 -202
- package/skills/text-to-lottie/references/chapterization-transition-grammar.md +0 -132
- package/skills/text-to-lottie/references/design-taste.md +0 -292
- package/skills/text-to-lottie/references/lottie-spec-map.md +0 -82
- package/skills/text-to-lottie/references/motion-taste.md +0 -260
- package/skills/text-to-lottie/references/player-contract.md +0 -325
- package/skills/text-to-lottie/references/recipe-camera-scene-motion.md +0 -65
- package/skills/text-to-lottie/references/recipe-data-stats.md +0 -104
- package/skills/text-to-lottie/references/recipe-diagram-technical.md +0 -106
- package/skills/text-to-lottie/references/recipe-loaders-icons.md +0 -70
- package/skills/text-to-lottie/references/recipe-logo.md +0 -72
- package/skills/text-to-lottie/references/recipe-lower-thirds.md +0 -62
- package/skills/text-to-lottie/references/recipe-product-promo.md +0 -99
- package/skills/ultrademo/SKILL.md +0 -212
- package/skills/video-assemble/SKILL.md +0 -101
- package/skills/video-assemble-zenstory-ai/SKILL.md +0 -153
- package/skills/video-assemble-zenstory-ai/references/audio-modes.md +0 -63
- package/skills/video-assemble-zenstory-ai/references/explicit-audio-mix.md +0 -77
- package/skills/video-assemble-zenstory-ai/references/jianying/SOURCE.md +0 -14
- package/skills/video-assemble-zenstory-ai/references/narration-adoption.md +0 -103
- package/skills/video-assemble-zenstory-ai/references/packaging.md +0 -44
- package/skills/video-assemble-zenstory-ai/references/source-score.md +0 -146
- package/skills/video-assemble-zenstory-ai/references/subtitle-track.md +0 -202
- package/skills/video-editing/SKILL.md +0 -688
- package/skills/video-explainer/SKILL.md +0 -163
- package/skills/video-explainer/references/brief-to-script.md +0 -56
- package/skills/video-explainer/references/errors-and-privacy.md +0 -18
- package/skills/video-explainer/references/motion-storyboard.md +0 -82
- package/skills/video-explainer/references/render-and-verify.md +0 -62
- package/skills/video-explainer/references/review-gate.md +0 -82
- package/skills/video-explainer/references/setup-and-doctor.md +0 -33
- package/skills/video-script-builder/SKILL.md +0 -329
- package/skills/video-script-builder/examples/quick-start-transcript.md +0 -19
- package/skills/video-script-builder/references/audio-workflow.md +0 -84
- package/skills/video-script-builder/references/caption-components.md +0 -70
- package/skills/video-script-builder/references/common-pitfalls.md +0 -80
- package/skills/video-script-builder/references/component-catalog.md +0 -197
- package/skills/video-script-builder/references/component-recipes.md +0 -165
- package/skills/video-script-builder/references/gsap-patterns.md +0 -112
- package/skills/video-script-builder/references/pacing-rules.md +0 -78
- package/skills/video-script-builder/references/quality-checklist.md +0 -98
- package/skills/video-script-builder/references/remotion-patterns.md +0 -211
- package/skills/video-script-builder/references/shader-transitions.md +0 -115
- package/skills/video-script-builder/references/taste-principles.md +0 -160
- package/skills/video-scrub/SKILL.md +0 -216
- package/skills/video-scrub/references/profiles.md +0 -89
- package/skills/video-scrub/references/residue-map.md +0 -204
- package/skills/video-short-maker/SKILL.md +0 -182
- package/skills/video-shot-analysis-feishu/SKILL.md +0 -173
- package/skills/video-shotcraft/SKILL.md +0 -267
- package/skills/video-shotcraft/docs/deepseek-harness.md +0 -69
- package/skills/video-shotcraft/references/aesthetic-rules.md +0 -177
- package/skills/video-shotcraft/references/final-review.md +0 -112
- package/skills/video-shotcraft/references/guided-free-creation.md +0 -199
- package/skills/video-shotcraft/references/jianying-export.md +0 -182
- package/skills/video-shotcraft/references/music-beat-sync.md +0 -219
- package/skills/video-shotcraft/references/pipeline.md +0 -390
- package/skills/video-shotcraft/references/sequences/promo-energy-arc.md +0 -50
- package/skills/video-shotcraft/references/shots/ATTRIBUTION.md +0 -65
- package/skills/video-shotcraft/references/shots/camera/basic-3d-scene.md +0 -37
- package/skills/video-shotcraft/references/shots/camera/crash-zoom-punch.md +0 -39
- package/skills/video-shotcraft/references/shots/camera/cursor-flyover.md +0 -38
- package/skills/video-shotcraft-vincentwei10/SKILL.md +0 -316
- package/skills/video-shotcraft-vincentwei10/references/aesthetic-rules.md +0 -187
- package/skills/video-shotcraft-vincentwei10/references/final-review.md +0 -116
- package/skills/video-shotcraft-vincentwei10/references/guided-free-creation.md +0 -199
- package/skills/video-shotcraft-vincentwei10/references/jianying-export.md +0 -183
- package/skills/video-shotcraft-vincentwei10/references/music-beat-sync.md +0 -257
- package/skills/video-shotcraft-vincentwei10/references/pipeline.md +0 -401
- package/skills/video-shotcraft-vincentwei10/references/publish-upload-post.md +0 -111
- package/skills/video-shotcraft-vincentwei10/references/sequences/promo-energy-arc.md +0 -50
- package/skills/video-shotcraft-vincentwei10/references/shots/ATTRIBUTION.md +0 -62
- package/skills/video-shotcraft-vincentwei10/references/shots/camera/basic-3d-scene.md +0 -41
- package/skills/video-shotcraft-vincentwei10/references/shots/camera/crash-zoom-punch.md +0 -52
- package/skills/video-shotcraft-vincentwei10/references/shots/camera/cursor-flyover.md +0 -39
- package/skills/video-structure-analyzer/SKILL.md +0 -148
- package/skills/video-structure-analyzer/examples/xhs-rook-time-spend/xhs-rook-time-spend_/346/213/211/347/211/207/346/213/206/350/247/243.md +0 -50
- package/skills/video-structure-analyzer/examples/xhs-smelly-cat/xhs-smelly-cat_/346/213/211/347/211/207/346/213/206/350/247/243.md +0 -19
- package/skills/video-toolkit/SKILL.md +0 -686
- package/skills/videocut/SKILL.md +0 -159
- package/skills/videodb/SKILL.md +0 -497
- package/skills/videodb/reference/api-reference.md +0 -741
- package/skills/videodb/reference/capture-reference.md +0 -399
- package/skills/videodb/reference/capture.md +0 -110
- package/skills/videodb/reference/editor-reference.md +0 -506
- package/skills/videodb/reference/editor.md +0 -389
- package/skills/videodb/reference/generative.md +0 -344
- package/skills/videodb/reference/indexing-reference.md +0 -481
- package/skills/videodb/reference/indexing.md +0 -537
- package/skills/videodb/reference/legacy/index-reference.md +0 -223
- package/skills/videodb/reference/legacy/index.md +0 -241
- package/skills/videodb/reference/legacy/search.md +0 -249
- package/skills/videodb/reference/migration.md +0 -113
- package/skills/vlog-auto-edit/SKILL.md +0 -982
- package/skills/vlog-auto-edit/examples/project_structure.md +0 -84
- package/skills/vox-animated-ad-mcp/SKILL.md +0 -419
- package/skills/vox-director/SKILL.md +0 -351
- package/skills/vox-director/references/beat-layer.md +0 -143
- package/skills/vox-director/references/host-mode.md +0 -120
- package/skills/vox-director/references/local-engine.md +0 -73
- package/skills/vox-director/references/models-and-gotchas.md +0 -91
- package/skills/vox-director/references/prompt-guide.md +0 -275
- package/skills/vox-director/references/voices.md +0 -59
- package/skills/xingchen-vox-collage/SKILL.md +0 -251
- package/skills/xingchen-vox-collage/references/asset-layer-contract.md +0 -98
- package/skills/xingchen-vox-collage/references/creative-exploration.md +0 -19
- package/skills/xingchen-vox-collage/references/learned-branches.md +0 -34
- package/skills/xingchen-vox-collage/references/remotion-scene-contract.md +0 -77
- package/skills/xingchen-vox-collage/references/visual-language.md +0 -74
- package/skills/xingchen-vox-collage/references/visual-qa.md +0 -59
- package/skills/youtube/SKILL.md +0 -147
- package/skills/youtube/references/algorithm-guide.md +0 -59
- package/skills/youtube/references/analytics-benchmarks.md +0 -67
- package/skills/youtube/references/dataforseo-integration.md +0 -51
- package/skills/youtube/references/monetization-guide.md +0 -62
- package/skills/youtube/references/repurposing-guide.md +0 -54
- package/skills/youtube/references/retention-scripting-guide.md +0 -75
- package/skills/youtube/references/seo-playbook.md +0 -77
- package/skills/youtube/references/shorts-playbook.md +0 -64
- package/skills/youtube/references/thumbnail-ctr-guide.md +0 -73
- package/skills/youtube-shorts-factory/SKILL.md +0 -358
- package/skills/youtube-shorts-factory/resources/adaptation-guide.md +0 -133
- package/skills/youtube-shorts-factory/resources/storyboard-template.md +0 -271
- package/skills/youtube-shorts-factory/resources/workflow-steps.md +0 -139
- package/studio/ui/dist/assets/ExportCenter-DEyy1vs_.js +0 -1
- package/studio/ui/dist/assets/SettingsModal-CQmsA2A2.js +0 -2
- package/studio/ui/dist/assets/es-AqUfIkAy.js +0 -1
- package/studio/ui/dist/assets/index-C7moXjTY.css +0 -1
- package/studio/ui/dist/assets/index-DdU5QNpY.js +0 -1623
- package/studio/ui/dist/assets/ja-YwiCB4QQ.js +0 -1
- package/studio/ui/dist/assets/ko-CKtBPDze.js +0 -1
- package/studio/ui/dist/assets/zh-CN-DtNEwKWJ.js +0 -1
|
@@ -1,982 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: vlog-auto-edit
|
|
3
|
-
description: "AI Agent自动剪辑旅行Vlog的完整工作流。从原始素材到成品视频,系统级只需ffmpeg,其余在Python venv内完成。by nyx研究所 (GitHub @znyupup · B站/小红书 @nyx研究所) Runs in AICUT: the film is film.html, a page per shot, drawn by `aicut look` and `aicut render`."
