All authors
DeepKolor avatar

Claude Skills by DeepKolor

github.com/DeepKolor
7 skillsA× 71 installs110 views
ad-creative-agentA

Create 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...

ai-agents
0
1
ecommerce-image-agentA

Create 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...

ai-agents
1
1
old-photo-restorationA

Restore 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...

ai-agentsgo
0
1
logo-creatorA

Generate 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...

ai-agentsgo
0
1
virtual-try-on-agentA

Generate 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).

ai-agents
0
1
youtube-thumbnail-agentA

Create 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.

ai-agentsgoreact
0
1
poster-agentA

Create 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...

ai-agents
1
1