Agent Skills · Design & Media
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Design and media skills turn copy and images into a layout: a product page, a storyboard, a simple visual. They are useful when you already have the assets and you want HTML or a structured mock you can edit. They are harmful when they invent reviews, certifications, or before-and-after claims to fill space.
Check the output for sentences that were not in your brief. A detail-page generator that adds "customers love this" has written advertising you may not be allowed to publish. Remove those lines or remove the skill. The checklist exists for this exact surprise.
This shelf overlaps content creation. Stay here when the deliverable is layout or media, and move to content creation when the deliverable is the prose. An office skill is the better fit when the output must be a slide file in a suite you already use.
Images you upload may leave your machine if the agent's model is hosted. Product photography that is not public yet deserves the same care as source code. Read the prompt for upload, CDN, and remote font instructions. A page that hotlinks a file you thought was local will break, and it may also publish the file.
Prefer a skill that emits something you can diff and host yourself. A skill that only previews inside a vendor sandbox is a demo. Demos are fine. Do not describe them as your storefront.
Downloads on this shelf reward flashy before-and-after examples. Open the upstream page and see if the example is the product you will get or a designer mock the prompt never reproduces. If the README is only a gallery, the prompt is probably thinner than the gallery.
Host the images yourself before you share the page. A hotlinked preview that worked on your laptop will break for the customer, and it may expose a file you thought was temporary. Export, then check the network panel once.
Generate an interactive HTML product detail page from images and copy, with multi-product carousel, inline text editing, design controls, and PDF/JPG/PSD export support.
Enter a material name to get preview and download links for free, commercially usable video assets, with paid platform options, pricing, and search suggestions when results are limited.
Uses Microsoft Edge online speech synthesis to convert text to MP3 with adjustable voice, rate, pitch, and headless playback.
Plan and brief Amazon MAIN, Listing, and A+ image sets from verified product facts, then return plan and image QA status.
A design-system guidance skill for Impeccable that produces token-based rules, component states, accessibility criteria, and QA checklists.
Generate felt-craft pendant designs, part breakdowns, and structured analysis from a product image or Base64 input.
Director-level video lapian that diagnoses material precision, then produces frame evidence, director analysis, a style bible, and a showcase video.
A ComfyUI image-generation skill that uses a five-step dialog to collect prompts, prefill templates, confirm parameters, submit API jobs, and return results.
Call Mew image and design APIs in two stages to create an emotional background and compose a share-ready quote check-in poster.
Converts image sequences, videos, or screen recordings into GIFs with Python, supporting timing, looping, optimization, and quick command-line use.
Generate a 4-direction, 10-frame 2D game character sprite sheet from reference images as a transparent PNG.
Guides Suno AI style prompts, meta tags, and lyric structure to produce songwriting outputs.