|
|
4
|
-
license: MIT
|
|
5
|
-
source: "znyupup/ai-video-editing-skill"
|
|
6
|
-
---
|
|
7
|
-
|
|
8
|
-
# AI Agent 自动剪辑旅行 Vlog
|
|
9
|
-
|
|
10
|
-
## Running it in AICUT
|
|
11
|
-
|
|
12
|
-
AICUT's film is `film.html`: it cuts pages, footage, pictures and sound together on tracks. A page is a web page that
|
|
13
|
-
sets `window.film = { frame(t) }` and draws that moment — no framework, no build step, no composition object, no
|
|
14
|
-
`registerRoot`. Five shots are five pages cut together, not one page that changes scene, so each shot stays trimmable
|
|
15
|
-
and replaceable in Studio.
|
|
16
|
-
|
|
17
|
-
```sh
|
|
18
|
-
npx -y @autoaiai/aicut@latest # the manual: the format and the commands, always current
|
|
19
|
-
npx -y @autoaiai/aicut@latest open . # make this folder a film and print Studio's address
|
|
20
|
-
npx -y @autoaiai/aicut@latest look # a contact sheet of the whole film, its sound, and a determinism check
|
|
21
|
-
npx -y @autoaiai/aicut@latest look 4.5 # one frame, full size — look at the PNG, not at the code
|
|
22
|
-
npx -y @autoaiai/aicut@latest render # the MP4, beside film.html
|
|
23
|
-
```
|
|
24
|
-
|
|
25
|
-
Run the manual before the first film: it is authoritative for the format, and this skill is about the method above it.
|
|
26
|
-
|
|
27
|
-
Where the words below name another program's part, it becomes this:
|
|
28
|
-
|
|
29
|
-
| elsewhere | in AICUT |
|
|
30
|
-
|---|---|
|
|
31
|
-
| composition, timeline, project file | `film.html`; tracks and clips inside it |
|
|
32
|
-
| a scene, a sequence, a slide | a page (`pages/<name>.html`) cut onto a track |
|
|
33
|
-
| `useCurrentFrame()`, `interpolate()` | `frame(t)` — the picture depends only on `t`, never on state or `Date.now()` |
|
|
34
|
-
| a still, a screengrab | `aicut look <t>` |
|
|
35
|
-
| `render` / `build` / `export` | `aicut render` (the person can also export from Studio) |
|
|
36
|
-
| a dev server, a preview window | `aicut open` and the Studio address it prints |
|
|
37
|
-
|
|
38
|
-
Hard rules that hold whatever the method says: the picture depends only on `t`; every value in the person's prompt is
|
|
39
|
-
binding; look at the frames `look` writes before saying a film is done.
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
**Author:** nyx研究所 · [GitHub](https://github.com/znyupup) · [B站 @nyx研究所](https://space.bilibili.com/4330525) · 小红书 @nyx研究所 · [X @znyupup_music](https://x.com/znyupup_music)
|
|
43
|
-
|
|
44
|
-
> 把一堆手机拍的旅行素材,用AI自动剪成一个完整vlog。
|
|
45
|
-
> 最小依赖:ffmpeg + Python(whisper或FunASR+Pillow) + 视觉API。系统级只装ffmpeg,其余pip装。
|
|
46
|
-
|
|
47
|
-
## 触发条件
|
|
48
|
-
|
|
49
|
-
- 用户有一批旅行/日常视频素材,想自动剪成vlog
|
|
50
|
-
- 用户说"帮我剪个视频"、"自动剪辑"、"vlog剪辑"
|
|
51
|
-
|
|
52
|
-
## 前置要求
|
|
53
|
-
|
|
54
|
-
### 1. 系统工具
|
|
55
|
-
|
|
56
|
-
| 工具 | 用途 | 安装 |
|
|
57
|
-
|------|------|------|
|
|
58
|
-
| ffmpeg | 视频裁剪/编码/拼接/抽帧/音量检测 | `brew install ffmpeg` (macOS) / `apt install ffmpeg` (Linux) |
|
|
59
|
-
| Python 3.9+ | 脚本胶水 | macOS/Linux 系统自带 |
|
|
60
|
-
|
|
61
|
-
### 2. Python依赖(先检测,已有则跳过)
|
|
62
|
-
|
|
63
|
-
**先检测系统是否已安装所需包,不要无脑创建 venv:**
|
|
64
|
-
|
|
65
|
-
# 检测 whisper
|
|
66
|
-
python3 -c "import whisper; print('✅ whisper已安装:', whisper.__file__)"
|
|
67
|
-
|
|
68
|
-
# 检测 Pillow
|
|
69
|
-
python3 -c "from PIL import Image; print('✅ Pillow已安装')"
|
|
70
|
-
```
|
|
71
|
-
**⚠ 重要:不要用 `2>/dev/null` 吃掉错误!要看到实际报错才能判断是真没装还是PATH问题。**
|
|
72
|
-
|
|
73
|
-
**⚠ macOS 注意:** 检查系统已安装的包再决定是否需要 venv。如果系统 python3 已经能 `import whisper` 和 `from PIL import Image`,直接用就行,不要盲目创建 venv 导致找不到已有的包。
|
|
74
|
-
|
|
75
|
-
**仅在检测不通过时才安装:**
|
|
76
|
-
```
|
|
77
|
-
|
|
78
|
-
# 方案A: 直接装到用户环境(推荐)
|
|
79
|
-
pip install openai-whisper Pillow
|
|
80
|
-
|
|
81
|
-
# 方案B: 如果用户环境有冲突,再用 venv
|
|
82
|
-
python3 -m venv .venv && source .venv/bin/activate
|
|
83
|
-
pip install openai-whisper Pillow
|
|
84
|
-
```
|
|
85
|
-
**⚠ 不要每个项目都新建 venv 重装一遍!whisper模型文件1.4GB,pip install也要几分钟。**
|
|
86
|
-
|
|
87
|
-
**⚠ ASR引擎二选一:Whisper 或 FunASR**
|
|
88
|
-
|
|
89
|
-
本工作流支持两个ASR引擎,优先用 whisper,whisper 装不上就用 FunASR:
|
|
90
|
-
|
|
91
|
-
| | Whisper (OpenAI) | FunASR (阿里达摩院) |
|
|
92
|
-
|---|---|---|
|
|
93
|
-
| 安装 | `pip install openai-whisper` | `pip install funasr modelscope torchaudio` |
|
|
94
|
-
| 模型 | medium (1.4GB, 从GitHub下载) | paraformer-zh (1.05GB, 从ModelScope下载) |
|
|
95
|
-
| 附加模型 | 无 | VAD模型 + 标点模型 (首次运行自动下载, 共~50MB) |
|
|
96
|
-
| 中文效果 | 好 | 好(与whisper medium相当,细节略多) |
|
|
97
|
-
| 速度 | 14s音频 ≈ 5-10s (CPU) | 14s音频 ≈ 1.9s (CPU, RTF=0.132) ⚡ |
|
|
98
|
-
| 时间戳粒度 | 句级别 (每句话一个start/end) | 字级别 (每个字一个时间戳) |
|
|
99
|
-
| 模型下载源 | GitHub (国内不稳定,容易失败) | ModelScope (国内极快,~15MB/s) |
|
|
100
|
-
| 隐性依赖 | torch | torch + torchaudio (⚠ 必须额外装) |
|
|
101
|
-
|
|
102
|
-
**检测已安装的ASR引擎:**
|
|
103
|
-
```
|
|
104
|
-
```bash
|
|
105
|
-
python3 -c "import whisper; print('✅ whisper可用')" 2>/dev/null \
|
|
106
|
-
|| python3 -c "from funasr import AutoModel; print('✅ funasr可用')" 2>/dev/null \
|
|
107
|
-
|| echo "❌ 没有可用的ASR引擎,需要安装一个"
|
|
108
|
-
```
|
|
109
|
-
```
|
|
110
|
-
**⚠ FunASR 安装注意事项:**
|
|
111
|
-
- 必须装 torchaudio!`pip install funasr modelscope` 不会自动装 torchaudio,import 时会报 `No module named 'torchaudio'`
|
|
112
|
-
- 正确安装命令:`pip install funasr modelscope torchaudio`
|
|
113
|
-
- 首次运行会自动从 ModelScope 下载3个模型(ASR + VAD + 标点),总共约1.1GB,国内速度快
|
|
114
|
-
- 模型缓存在 `~/.cache/modelscope/hub/models/iic/` 目录下
|
|
115
|
-
- import 时会有 urllib3 的 SSL 警告(NotOpenSSLWarning),可忽略,不影响功能
|
|
116
|
-
|
|
117
|
-
**标题卡方案自动选择:**
|
|
118
|
-
```
|
|
119
|
-
|
|
120
|
-
