Loading...
Loading...
Found 13 Skills
Generate video clips: prompt-to-video, image-to-video, reference-guided, extend, upscale, reframe; text CONTENT → -motion. Draft cheap, then hero render. Metered.
Make video and motion on Moda: short generated clips (text-to-video, image-to-video from a logo, photo, or canvas frame, reference-guided), brand stingers, animated posts and ads, logo animations, video upscaling, and vector-native motion (animated shader fills, animation-canvas exports). Use for "make a video", a GIF or mp4, an animated ad/post/banner, a motion graphic, animating a logo/image/design, or upscaling a video. moda-video owns anything that renders to mp4/gif — an animated social post is this skill for the motion (moda-social owns still sizes and formats). Still posts/carousels/banners → moda-social; slide decks → moda-deck; live sites → moda-website; edits to an existing canvas that stay still → moda-edit. Video generation is a metered lane; canvas motion authoring and mp4/gif export are not.
Vector-native motion: keyframes, animated posts/banners, logo stingers, shader fills, photo slideshows, timeline compositing. Free authoring; exports mp4/gif.
Real footage into a film: index and search local clips, upload only the selects — an editable Moda timeline + mp4 out. Highlight reel, rough cut. Local lane.
Make precise edits to an existing Moda canvas from its URL or share link — reword or restyle text, recolor, realign, resize, swap an image, add or delete a section, fix a slide someone touched in the editor. Use when the user pastes a moda.app canvas or share URL (or a cvs_ id) and asks for changes, or to revise a design a previous moda skill or Moda's AI built. Deterministic: reads canvas state, applies targeted markup/code edits, verifies with lint and screenshots. Adding or changing motion on the canvas: load moda-video.
Images as the deliverable on Moda: generate, edit, or transform — text-to-image, reference-guided, generative edit, upscale a photo, outpaint/uncrop, reframe a photo/image. Use for: "generate an image", "remove the background", "upscale this photo". NOT: imagery inside a design you're building — that format skill generates its own; animating an image → moda-video; logo design → moda-social. Metered.
Generate audio on Moda: voiceover/TTS, narration, music, jingles, sound effects — up to 10 minutes per render, delivered as a file (audio can't be placed on a canvas). Use for: voiceover, narration, "read this aloud", jingle, background music, SFX. Pairs with moda-video-clip for scored video. Metered.
Create a real, editable slide deck on Moda from a brief, a document, or the current repo. Use when the user asks for a deck, slides, a presentation, pitch deck, keynote, QBR, board update, sales/client deck, launch deck, or "turn this doc/repo/notes into slides". Produces designed pages on a Moda canvas (live URL, stays editable) and exports native PPTX with real shapes and text layers, or a text-layer PDF — not screenshots pasted into python-pptx. Animated slides or a motion version of the deck: load moda-video.
Design documents on Moda — one page or fifty: one-pager, report, brief, whitepaper, proposal, fact sheet, handout, infographic; US-Letter/A4 pages on a live canvas, exported as a real PDF with selectable text. Use for: PDF (any page count), newsletter, "make this markdown/README look designed". NOT: print pieces (poster, flyer, menu, resume, cards) → moda-document-print; slides → moda-deck; animated/motion → moda-video.
Moda brand kits — fetch, create, update, apply, and audit designs against them. Use for: brand kit, on-brand, brand colors/fonts/logo, "use our brand", "match our site", rebrand. Create from a website URL OR manual tokens — one source, never both. Kits, not renders: the artifact skill leads and pulls the kit — a brand-led "make a video" → moda-video. Designing a NEW logo → moda-social.
Moda meta and routing help — not a design tool. Use for meta asks only: installing or updating Moda, authentication and org switching, "what can Moda do?", "which Moda skill or tool should handle X?", CLI troubleshooting (doctor, last-error, typed errors), automation and integration asks ("set up Moda to auto-post/sync/schedule X", connect Moda to another tool, recurring jobs — the automation part only: any artifact to author still routes to its format skill) — or when a Moda request doesn't CLEARLY fit any other moda skill (a matching format skill always wins; this is the none-fit catcher, never a shortcut). Creating or editing designs, decks, documents, sites, graphics, videos, or diagrams is never this skill — load the format skill (moda-deck, moda-one-pager, moda-social, moda-diagram, moda-website, moda-video, moda-brand, moda-edit).
Instagram creative: feed posts, stories, reel covers, carousels — IG sizes and safe areas built in. Stills only; animated → moda-video.