All authors
Claude Skills by DeepKolor
github.com/DeepKolor16 skills13 installs225 views
- ad-creative-agentCreate product and brand advertising creatives for paid placement — social feed/story ads, display banners, web banners — with on-image ad copy (headline, CTA, brand name) and A/B variants. Use when the image will run as a paid or off-store traffic acquisition asset: a product 宣传图, banner, 广告, ad image, promotional ad, or campaign creative, with or without a named platform. Draft headline/CTA when the user omits copy. Use image-to-image when a product photo is supplied. Do not use for on-stor...Votes: 0GitHub stars: 2
- ecommerce-image-agentCreate visual concepts, ready-to-generate prompts, and AI images for ecommerce and conversion-focused product visuals: hero images, lifestyle scenes, flat lays, listing galleries, product-detail pages, store visuals, and coherent image packs. Use when the image presents a product for listing, PDP, storefront, or brand account content — on-image informational copy (卖点, specs, size charts) is in scope. Do not use for paid-placement ad creatives — feed/story/display ads, 投放 banners, or promotion...Votes: 1GitHub stars: 2
- old-photo-restorationRestore and enhance old photographs — repair scratches/creases/mold/tears, deblur faces, correct fading and yellowing, upscale quality, and naturally colorize black-and-white photos. Use when a supplied photograph is old, damaged, faded, or black-and-white and the goal is faithful recovery. Fidelity first — never swap faces, over-beautify, or alter a person's identity. Do not use for creating new stylized portraits. Do not use for ID-photo specs. Do not use for editing intact modern photos (o...Votes: 0GitHub stars: 2
- logo-creatorGenerate professional brand logos — wordmark, icon, combination mark, monogram, emblem, or abstract mark — with structured generation prompts (logo type, style, color, detail level). Supports reference-inspired original marks and iterative refinement on an approved logo. Use when the deliverable is a single logo or logo direction, not a full visual system. Do not use for multi-asset brand identity packages with VI guidelines, packaging systems, or launch kits. Do not use for mascot or charact...Votes: 0GitHub stars: 2
- virtual-try-on-agentGenerate virtual apparel try-on images from a request or supplied person and clothing references. Use when the user asks to virtually try on clothing, change an outfit, dress a person in a provided garment, replace clothing in a photo, or preview a garment on a model. Do not use for generic fashion imagery, ecommerce product placement, or product catalog visuals. Do not use for general photo edits without an outfit change (object removal, background swap, retouch, restyle).Votes: 0GitHub stars: 2
- youtube-thumbnail-agentCreate high-CTR YouTube video thumbnails (1280×720, 16:9) — creator reaction faces, object heroes, before/after splits, bold-text hooks, tutorial UI shots — with duration-badge safe zone, 3-element rule, and mobile-size readability. Use when the deliverable is a cover image for a YouTube video and the goal is click-through rate. Do not use for paid ad creatives or non-YouTube platform covers. Do not use for artistic posters, movie/book/album covers.Votes: 0GitHub stars: 2
- poster-agentCreate or restyle non-product posters and cover artwork for films, books, albums, exhibitions, conferences, community events, editorial stories, and cultural campaigns. Use when the deliverable is a single designed poster or cover with a subject, message, hierarchy, and target surface. Supports photographic, illustrated, typographic, collage, modernist, vintage, and experimental directions. Exclude product-selling visuals, paid-placement ads, video thumbnails, mascot/IP character campaigns, a...Votes: 1GitHub stars: 2
- Brand Visual System AgentCreate complete brand visual identity systems including brand strategy, logo systems, VI guidelines, color and typography systems, graphic language, marketing materials, packaging, merchandise, brand IP or mascot design, and visual extensions. Use when the deliverable is a cohesive multi-asset brand identity rather than a single image. Do not use for single conversion ads. Do not use for ecommerce product image packs. Do not use for one-off artistic posters or covers.Votes: 0GitHub stars: 2
- Id Photo AgentCreate compliant ID photos from a supplied portrait — background recolor, AI outfit change, standard size cropping, and print-sheet layout. Use when the deliverable must meet a document photo specification (standard sizes, solid-color background, passport/visa/application/headshot compliance). Do not use for styled portrait shoots, film/artistic portraits, or magazine headshots without an ID-photo spec. Do not use for dressing a person in a supplied garment image. Do not use for general backg...Votes: 0GitHub stars: 2
- Image Quality AgentUse when the user wants to create or edit a still image and the request does not match any domain-specific intent such as paid ad creative, marketplace product photo, styled portrait, ID document, poster/cover, interior design, brand identity, IP character, multi-image composite, old-photo restoration, or YouTube thumbnail. Improves vague or generic requests into concrete, model-ready prompts with deliberate composition, color harmony, lighting, lens, material, and style. Do not use for video...Votes: 0GitHub stars: 2
- Interior Design AgentInterior design and virtual staging from a user-supplied room photo — stage empty rooms, empty furnished spaces, restyle soft furnishings, preview renovation results, convert room function, and produce real-estate staging. Use when the goal is to redesign, furnish, empty, or restyle an interior space shown in a supplied photo. Locks room structure, windows/doors, camera angle, perspective, and light direction — changes only confirmed furniture, decor, surfaces, or room function. Output is a v...Votes: 0GitHub stars: 2
- Ip Design AgentOne-stop original IP character design and full-category material extension — brand mascots, hero character design, three-view turnarounds, expression/pose/costume sheets, emoji/sticker packs, scene illustrations, blind-box/figurine mockups, merchandise and campaign KVs — with a consistency-first reference workflow. Use when the deliverable centers on an original character or mascot IP, from a single design to a full asset family. Do not use for pure posters or covers without a character IP. D...Votes: 0GitHub stars: 2
- Photo Composite AgentComposite multiple user-supplied photos into one coherent image — put a person or object from photo A into photo B, build group photos from separate portraits, blend a product into a real scene, or fuse several reference images. Use when at least two supplied source images must merge into one with strict consistency across scale, occlusion, perspective, contact shadows, and light/color. Do not use for single-photo edits (removal, retouch, background swap on one image). Do not use for dressing...Votes: 0GitHub stars: 2
- Photo Editing AgentEdit user-supplied photos — remove or replace objects and bystanders, swap backgrounds (solid color, transparent-look, scene replacement), retouch skin, adjust color and lighting, convert to anime/comic styles (Ghibli, Pixar, manga, sticker presets), extend or re-crop the canvas, enhance clarity, replace text in images. Use when the goal is to modify one existing photo while preserving everything not asked to change. One main change per generation. Do not use for dressing a person in supplied...Votes: 0GitHub stars: 2
- Portrait Photo AgentCreate professional portrait photography — realistic, film, Korean, Japanese, Hong Kong retro, new Chinese style, black-and-white, and magazine/business headshots — plus identity-preserving partial restyling of user photos: hairstyle, hair color, beard, makeup, light facial retouch. Use when the deliverable is a styled portrait of a person (a new shoot, or an identity-preserving tweak of a supplied photo) with no product-selling or document-spec intent. Parses the request, completes missing d...Votes: 0GitHub stars: 2
- Video AgentUse when the user asks to create, improve, audit, or split prompts for AI video — storyboards, shot lists, director treatments, montage, camera direction, continuity, dialogue, and sound design. Can execute generation via create_video_task when the user clearly wants a video made.Votes: 0GitHub stars: 2