# 有drawtext → 直接用ffmpeg,不需要Pillow
|
|
121
|
-
|
|
122
|
-
# 没有 → 用Pillow生成透明PNG再overlay(macOS brew ffmpeg通常没编freetype)
|
|
123
|
-
```
|
|
124
|
-
**可选(参考分析阶段用):**
|
|
125
|
-
```
|
|
126
|
-
```bash
|
|
127
|
-
which yt-dlp && echo "✅ yt-dlp已安装" || pip install yt-dlp
|
|
128
|
-
python3 -c "import scenedetect" 2>/dev/null && echo "✅ scenedetect已安装" || pip install scenedetect
|
|
129
|
-
```
|
|
130
|
-
|
|
131
|
-
### 3. 视觉理解模型(API)
|
|
132
|
-
|
|
133
|
-
需要一个能理解图像内容的视觉模型API,用于分析素材画面。
|
|
134
|
-
|
|
135
|
-
**要求:**
|
|
136
|
-
- 支持 OpenAI Chat Completions 格式(messages + image_url)
|
|
137
|
-
- 支持 base64 图片输入(本地素材抽帧后编码上传)
|
|
138
|
-
- 中文理解能力(需要描述画面内容、标注镜头类型等)
|
|
139
|
-
|
|
140
|
-
**推荐模型:**
|
|
141
|
-
|
|
142
|
-
| 模型 | 费用 | 说明 |
|
|
143
|
-
|------|------|------|
|
|
144
|
-
| 智谱 GLM-4.6V-Flash | 免费 | 注册 https://open.bigmodel.cn 即用,中文理解好 |
|
|
145
|
-
| GPT-4o | 付费 | 效果最好 |
|
|
146
|
-
| Qwen-VL | 付费 | 阿里云,中文好 |
|
|
147
|
-
|
|
148
|
-
**调用示例:**
|
|
149
|
-
|
|
150
|
-
```python
|
|
151
|
-
import base64, json, urllib.request
|
|
152
|
-
|
|
153
|
-
API_URL = 'YOUR_VISION_API_ENDPOINT' # 替换为你的视觉模型端点
|
|
154
|
-
API_KEY='***' # 替换为你的API Key
|
|
155
|
-
MODEL = 'YOUR_MODEL_NAME' # 替换为你的模型名
|
|
156
|
-
|
|
157
|
-
with open('frame.jpg', 'rb') as f:
|
|
158
|
-
img_b64 = base64.b64encode(f.read()).decode()
|
|
159
|
-
|
|
160
|
-
payload = {
|
|
161
|
-
'model': MODEL,
|
|
162
|
-
'messages': [{'role': 'user', 'content': [
|
|
163
|
-
{'type': 'image_url', 'image_url': {'url': f'data:image/jpeg;base64,{img_b64}'}},
|
|
164
|
-
{'type': 'text', 'text': '简洁描述画面内容,标注:镜头类型(远/全/中/近/特写)、拍摄手法(固定/手持/移动)、画面氛围。格式:内容|类型|手法|氛围'}
|
|
165
|
-
]}],
|
|
166
|
-
'max_tokens': 200
|
|
167
|
-
}
|
|
168
|
-
|
|
169
|
-
req = urllib.request.Request(API_URL, json.dumps(payload).encode(),
|
|
170
|
-
{'Content-Type': 'application/json', 'Authorization': f'Bearer {API_KEY}'})
|
|
171
|
-
with urllib.request.urlopen(req, timeout=30) as resp:
|
|
172
|
-
result = json.loads(resp.read())
|
|
173
|
-
print(result['choices'][0]['message']['content'])
|
|
174
|
-
```
|
|
175
|
-
**⚠ 视觉API调用注意事项:**
|
|
176
|
-
- 输入格式:ffmpeg抽帧为JPEG → base64编码 → `data:image/jpeg;base64,{b64}` 放入 image_url
|
|
177
|
-
- 抽帧尺寸:不需要原始分辨率,缩到 720p 即可(节省上传带宽和token)
|
|
178
|
-
- 端点区分:有些平台视觉模型和文本模型端点不同,确认用对
|
|
179
|
-
- 限流:高峰时段容易被限流,加 retry + sleep
|
|
180
|
-
```
|
|
181
|
-
|
|
182
|
-
### 不需要的(踩过的坑)
|
|
183
|
-
|
|
184
|
-
- ❌ 剪映/CapCut — v10.4+ 项目文件加密,无法程序化操作
|
|
185
|
-
- ❌ moviepy — ffmpeg命令行已够用,多一层抽象反而不灵活
|
|
186
|
-
- ❌ capcut-cli (GitHub) — 基于明文JSON,对加密后的新版无效
|
|
187
|
-
- ❌ ImageMagick — Pillow已够用,不需要再装一个图像工具
|
|
188
|
-
|
|
189
|
-
## 工作流(7个阶段)
|
|
190
|
-
|
|
191
|
-
### 阶段1: 素材盘点
|
|
192
|
-
|
|
193
|
-
目标:了解你有什么素材。
|
|
194
|
-
|
|
195
|
-
# 批量获取素材信息
|
|
196
|
-
for f in footage/*.{MOV,mp4,MP4}; do
|
|
197
|
-
echo "=== $f ==="
|
|
198
|
-
ffprobe -v quiet -print_format json -show_format -show_streams "$f" \
|
|
199
|
-
| python3 -c "import json,sys; d=json.load(sys.stdin); \
|
|
200
|
-
s=d['streams'][0]; f=d['format']; \
|
|
201
|
-
print(f\" 时长: {float(f['duration']):.1f}s\"); \
|
|
202
|
-
print(f\" 分辨率: {s['width']}x{s['height']}\"); \
|
|
203
|
-
print(f\" 编码: {s['codec_name']}\")"
|
|
204
|
-
done
|
|
205
|
-
```
|
|
206
|
-
输出一份素材清单:数量、总时长、分辨率分布、拍摄时间范围。
|
|
207
|
-
```
|
|
208
|
-
|
|
209
|
-
### 阶段2: 参考研究(可选但强烈建议)
|
|
210
|
-
|
|
211
|
-
目标:建立"好vlog长什么样"的认知。不做这步直接剪,效果会很差。
|
|
212
|
-
|
|
213
|
-
**步骤:**
|
|
214
|
-
1. 找2-3个同类型优质vlog(B站/YouTube)
|
|
215
|
-
2. `yt-dlp` 下载720p视频 + 音频
|
|
216
|
-
3. `whisper` 转录旁白(提取叙事结构)
|
|
217
|
-
4. `scenedetect` 检测镜头切换(统计节奏)
|
|
218
|
-
5. `ffmpeg` 抽关键帧 + 视觉API分析(理解画面构成)
|
|
219
|
-
|
|
220
|
-
**已验证的规律:**
|
|
221
|
-
|
|
222
|
-
- 镜头节奏: 平均3-4秒/镜头是黄金节奏
|
|
223
|
-
- 内容配比: 美食40-45% + 风景30% + 人物15% + 日常15%
|
|
224
|
-
- 镜头类型: 近景/中景为主(60-65%),全景/远景穿插(35-40%)
|
|
225
|
-
- 叙事结构: 精彩片头 → 出发/到达 → 按地点串联 → 情感升华收尾
|
|
226
|
-
- 长短交替: 短镜头(<2s)做蒙太奇,长镜头(>8s)做叙事
|
|
227
|
-
|
|
228
|
-
**剪辑教程要点:**
|
|
229
|
-
1. 找侧重点,不要流水账
|
|
230
|
-
2. 三幕式结构: 25%悬念 + 50%发展 + 25%收尾
|
|
231
|
-
3. 精彩放片头
|
|
232
|
-
4. 情感占51%(Walter Murch六法则)
|
|
233
|
-
|
|
234
|
-
### 阶段3: 素材三维分析
|
|
235
|
-
|
|
236
|
-
目标:让AI理解每条素材的内容。每条素材做三维分析:
|
|
237
|
-
|
|
238
|
-
**a) 音频分析 — ASR转录(Whisper 或 FunASR)**
|
|
239
|
-
|
|
240
|
-
# 提取音频(16kHz单声道WAV,两个引擎通用的最佳输入格式)
|
|
241
|
-
ffmpeg -i footage/INPUT.MOV -vn -acodec pcm_s16le -ar 16000 -ac 1 /tmp/audio.wav
|
|
242
|
-
```
|
|
243
|
-
**方案1: Whisper转录(优先使用)**
|
|
244
|
-
```
|
|
245
|
-
```python
|
|
246
|
-
import whisper, json
|
|
247
|
-
model = whisper.load_model('medium')
|
|
248
|
-
result = model.transcribe('/tmp/audio.wav', language='zh')
|
|
249
|
-
segments = [{"start": s['start'], "end": s['end'], "text": s['text']} for s in result['segments']]
|
|
250
|
-
|
|
251
|
-
# 输出: [{"start": 0.5, "end": 2.3, "text": "我们现在在中央大街"}, ...]
|
|
252
|
-
```
|
|
253
|
-
**方案2: FunASR转录(Whisper装不上时的替代)**
|
|
254
|
-
```
|
|
255
|
-
```python
|
|
256
|
-
import warnings
|
|
257
|
-
warnings.filterwarnings("ignore")
|
|
258
|
-
from funasr import AutoModel
|
|
259
|
-
|
|
260
|
-
model = AutoModel(
|
|
261
|
-
model="paraformer-zh", # Paraformer-large,中文ASR主模型(1.05GB)
|
|
262
|
-
vad_model="fsmn-vad", # 语音活动检测,自动切分静音段
|
|
263
|
-
punc_model="ct-punc", # 自动加标点
|
|
264
|
-
log_level="ERROR",
|
|
265
|
-
disable_update=True # 跳过版本检查,加快启动
|
|
266
|
-
)
|
|
267
|
-
|
|
268
|
-
result = model.generate(input="/tmp/audio.wav")
|
|
269
|
-
text = result[0]["text"] # 完整识别文本(已加标点)
|
|
270
|
-
timestamps = result[0].get("timestamp", []) # 字级别时间戳 [[start_ms, end_ms], ...]
|
|
271
|
-
|
|
272
|
-
# ⚠ FunASR时间戳是字级别(毫秒),需要聚合成句级别才能和whisper格式统一
|
|
273
|
-
|
|
274
|
-
# 聚合策略:按标点符号(。!?,)切分成句子
|
|
275
|
-
segments = []
|
|
276
|
-
if timestamps and text:
|
|
277
|
-
puncs = set("。!?,,.!?")
|
|
278
|
-
current_start = timestamps[0][0] / 1000.0
|
|
279
|
-
current_text = ""
|
|
280
|
-
chars = list(text)
|
|
281
|
-
for i, (char, ts) in enumerate(zip(chars, timestamps)):
|
|
282
|
-
current_text += char
|
|
283
|
-
if char in puncs or i == len(chars) - 1:
|
|
284
|
-
segments.append({
|
|
285
|
-
"start": round(current_start, 1),
|
|
286
|
-
"end": round(ts[1] / 1000.0, 1),
|
|
287
|
-
"text": current_text.strip()
|
|
288
|
-
})
|
|
289
|
-
if i < len(chars) - 1:
|
|
290
|
-
current_start = timestamps[i + 1][0] / 1000.0
|
|
291
|
-
current_text = ""
|
|
292
|
-
|
|
293
|
-
# 输出格式与whisper一致: [{"start": 0.6, "end": 2.9, "text": "我们现在在中央大街的入口,"}, ...]
|
|
294
|
-
```
|
|
295
|
-
**⚠ FunASR 输出差异注意:**
|
|
296
|
-
- FunASR 返回的是完整文本 + 字级别时间戳,不像 whisper 直接给句级别 segments
|
|
297
|
-
- 上面的聚合代码把字级别时间戳按标点切分成句子,输出格式与 whisper 对齐
|
|
298
|
-
- 如果素材没有语音,FunASR 返回空文本 `""`,timestamps 为空 `[]`
|
|
299
|
-
- FunASR 速度比 whisper 快 3-5x(14s音频只需1.9s),批量处理时优势明显
|
|
300
|
-
|
|
301
|
-
**b) 音量检测 — ffmpeg**
|
|
302
|
-
```
|
|
303
|
-
|
|
304
|
-
# mean_volume: 平均音量(dB) max_volume: 峰值音量(dB)
|
|
305
|
-
|
|
306
|
-
# mean < -40dB 基本无声 mean > -20dB 有明显声音/语音
|
|
307
|
-
```
|
|
308
|
-
**c) 视觉分析 — ffmpeg抽帧 + 视觉理解模型**
|
|
309
|
-
```
|
|
310
|
-
|
|
311
|
-
# 抽帧策略(按时长分段)
|
|
312
|
-
|
|
313
|
-
# ≤20s → 3帧(首/中/尾)
|
|
314
|
-
|
|
315
|
-
# 20-60s → 5帧
|
|
316
|
-
|
|
317
|
-
# >60s → 每15s一帧
|
|
318
|
-
|
|
319
|
-
# 抽首/中/尾三帧示例(缩到720p节省带宽)
|
|
320
|
-
ffmpeg -i footage/INPUT.MOV -vf "select=eq(n\,0),scale=1280:-1" -frames:v 1 -q:v 2 frame_start.jpg
|
|
321
|
-
ffmpeg -i footage/INPUT.MOV -vf "select=eq(n\,MIDDLE),scale=1280:-1" -frames:v 1 -q:v 2 frame_mid.jpg
|
|
322
|
-
ffmpeg -i footage/INPUT.MOV -vf "reverse,scale=1280:-1" -frames:v 1 -q:v 2 frame_end.jpg
|
|
323
|
-
```
|
|
324
|
-
**d) 输出格式**(每条素材一个JSON)
|
|
325
|
-
```
|
|
326
|
-
```json
|
|
327
|
-
{
|
|
328
|
-
"filename": "clip_001.MOV",
|
|
329
|
-
"duration": 15.3,
|
|
330
|
-
"resolution": "1920x1080",
|
|
331
|
-
"visual": [
|
|
332
|
-
{"time": "0:00", "description": "...", "shot_type": "近景", "camera": "手持", "mood": "温馨"}
|
|
333
|
-
],
|
|
334
|
-
"audio": {
|
|
335
|
-
"has_speech": true,
|
|
336
|
-
"mean_volume_db": -20.5,
|
|
337
|
-
"max_volume_db": -3.2,
|
|
338
|
-
"transcript": [{"start": 0.5, "end": 2.3, "text": "..."}]
|
|
339
|
-
}
|
|
340
|
-
}
|
|
341
|
-
|
|
342
|
-
### 阶段3.5: 素材精修预处理
|
|
343
|
-
|
|
344
|
-
目标:在给LLM之前,自动标注每条素材的"推荐有效区间",让LLM专注叙事编排。
|
|
345
|
-
|
|
346
|
-
**为什么需要这步:**
|
|
347
|
-
原始手机素材普遍存在:开头录制口令、同一句话重复多遍、前1-2s举手机晃动、说完话后拖很长的无意义画面。如果把这些原始数据直接给LLM,LLM输出的plan还需要逐条修补。
|
|
348
|
-
|
|
349
|
-
**预处理做四件事:**
|
|
350
|
-
|
|
351
|
-
#### a) 录制口令检测
|
|
352
|
-
|
|
353
|
-
```python
|
|
354
|
-
RECORDING_CUES = [
|
|
355
|
-
"开始了", "好了开始", "开始录了", "好了 开始",
|
|
356
|
-
"走了", "好了", "来了", # 仅在前3s内出现时算口令
|
|
357
|
-
]
|
|
358
|
-
|
|
359
|
-
def detect_cues(transcript_segments, duration):
|
|
360
|
-
"""检测录制口令,返回skip zones"""
|
|
361
|
-
skip_zones = []
|
|
362
|
-
for seg in transcript_segments:
|
|
363
|
-
text = seg['text'].strip()
|
|
364
|
-
if seg['start'] < 3.0 and any(text.startswith(c) or text == c for c in RECORDING_CUES):
|
|
365
|
-
skip_zones.append({
|
|
366
|
-
'type': 'recording_cue',
|
|
367
|
-
'range': [seg['start'], seg['end']],
|
|
368
|
-
'text': text,
|
|
369
|
-
'action': 'skip'
|
|
370
|
-
})
|
|
371
|
-
if seg['end'] > duration - 3.0 and text in ["好了", "走了", "好了 走"]:
|
|
372
|
-
skip_zones.append({
|
|
373
|
-
'type': 'recording_cue',
|
|
374
|
-
'range': [seg['start'], seg['end']],
|
|
375
|
-
'text': text,
|
|
376
|
-
'action': 'skip'
|
|
377
|
-
})
|
|
378
|
-
return skip_zones
|
|
379
|
-
```
|
|
380
|
-
#### b) 重复语音检测
|
|
381
|
-
```
|
|
382
|
-
```python
|
|
383
|
-
from difflib import SequenceMatcher
|
|
384
|
-
|
|
385
|
-
def detect_repeats(segments, threshold=0.6):
|
|
386
|
-
"""检测重复语音,标记建议跳过的重复段"""
|
|
387
|
-
repeats = []
|
|
388
|
-
for i, a in enumerate(segments):
|
|
389
|
-
for j, b in enumerate(segments):
|
|
390
|
-
if j <= i: continue
|
|
391
|
-
ratio = SequenceMatcher(None, a['text'], b['text']).ratio()
|
|
392
|
-
if ratio >= threshold and len(a['text']) > 4:
|
|
393
|
-
skip = a if len(a['text']) <= len(b['text']) else b
|
|
394
|
-
repeats.append({
|
|
395
|
-
'type': 'repeat',
|
|
396
|
-
'range': [skip['start'], skip['end']],
|
|
397
|
-
'text': skip['text'],
|
|
398
|
-
'kept': b['text'] if skip == a else a['text'],
|
|
399
|
-
'action': 'suggest_skip'
|
|
400
|
-
})
|
|
401
|
-
return repeats
|
|
402
|
-
```
|
|
403
|
-
#### c) 起手晃动 / 结尾拖拽检测
|
|
404
|
-
```
|
|
405
|
-
```python
|
|
406
|
-
def detect_trim_points(segments, duration, mean_volume_db):
|
|
407
|
-
"""基于语音+音量推荐起止点"""
|
|
408
|
-
suggested_start = 0.0
|
|
409
|
-
suggested_end = duration
|
|
410
|
-
|
|
411
|
-
if segments:
|
|
412
|
-
first_speech = segments[0]['start']
|
|
413
|
-
last_speech_end = segments[-1]['end']
|
|
414
|
-
if first_speech > 2.0:
|
|
415
|
-
suggested_start = max(0, first_speech - 0.5)
|
|
416
|
-
if duration - last_speech_end > 3.0:
|
|
417
|
-
suggested_end = last_speech_end + 1.5
|
|
418
|
-
else:
|
|
419
|
-
if duration > 5.0:
|
|
420
|
-
suggested_start = 1.0
|
|
421
|
-
|
|
422
|
-
return suggested_start, suggested_end
|
|
423
|
-
```
|
|
424
|
-
#### d) 纯画面时长限制
|
|
425
|
-
|
|
426
|
-
| 模式 | 纯画面上限 | 口令处理 | 重复处理 | 起手晃动 |
|
|
427
|
-
|----------|-----------|---------|---------------|---------|
|
|
428
|
-
| strict | 8-10s | 全部去除 | 只留1遍 | 去1.5s |
|
|
429
|
-
| normal | 12-15s | 去除明确口令 | 去明显重复 | 去1.0s |
|
|
430
|
-
| loose | 20-25s | 仅去"开始了" | 保留大部分 | 去0.5s |
|
|
431
|
-
|
|
432
|
-
#### e) 输出格式
|
|
433
|
-
|
|
434
|
-
预处理结果追加到素材分析数据里:
|
|
435
|
-
```
|
|
436
|
-
```
|
|
437
|
-
━━━ clip_012.mp4 | 时长25.8s | 1920x1080 ━━━
|
|
438
|
-
【画面】...
|
|
439
|
-
【语音】...
|
|
440
|
-
【精修建议】模式: normal
|
|
441
|
-
原始区间: [0.0 - 25.8]
|
|
442
|
-
推荐区间: [2.4 - 25.8]
|
|
443
|
-
⊘ [0.0-2.4] 跳过: 录制口令 "开始了"
|
|
444
|
-
有效语音: [2.62-25.8]
|
|
445
|
-
```
|
|
446
|
-
```
|
|
447
|
-
**⚠ 重要原则:预处理只做标注和建议,不做硬裁剪。LLM保留最终决定权。**
|
|
448
|
-
```
|
|
449
|
-
|
|
450
|
-
### 阶段4: LLM叙事编排
|
|
451
|
-
|
|
452
|
-
目标:把预处理后的素材数据交给LLM,生成剪辑方案。
|
|
453
|
-
|
|
454
|
-
输入:素材分析 + 精修建议(推荐区间) + 参考研究结论
|
|
455
|
-
输出:剪辑方案JSON(结构见下方schema)
|
|
456
|
-
|
|
457
|
-
#### edit_plan JSON Schema
|
|
458
|
-
|
|
459
|
-
```json
|
|
460
|
-
{
|
|
461
|
-
"title": "视频标题",
|
|
462
|
-
"structure": [
|
|
463
|
-
{
|
|
464
|
-
"section": "段落名 — 副标题",
|
|
465
|
-
"description": "本段落内容概述",
|
|
466
|
-
"clips": [
|
|
467
|
-
{
|
|
468
|
-
"file": "素材文件名.mp4",
|
|
469
|
-
"start": 0.0,
|
|
470
|
-
"end": 12.0,
|
|
471
|
-
"note": "画面内容简述",
|
|
472
|
-
"subtitle": "保留的语音文字"
|
|
473
|
-
}
|
|
474
|
-
]
|
|
475
|
-
}
|
|
476
|
-
],
|
|
477
|
-
"bgm_suggestion": "BGM风格建议(含genre/mood/instruments/tempo/bpm)",
|
|
478
|
-
"editing_notes": "整体剪辑说明"
|
|
479
|
-
}
|
|
480
|
-
```
|
|
481
|
-
**约束:**
|
|
482
|
-
- 同一素材可出现在多个clip中(不同时间区间)
|
|
483
|
-
- start/end 不能截断语音中间(阶段4.5会校验)
|
|
484
|
-
- 第一个section建议是"开篇"类引入段落
|
|
485
|
-
- 最后一个section建议是"收尾"类段落
|
|
486
|
-
|
|
487
|
-
详细prompt模板见 `templates/edit_plan_prompt.md`。
|
|
488
|
-
```
|
|
489
|
-
|
|
490
|
-
### 阶段4+ : 分镜可视化 + Dashboard(浏览器预览)
|
|
491
|
-
|
|
492
|
-
目标:把LLM输出的剪辑方案做成图文并茂的网页,方便用户直观Review。
|
|
493
|
-
|
|
494
|
-
**Dashboard 包含两个面板:**
|
|
495
|
-
|
|
496
|
-
1. **📋 素材总览** — 素材缩略图网格 + 时长/语音/音量标注 + 筛选(全部/已用/未用/含语音) + 点击查看详情
|
|
497
|
-
2. **✅ 成品质量检查** — 成品视频定时抽帧(每30秒) + 段落定位 + 点击放大
|
|
498
|
-
|
|
499
|
-
**使用 `gen_dashboard.py` 脚本:**
|
|
500
|
-
|
|
501
|
-
# 最小用法(只生成素材面板)
|
|
502
|
-
python3 scripts/gen_dashboard.py \
|
|
503
|
-
--analysis clip_analysis.json \
|
|
504
|
-
--plan edit_plan.json \
|
|
505
|
-
--footage footage/ \
|
|
506
|
-
--out output/
|
|
507
|
-
|
|
508
|
-
# 完整两面板(含成品QC帧)
|
|
509
|
-
python3 scripts/gen_dashboard.py \
|
|
510
|
-
--analysis clip_analysis.json \
|
|
511
|
-
--plan edit_plan.json \
|
|
512
|
-
--footage footage/ \
|
|
513
|
-
--video output/final.mp4 \
|
|
514
|
-
--out output/
|
|
515
|
-
```
|
|
516
|
-
**支持两种分析数据格式(自动检测):**
|
|
517
|
-
- 标准格式 `clip_analysis.json`: `{filename, duration, visual: [...], audio: {...}}`
|
|
518
|
-
- 紧凑格式 `clips_compact.json`: `{file, dur, visual: "string", speech: [...]}`
|
|
519
|
-
|
|
520
|
-
用户确认分镜方案后,再进入渲染阶段。
|
|
521
|
-
```
|
|
522
|
-
|
|
523
|
-
### 阶段4.5: 语音截断校验
|
|
524
|
-
|
|
525
|
-
目标:自动校验LLM输出的plan,确保没有把任何语音从中间截断。
|
|
526
|
-
|
|
527
|
-
```python
|
|
528
|
-
def validate_speech(plan_clips, speech_data):
|
|
529
|
-
"""检查每个clip的start/end是否截断了语音"""
|
|
530
|
-
issues = []
|
|
531
|
-
for clip in plan_clips:
|
|
532
|
-
f = clip['file']
|
|
533
|
-
cs, ce = clip['start'], clip['end']
|
|
534
|
-
if f not in speech_data: continue
|
|
535
|
-
for ss, se, txt in speech_data[f]:
|
|
536
|
-
if ss < ce and se > cs: # 语音与clip有交集
|
|
537
|
-
if ss < cs - 0.3: # 语音开始在clip之前
|
|
538
|
-
issues.append(f"截断开头: {f} clip从{cs}开始,但语音\"{txt}\"从{ss}开始")
|
|
539
|
-
if se > ce + 0.5: # 语音结束在clip之后
|
|
540
|
-
issues.append(f"截断结尾: {f} clip在{ce}结束,但语音\"{txt}\"到{se}结束")
|
|
541
|
-
return issues
|
|
542
|
-
```
|
|
543
|
-
**校验不通过时:自动修复start/end,不需要回LLM重新编排。**
|
|
544
|
-
|
|
545
|
-
#### 自动修复逻辑
|
|
546
|
-
```
|
|
547
|
-
```python
|
|
548
|
-
def fix_speech_cuts(plan, speech_data, margin=0.3):
|
|
549
|
-
"""
|
|
550
|
-
自动修复语音截断问题。直接修改plan中的start/end。
|
|
551
|
-
|
|
552
|
-
参数:
|
|
553
|
-
plan: edit_plan dict (会被原地修改)
|
|
554
|
-
speech_data: dict, {filename: [(start, end, text), ...]}
|
|
555
|
-
margin: float, 语音边界容差(秒)
|
|
556
|
-
|
|
557
|
-
返回:
|
|
558
|
-
fixes: list of str, 修复日志
|
|
559
|
-
"""
|
|
560
|
-
fixes = []
|
|
561
|
-
|
|
562
|
-
for sec in plan["structure"]:
|
|
563
|
-
for clip in sec["clips"]:
|
|
564
|
-
f = clip["file"]
|
|
565
|
-
cs = float(clip["start"])
|
|
566
|
-
ce = float(clip["end"])
|
|
567
|
-
|
|
568
|
-
if f not in speech_data:
|
|
569
|
-
continue
|
|
570
|
-
|
|
571
|
-
for ss, se, txt in speech_data[f]:
|
|
572
|
-
if ss >= ce or se <= cs:
|
|
573
|
-
continue
|
|
574
|
-
|
|
575
|
-
# 开头截断:clip.start > speech.start + margin
|
|
576
|
-
if ss < cs - margin and se > cs:
|
|
577
|
-
old_start = cs
|
|
578
|
-
new_start = max(0, ss - 0.1)
|
|
579
|
-
clip["start"] = round(new_start, 1)
|
|
580
|
-
fixes.append(
|
|
581
|
-
f" 修复开头: {f} [{old_start}→{new_start}] "
|
|
582
|
-
f"语音\"{txt[:20]}\"从{ss}s开始"
|
|
583
|
-
)
|
|
584
|
-
cs = new_start
|
|
585
|
-
|
|
586
|
-
# 结尾截断:clip.end < speech.end - margin
|
|
587
|
-
if se > ce + margin and ss < ce:
|
|
588
|
-
old_end = ce
|
|
589
|
-
new_end = se + 0.2
|
|
590
|
-
clip["end"] = round(new_end, 1)
|
|
591
|
-
fixes.append(
|
|
592
|
-
f" 修复结尾: {f} [{old_end}→{new_end}] "
|
|
593
|
-
f"语音\"{txt[:20]}\"到{se}s结束"
|
|
594
|
-
)
|
|
595
|
-
ce = new_end
|
|
596
|
-
|
|
597
|
-
return fixes
|
|
598
|
-
|
|
599
|
-
|
|
600
|
-
def validate_and_fix(plan, speech_data):
|
|
601
|
-
"""
|
|
602
|
-
端到端校验+修复入口。
|
|
603
|
-
|
|
604
|
-
用法:
|
|
605
|
-
import json
|
|
606
|
-
# 加载plan
|
|
607
|
-
plan = json.load(open('edit_plan.json'))
|
|
608
|
-
# 加载语音数据 (格式: {filename: [{start, end, text}, ...]})
|
|
609
|
-
raw = json.load(open('clip_analysis.json'))
|
|
610
|
-
speech_data = {}
|
|
611
|
-
for clip_info in raw:
|
|
612
|
-
fname = clip_info['filename']
|
|
613
|
-
if clip_info['audio']['has_speech']:
|
|
614
|
-
speech_data[fname] = [
|
|
615
|
-
(s['start'], s['end'], s['text'])
|
|
616
|
-
for s in clip_info['audio']['transcript']
|
|
617
|
-
]
|
|
618
|
-
|
|
619
|
-
# 校验
|
|
620
|
-
all_clips = [c for sec in plan['structure'] for c in sec['clips']]
|
|
621
|
-
issues = validate_speech(all_clips, speech_data)
|
|
622
|
-
print(f'发现 {len(issues)} 个截断问题')
|
|
623
|
-
|
|
624
|
-
# 修复
|
|
625
|
-
fixes = fix_speech_cuts(plan, speech_data)
|
|
626
|
-
print(f'自动修复 {len(fixes)} 处')
|
|
627
|
-
|
|
628
|
-
# 二次校验确认
|
|
629
|
-
all_clips2 = [c for sec in plan['structure'] for c in sec['clips']]
|
|
630
|
-
issues2 = validate_speech(all_clips2, speech_data)
|
|
631
|
-
assert len(issues2) == 0, f'仍有 {len(issues2)} 个问题未修复!'
|
|
632
|
-
print('✅ 二次校验通过')
|
|
633
|
-
|
|
634
|
-
# 保存修复后的plan
|
|
635
|
-
json.dump(plan, open('edit_plan_fixed.json', 'w', ensure_ascii=False), indent=2)
|
|
636
|
-
"""
|
|
637
|
-
all_clips = [c for sec in plan['structure'] for c in sec['clips']]
|
|
638
|
-
issues = validate_speech(all_clips, speech_data)
|
|
639
|
-
fixes = fix_speech_cuts(plan, speech_data)
|
|
640
|
-
return issues, fixes
|
|
641
|
-
```
|
|
642
|
-
**修复策略:**
|
|
643
|
-
|
|
644
|
-
| 截断类型 | 检测条件 | 修复方式 |
|
|
645
|
-
|----------|---------|---------|
|
|
646
|
-
| 开头截断 | clip.start > speech.start + margin | clip.start → speech.start - 0.1s |
|
|
647
|
-
| 结尾截断 | clip.end < speech.end - margin | clip.end → speech.end + 0.2s |
|
|
648
|
-
|
|
649
|
-
**边界容差 (margin=0.3s):** Whisper/FunASR 时间戳有±0.2-0.3s误差。修复后必须跑二次校验。
|
|
650
|
-
```
|
|
651
|
-
|
|
652
|
-
### 阶段5: ffmpeg自动执行
|
|
653
|
-
|
|
654
|
-
目标:把剪辑方案转成ffmpeg命令并执行。
|
|
655
|
-
|
|
656
|
-
#### 渲染策略:逐片段裁剪 → 拼接
|
|
657
|
-
|
|
658
|
-
# 单个片段裁剪+编码
|
|
659
|
-
ffmpeg -y -ss 00:00:02.400 -i footage/INPUT.mp4 -t 00:00:23.400 \
|
|
660
|
-
-vf "scale=1920:1080:force_original_aspect_ratio=decrease,pad=1920:1080:(ow-iw)/2:(oh-ih)/2,setsar=1" \
|
|
661
|
-
-r 30 -c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p \
|
|
662
|
-
-c:a aac -b:a 128k -ar 44100 -ac 2 \
|
|
663
|
-
-movflags +faststart segments/seg_001.mp4
|
|
664
|
-
|
|
665
|
-
# 拼接成品
|
|
666
|
-
ffmpeg -y -f concat -safe 0 -i concat.txt -c copy -movflags +faststart output.mp4
|
|
667
|
-
```
|
|
668
|
-
#### 变速
|
|
669
|
-
```
|
|
670
|
-
|
|
671
|
-
# 2倍速(视频+音频同步)
|
|
672
|
-
ffmpeg -i input.mp4 -filter:v "setpts=0.5*PTS" -filter:a "atempo=2.0" out.mp4
|
|
673
|
-
```
|
|
674
|
-
#### 片头高光蒙太奇
|
|
675
|
-
|
|
676
|
-
从各段落选最有视觉冲击力的镜头,快切拼接放在视频最前面。
|
|
677
|
-
|
|
678
|
-
**选片原则:**
|
|
679
|
-
- 每个主要段落选1个精彩画面
|
|
680
|
-
- 每个镜头0.5-1秒,快切节奏
|
|
681
|
-
- 总共6-10个镜头,总时长5-8秒
|
|
682
|
-
- 排除竖屏素材
|
|
683
|
-
- 不加音频(-an),最终由BGM覆盖
|
|
684
|
-
```
|
|
685
|
-
```python
|
|
686
|
-
import subprocess, os
|
|
687
|
-
|
|
688
|
-
highlights = [
|
|
689
|
-
('footage/clip_a.mp4', 1.5, 2.2),
|
|
690
|
-
('footage/clip_b.mp4', 2.0, 2.7),
|
|
691
|
-
# ... 每个0.7秒左右
|
|
692
|
-
]
|
|
693
|
-
|
|
694
|
-
for i, (f, start, end) in enumerate(highlights, 1):
|
|
695
|
-
dur = end - start
|
|
696
|
-
cmd = f'ffmpeg -y -ss {start} -i "{f}" -t {dur} ' \
|
|
697
|
-
f'-vf "scale=1920:1080:force_original_aspect_ratio=decrease,' \
|
|
698
|
-
f'pad=1920:1080:(ow-iw)/2:(oh-ih)/2" ' \
|
|
699
|
-
f'-c:v libx264 -preset ultrafast -crf 23 -pix_fmt yuv420p ' \
|
|
700
|
-
f'-an highlights/hl_{i}.mp4'
|
|
701
|
-
subprocess.run(cmd, shell=True)
|
|
702
|
-
|
|
703
|
-
# concat
|
|
704
|
-
with open('highlights/concat.txt', 'w') as f:
|
|
705
|
-
for i in range(1, len(highlights)+1):
|
|
706
|
-
f.write(f"file 'hl_{i}.mp4'\n")
|
|
707
|
-
|
|
708
|
-
subprocess.run('ffmpeg -y -f concat -safe 0 -i highlights/concat.txt '
|
|
709
|
-
'-c copy highlights/montage.mp4', shell=True)
|
|
710
|
-
```
|
|
711
|
-
#### 段落标题叠加
|
|
712
|
-
|
|
713
|
-
用 Pillow 生成透明RGBA的PNG,ffmpeg overlay到视频画面上。**不要用黑底标题卡**。
|
|
714
|
-
```
|
|
715
|
-
```python
|
|
716
|
-
from PIL import Image, ImageDraw, ImageFont, ImageFilter
|
|
717
|
-
|
|
718
|
-
W, H = 1920, 1080
|
|
719
|
-
title = "段落标题"
|
|
720
|
-
|
|
721
|
-
img = Image.new("RGBA", (W, H), (0, 0, 0, 0))
|
|
722
|
-
draw = ImageDraw.Draw(img)
|
|
723
|
-
|
|
724
|
-
# 字体:macOS用冬青黑体,Linux用Noto Sans CJK
|
|
725
|
-
|
|
726
|
-
# font = ImageFont.truetype("/System/Library/Fonts/Hiragino Sans GB.ttc", 60) # macOS
|
|
727
|
-
|
|
728
|
-
# font = ImageFont.truetype("/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc", 60) # Linux
|
|
729
|
-
font = ImageFont.truetype("YOUR_FONT_PATH", 60)
|
|
730
|
-
|
|
731
|
-
bbox = draw.textbbox((0, 0), title, font=font)
|
|
732
|
-
tw, th = bbox[2] - bbox[0], bbox[3] - bbox[1]
|
|
733
|
-
x, y = (W - tw) // 2, (H - th) // 2
|
|
734
|
-
|
|
735
|
-
# 柔和阴影
|
|
736
|
-
shadow = Image.new("RGBA", (W, H), (0, 0, 0, 0))
|
|
737
|
-
sd = ImageDraw.Draw(shadow)
|
|
738
|
-
sd.text((x+2, y+2), title, fill=(0, 0, 0, 180), font=font)
|
|
739
|
-
shadow = shadow.filter(ImageFilter.GaussianBlur(radius=6))
|
|
740
|
-
|
|
741
|
-
img = Image.alpha_composite(img, shadow)
|
|
742
|
-
draw = ImageDraw.Draw(img)
|
|
743
|
-
draw.text((x, y), title, fill=(255, 255, 255, 240), font=font)
|
|
744
|
-
img.save("title_overlay.png")
|
|
745
|
-
```
|
|
746
|
-
**overlay到视频上:**
|
|
747
|
-
```
|
|
748
|
-
|
|
749
|
-
# 标题显示前3秒
|
|
750
|
-
ffmpeg -y -i section.mp4 -i title.png \
|
|
751
|
-
-filter_complex "overlay=0:0:enable='between(t,0,3)'" \
|
|
752
|
-
-c:v libx264 -preset medium -crf 18 -pix_fmt yuv420p \
|
|
753
|
-
-c:a aac -b:a 128k -movflags +faststart \
|
|
754
|
-
section_titled.mp4
|
|
755
|
-
```
|
|
756
|
-
**⚠ overlay关键Pitfall:**
|
|
757
|
-
- ❌ 不要加 `shortest=1` — PNG只有1帧,会导致视频流立刻截断
|
|
758
|
-
- ✅ 直接用 `overlay=0:0:enable='between(t,0,3)'` 最简单可靠
|
|
759
|
-
- ✅ 先用短片段(5-8s)验证overlay效果
|
|
760
|
-
|
|
761
|
-
#### 段落拼接(推荐方案)
|
|
762
|
-
|
|
763
|
-
**✅ 正确方案:逐段编码 → concat copy**
|
|
764
|
-
```
|
|
765
|
-
```bash
|
|
766
|
-
echo "file 'final_sec_01.mp4'" > concat.txt
|
|
767
|
-
echo "file 'final_sec_02.mp4'" >> concat.txt
|
|
768
|
-
```
|
|
769
|
-
```
|
|
770
|
-
**❌ 不要用xfade链式合并:** 链式xfade会导致帧数累积丢失,后半段全黑。
|
|
771
|
-
|
|
772
|
-
**段落间过渡**:段落内硬切即可。如需渐变,每段首尾加fade比xfade更可靠。
|
|
773
|
-
|
|
774
|
-
#### BGM生成与混音(可选)
|
|
775
|
-
|
|
776
|
-
BGM 可以手动添加,也可以用 AI 音乐生成工具(如 MiniMax music、Suno 等)。
|
|
777
|
-
|
|
778
|
-
##### a) AI 生成 BGM
|
|
779
|
-
|
|
780
|
-
**风格映射参考(vlog常用):**
|
|
781
|
-
|
|
782
|
-
| Vlog 风格 | genre | mood | instruments | tempo |
|
|
783
|
-
|-----------|-------|------|-------------|-------|
|
|
784
|
-
| 轻松日常 | indie pop | cheerful, carefree | ukulele, acoustic guitar | moderate |
|
|
785
|
-
| 文艺治愈 | folk, acoustic | warm, gentle | acoustic guitar, piano, strings | slow |
|
|
786
|
-
| 美食探店 | jazz, bossa nova | cozy, playful | piano, upright bass | moderate |
|
|
787
|
-
| 冰雪/冬季 | cinematic, ambient | serene, majestic | piano, celesta, strings | slow |
|
|
788
|
-
| 热带/海岛 | tropical house | sunny, relaxed | steel drums, marimba | upbeat |
|
|
789
|
-
| 城市探索 | lo-fi hip hop | chill, urban | keys, vinyl crackle | moderate |
|
|
790
|
-
|
|
791
|
-
##### b) 混合到视频
|
|
792
|
-
```
|
|
793
|
-
|
|
794
|
-
# BGM 音量 10-15%(有语音的vlog要压低BGM)
|
|
795
|
-
ffmpeg -y -i video_no_bgm.mp4 -i bgm.m4a \
|
|
796
|
-
-filter_complex "[0:a]volume=1.0[orig];[1:a]volume=0.12[bgm];[orig][bgm]amix=inputs=2:duration=first:dropout_transition=2[aout]" \
|
|
797
|
-
-map 0:v -map "[aout]" -c:v copy -c:a aac -b:a 192k \
|
|
798
|
-
-movflags +faststart output/final.mp4
|
|
799
|
-
```
|
|
800
|
-
**BGM 音量建议:**
|
|
801
|
-
- 有大量语音/旁白 → 8-12%
|
|
802
|
-
- 语音较少,空镜为主 → 15-25%
|
|
803
|
-
- 纯空镜蒙太奇段落 → 30-40%
|
|
804
|
-
|
|
805
|
-
#### 变速
|
|
806
|
-
```
|
|
807
|
-
|
|
808
|
-
## Pitfalls
|
|
809
|
-
|
|
810
|
-
1. **剪映不可用** — v10.4+ 对 draft_info.json 加密,不要浪费时间
|
|
811
|
-
2. **视觉API端点要区分** — 有些平台视觉模型和文本模型端点不同,确认用对
|
|
812
|
-
3. **Whisper模型选择** — base中文太差,large太慢,medium是性价比最优
|
|
813
|
-
4. **不要跳过参考研究** — 没有"好vlog标准"的AI会剪出流水账
|
|
814
|
-
5. **ffmpeg编码兼容** — 拼接时注意素材编码一致性,先逐片段统一编码再concat
|
|
815
|
-
6. **视觉API限流** — 高峰时段容易限流,加retry和sleep
|
|
816
|
-
7. **预处理在LLM之前做** — 口令/重复/晃动检测在阶段3.5处理
|
|
817
|
-
8. **预处理是建议不是硬裁剪** — LLM保留覆盖权,某些口令可能有叙事价值
|
|
818
|
-
9. **语音截断必须自动校验** — LLM输出的plan可能在语音中间切断
|
|
819
|
-
10. **Whisper幻觉** — 纯音乐/环境音段落whisper会编造文字,需用音量阈值(-40dB)过滤
|
|
820
|
-
11. **竖屏混横屏** — 素材分析阶段就要检测,竖屏(9:16)混在横屏里很突兀,建议去掉
|
|
821
|
-
12. **overlay不要加shortest=1** — PNG只有1帧,shortest=1会让视频流截断
|
|
822
|
-
13. **标题卡风格** — 白字+柔和阴影叠在视频画面上,**不要黑底标题卡**
|
|
823
|
-
14. **ffmpeg drawtext不可用** — macOS Homebrew ffmpeg默认没编译freetype,用Pillow生成PNG overlay代替
|
|
824
|
-
15. **HEVC警告可忽略** — "Error constructing the frame RPS" 是HEVC解码警告,不影响输出
|
|
825
|
-
16. **Non-monotonic DTS** — concat拼接时常见的时间戳警告,播放不受影响
|
|
826
|
-
17. **空镜不宜过长** — 无语音的纯画面>6s偏长,建议压缩到5-8s
|
|
827
|
-
18. **xfade链式合并不可靠** — 链式xfade会导致帧数累积丢失,后半段全黑,用concat代替
|
|
828
|
-
19. **先用短片段验证** — 每次改渲染方案都先用5-8秒短片段验证效果
|
|
829
|
-
20. **渲染完必须验证帧数** — `ffmpeg -i output.mp4 -f null -` 检查实际frame数
|
|
830
|
-
21. **BGM别太大声** — 有语音段BGM控制在8-12%,先试听再定
|
|
831
|
-
22. **多段BGM衔接** — 保持相近的key和tempo(bpm差值<20)
|
|
832
|
-
23. **混音后必须试听** — 不同素材原始音量差异大
|
|
833
|
-
24. **不要重复安装依赖** — whisper/Pillow等先检测再装,不要每次都新建venv
|
|
834
|
-
25. **FunASR必须装torchaudio** — `pip install funasr modelscope` 不够,必须 `pip install funasr modelscope torchaudio`,否则 import 报 `No module named 'torchaudio'`
|
|
835
|
-
26. **FunASR时间戳是字级别** — 不像whisper直接给句级别segments,FunASR返回每个字的[start_ms, end_ms],需要按标点聚合成句子才能喂给后续的语音截断校验(阶段4.5)
|
|
836
|
-
27. **FunASR幻觉比whisper轻** — 纯环境音/音乐时FunASR通常返回空文本,不像whisper会编造内容。但仍需用音量阈值(-40dB)做二次确认
|
|
837
|
-
|
|
838
|
-
### 编码与拼接类(视频教程实战新增)
|
|
839
|
-
|
|
840
|
-
28. **⚠️ atempo加速后音视频时长不一致** — atempo处理后音频比视频短0.4-0.8秒/段。8段累积差好几秒,后半段音画完全对不上。**每段剪辑后必须立即验证音视频时长差<0.05s**,超过则用apad补齐:
|
|
841
|
-
|
|
842
|
-
# 验证
|
|
843
|
-
ffprobe -show_entries stream=duration -select_streams v -of csv=p=0 seg.mp4 # 视频时长
|
|
844
|
-
ffprobe -show_entries stream=duration -select_streams a -of csv=p=0 seg.mp4 # 音频时长
|
|
845
|
-
|
|
846
|
-
# 补齐
|
|
847
|
-
ffmpeg -y -i seg.mp4 -af "apad" -c:v copy -c:a aac -shortest seg_fixed.mp4
|
|
848
|
-
```
|
|
849
|
-
29. **⚠️ concat copy音频时间戳不连续** — 多段concat copy后音频咔咔响/剪映音画偏移。**正确方案:音频单独提取wav+apad补齐+concat filter拼接,视频单独concat copy,最后合并**:
|
|
850
|
-
```
|
|
851
|
-
|
|
852
|
-
# 每段提取音频(apad补齐到视频时长)
|
|
853
|
-
ffmpeg -y -i seg.mp4 -vn -af "apad" -ar 48000 -ac 2 -c:a pcm_s16le -t {视频时长} seg.wav
|
|
854
|
-
|
|
855
|
-
# concat filter拼接音频(不是demuxer)
|
|
856
|
-
ffmpeg -y -i a.wav -i b.wav -filter_complex "[0:a][1:a]concat=n=2:v=0:a=1[aout]" -map "[aout]" -c:a aac audio.m4a
|
|
857
|
-
|
|
858
|
-
# 合并
|
|
859
|
-
ffmpeg -y -i video.mp4 -i audio.m4a -c:v copy -c:a copy output.mp4
|
|
860
|
-
```
|
|
861
|
-
30. **剪映兼容编码** — 导入剪映音画不同步的修复:`-r 30 -vsync cfr`(固定帧率) + `-x264-params "bframes=0"`(无B帧) + `-ar 48000 -ac 2`(统一音频)
|
|
862
|
-
|
|
863
|
-
31. **crf值对录屏类内容要低** — 录屏文字密集,crf 22码率不够会糊。录屏用`-crf 18`或`-b:v 3M`。一般vlog素材crf 22即可
|
|
864
|
-
|
|
865
|
-
32. **多次重编码画质累积损失** — 剪辑→拼接→加背景→叠进度条,每次编码都损失画质。**尽量一次filter链搞定**,减少编码次数
|
|
866
|
-
|
|
867
|
-
33. **后台ffmpeg进程泄漏** — kill后台任务时可能只杀shell不杀ffmpeg子进程。每次kill后`ps aux | grep ffmpeg`确认,残留用`kill -9 PID`
|
|
868
|
-
|
|
869
|
-
34. **开工前第一件事确认输出分辨率** — 全流程统一分辨率不要中途改。录屏类用1080p(文字密集对分辨率敏感),vlog素材用原始分辨率或1080p
|
|
870
|
-
|
|
871
|
-
35. **⚠️ overlay视频时音频被覆盖/丢失** — 用filter_complex overlay叠加进度条/水印等视频时,ffmpeg可能自动选取overlay源(静音)的音频而不是原视频的音频。**必须用`-map`明确指定音频来源**:
|
|
872
|
-
```
|
|
873
|
-
|
|
874
|
-
# ❌ 不指定map,音频可能来自overlay源(静音)
|
|
875
|
-
ffmpeg -i main.mp4 -i overlay.mp4 -filter_complex "overlay=0:0" output.mp4
|
|
876
|
-
|
|
877
|
-
# ✅ 明确map:视频取filter输出,音频取原视频
|
|
878
|
-
ffmpeg -i main.mp4 -i overlay.mp4 \
|
|
879
|
-
-filter_complex "[0:v][1:v]overlay=0:0[vout]" \
|
|
880
|
-
-map "[vout]" -map 0:a \
|
|
881
|
-
-c:v libx264 -c:a copy output.mp4
|
|
882
|
-
```
|
|
883
|
-
如果还不行(音频编解码问题),**分步做更可靠**:
|
|
884
|
-
```
|
|
885
|
-
|
|
886
|
-
# Step1: 只处理视频(-an去掉音频)
|
|
887
|
-
ffmpeg -i main.mp4 -i overlay.mp4 -filter_complex "overlay" -map "[vout]" -an video_only.mp4
|
|
888
|
-
|
|
889
|
-
# Step2: 把原始音频合回来
|
|
890
|
-
ffmpeg -i video_only.mp4 -i main.mp4 -map 0:v -map 1:a -c:v copy -c:a copy final.mp4
|
|
891
|
-
```
|
|
892
|
-
36. **⚠️ -shortest会截断音频** — 视频和音频时长不完全一致时,`-shortest`会丢掉最后几秒的音频。**优先用`-t {精确时长}`替代**,或者确保音视频等长后不加-shortest
|
|
893
|
-
```
|
|
894
|
-
|
|
895
|
-
## 端到端示例
|
|
896
|
-
|
|
897
|
-
### 项目文件结构
|
|
898
|
-
|
|
899
|
-
```
|
|
900
|
-
my-vlog-project/
|
|
901
|
-
├── footage/ # 原始素材(用户提供)
|
|
902
|
-
│ ├── clip_001.MOV
|
|
903
|
-
│ └── ...
|
|
904
|
-
│
|
|
905
|
-
├── analysis/ # 阶段3输出
|
|
906
|
-
│ └── clip_analysis.json
|
|
907
|
-
│
|
|
908
|
-
├── edit_plan.json # 阶段4输出
|
|
909
|
-
├── edit_plan_fixed.json # 阶段4.5输出
|
|
910
|
-
│
|
|
911
|
-
├── output/
|
|
912
|
-
│ ├── dashboard.html # Dashboard网页
|
|
913
|
-
│ ├── thumbnails/ # 素材缩略图
|
|
914
|
-
│ ├── qc_frames/ # 成品QC帧
|
|
915
|
-
│ ├── segments/ # 裁剪后的片段
|
|
916
|
-
│ ├── highlights/ # 片头高光蒙太奇
|
|
917
|
-
│ ├── titles/ # 段落标题PNG
|
|
918
|
-
│ ├── sections/ # 带标题的段落视频
|
|
919
|
-
│ ├── bgm/ # BGM文件
|
|
920
|
-
│ ├── video_no_bgm.mp4 # 无BGM的完整视频
|
|
921
|
-
│ └── final.mp4 # 🎬 成品视频
|
|
922
|
-
│
|
|
923
|
-
└── reference/ # 阶段2输出(可选)
|
|
924
|
-
```
|
|
925
|
-
|
|
926
|
-
### 中间产物示例
|
|
927
|
-
|
|
928
|
-
见 `examples/` 目录下的示例文件。
|
|
929
|
-
|
|
930
|
-
### 执行流程速查
|
|
931
|
-
|
|
932
|
-
```
|
|
933
|
-
素材文件夹 footage/
|
|
934
|
-
│
|
|
935
|
-
▼
|
|
936
|
-
阶段1: 素材盘点 → ffprobe批量扫描 → 清单
|
|
937
|
-
│
|
|
938
|
-
▼
|
|
939
|
-
阶段2: 参考研究 → 下载优质vlog → 分析节奏(可选)
|
|
940
|
-
│
|
|
941
|
-
▼
|
|
942
|
-
阶段3: 素材三维分析 → whisper/FunASR+音量+视觉 → clip_analysis.json
|
|
943
|
-
│
|
|
944
|
-
▼
|
|
945
|
-
阶段3.5: 精修预处理 → 口令/重复/晃动/纯画面标注
|
|
946
|
-
│
|
|
947
|
-
▼
|
|
948
|
-
阶段4: LLM叙事编排 → edit_plan.json
|
|
949
|
-
│
|
|
950
|
-
▼
|
|
951
|
-
阶段4+: Dashboard可视化 → 浏览器预览确认
|
|
952
|
-
│
|
|
953
|
-
▼
|
|
954
|
-
阶段4.5: 语音截断校验 → 自动修复
|
|
955
|
-
│
|
|
956
|
-
▼
|
|
957
|
-
阶段5: ffmpeg渲染 → 裁剪→标题→拼接→BGM → final.mp4 🎬
|
|
958
|
-
```
|
|
959
|
-
|
|
960
|
-
## 验证
|
|
961
|
-
|
|
962
|
-
- [ ] 素材盘点完成,生成清单
|
|
963
|
-
- [ ] 参考研究完成,提取规律
|
|
964
|
-
- [ ] 素材三维分析完成(视觉+音频+音量)
|
|
965
|
-
- [ ] 素材精修预处理完成
|
|
966
|
-
- [ ] LLM剪辑方案生成
|
|
967
|
-
- [ ] 语音截断校验通过
|
|
968
|
-
- [ ] **每段片段音视频时长差<0.05s**
|
|
969
|
-
- [ ] ffmpeg执行成功,输出成品视频
|
|
970
|
-
- [ ] **成品音频完整(不被-shortest截断)**
|
|
971
|
-
- [ ] **拖到视频后半段检查音画同步**
|
|
972
|
-
- [ ] 成品视频质量人工确认
|
|
973
|
-
|
|
974
|
-
---
|
|
975
|
-
|
|
976
|
-
**Author:** nyx研究所 · [GitHub](https://github.com/znyupup) · [B站](https://space.bilibili.com/4330525) · 小红书 @nyx研究所
|
|
977
|
-
**License:** MIT
|
|
978
|
-
|
|
979
|
-
## Source
|
|
980
|
-
|
|
981
|
-
Rewritten for AICUT from [`znyupup/ai-video-editing-skill`](https://github.com/znyupup/ai-video-editing-skill)
|
|
982
|
-
(MIT), SKILL.md. The method is that skill's own; the way it runs is AICUT's.
|