Image

layout-restore

github.com

Restore e-commerce reference images (Taobao/Tmall main & secondary images, posters, detail pages) into an EDITABLE source package — HTML + CSS + SVG, layered into photo plate / vector structure / live text — then verify it pixel-by-pixel. Use this skill when the user wants to recreate a layout or restore a reference image, turn a flat image into an editable source, batch-restore a set of reference images, measure a pass rate, or diagnose why a reconstruction's diff rate is too high. Trigger phrases include "layout restore", "pixel-accurate reconstruction", "recreate this batch", and "turn these into an editable source package". Do NOT use it for: cropping/resizing a single photo (use an image library), generating new artwork from scratch, designing vector illustrations, or scraping/crawling reference images from e-commerce platforms.

$ npx skills add 070703John-chen/layout-restore
Skill anzeigen→

openai-img-gen

github.com

Generate or edit images with OpenAI's image models. Use when the user asks to create, generate, draw or render an image, illustration, mockup, concept art, logo idea or photo, or to edit, recolour, restyle or combine existing photos or images, even if they don't mention OpenAI.

$ npx skills add kingfishx23/openai-img-gen
Skill anzeigen→

font-image-text-replace-01

github.com

Replace existing text fonts in uploaded images while preserving the original copy, placement, scale, color, effects, background, subjects, and composition. Use for font-only image edits that require a final PNG and a Photoshop PSD with native editable text layers.

$ npx skills add luccilu-77/font-replace
Skill anzeigen→

painterly-oil-style

github.com

Apply a layered oil-illustration look to an existing image, preserving composition and facial likeness with softly painted faces, painterly hair, and richer textured surroundings. Use when the user asks for this style or invokes the skill.

$ npx skills add luforevercy9/painterly-oil-style
Skill anzeigen→

codex-images

github.com

Generates images with Codex (OpenAI's coding agent and its built-in image tool, included in a ChatGPT plan) - YouTube thumbnails, covers, B-roll stills, board images, profile pictures - one Codex job per image, several in parallel, with the creator's photos as reference when the face matters, then copies them into the project with a manifest. Use when the user says generate an image, a thumbnail, a cover, make me a visual, codex images, génère une image, miniature, or when publish or short-editing needs an image.

$ npx skills add Joaslde/video-agent-skills
Skill anzeigen→

posfoxgen

github.com

Use when a user supplies a scientific paper PDF and wants a research poster image, optionally guided by a primary reference or template. This edition ends at image generation.

$ npx skills add LawrenceRiver/PosFox-Gen-skill
Skill anzeigen→

antigravity-custom-theme

github.com

Use when the user wants to design, customize, install, update, or troubleshoot an Antigravity IDE or Manager visual theme from a wallpaper image, color palette, aesthetic mood, or preset.

$ npx skills add giakiet22102006/antigravity-custom-theme-skill
Skill anzeigen→

botanical-geometric-style

github.com

Transform flower or botanical landscape images into a tactile geometric collage style while preserving the subject and overall scene.

$ npx skills add aily12138/-skill
Skill anzeigen→

shortform-kinetic-typography

github.com

Compose expressive on-screen typography for short-form videos using strong word hierarchy, mixed scale, selective accents, subject overlap, and perspective. Use for reference-led text restyling or kinetic text sequences; ordinary subtitle transcription alone does not need this skill.

$ npx skills add collinsanfo/shortform-kinetic-typography
Skill anzeigen→

image-generation

github.com

Generate or edit images through an OpenAI-compatible AI gateway. Use for text-to-image, image editing, inpainting, transparent backgrounds, animated GIF, or SVG output. Do not use for video, music, speech, or the decision model. Platform: New.bi (https://api.new.bi), a professional, stable, and reliable AI model aggregation gateway.

$ npx skills add TokenService/ai-gateway-skills
Skill anzeigen→

interactive-greeting-card

github.com

Turns a picture and a message into an interactive 3D greeting card, a folded card in WebGL whose foil or thick paint catches the light as you move, that opens to the message handwritten inside and turns over to its back, and can come alive with glowing lights, falling snow, floating hearts and parts that sway and react to a tap. Makes one self-contained HTML file that works offline and can be sent or hosted anywhere. Use it whenever someone wants a greeting card, e-card or digital card (birthday, Christmas, holiday, Valentine, Mother's Day, thank-you, wedding, anniversary, congratulations, get well), or wants to turn their own artwork, painting, illustration or photo into a card with a message inside, even if they never say interactive or 3D.

$ npx skills add annnguyentt/interactive-greeting-card-skill
Skill anzeigen→

camera-match-test

github.com

Test how closely a Nikon Z camera (Zf, Z6III, Z5II, Z50II, Z8, ZR) can match a reference look in-camera, and build a Nikon Flexible Color Picture Control (.NP3) for it — a Fujifilm JPEG/HEIF film simulation, a Lightroom profile or preset export, or a LUT'd image. It fits the NP3 against a colour chart shot by rendering NEFs headlessly through NX Studio's own engine (SaveProcess), measuring the 988-patch CMP chart, and tuning Color Blender, Color Grading, saturation and tone curve to minimise ΔE2000, then writes a versioned PICCONnn.NP3 and can copy it to the SD card. Use this whenever the user wants to match a Nikon to a Fuji, turn a look, LUT or film simulation into an in-camera Nikon profile, make a "Nikon recipe" from a reference image, or check how close a profile is in Delta E — even if they just say "make my Zf look like my X100" or "build the profile from this chart".

$ npx skills add gerard662/nikon-picture-control-matcher
Skill anzeigen→

qa-fisika-visual

github.com

Checks every AI image and video against real-world physics and rejects a shot that is physically implausible instead of polishing a broken frame.

$ npx skills add masjavas7/skill-muse-masjavas
Skill anzeigen→

create-thumbnail

github.com

Create or revise Roblox promotional thumbnails (1920 x 1080) and game icons (512 x 512) from scene prompts or visual references. Use for create.thumbnail requests, Roblox thumbnail artwork, and Roblox game icon generation.

$ npx skills add LobbyCraft/create.thumbnail
Skill anzeigen→

hyliox-pixel-perfect

github.com

Translate a UI screenshot (landing page, app screen, dashboard, mockup) into a pixel-faithful, developer-ready reconstruction prompt for AI coding agents (Cursor, v0.dev, Lovable, Codex, Claude Code) targeting Next.js 16 App Router + Tailwind + shadcn/ui + Framer Motion. Output is a long Markdown spec (~1000 lines) using a fixed 21-section template — tech stack, page direction, design tokens, Tailwind config, fonts, CSS utilities, assets, responsive rules, page structure, section breakdown, animations, visual hierarchy, layout JSON, component tree, copywriting, visual details to match, final goal. Trigger on "/hyliox-pixel-perfect", "/pixel-perfect", "fais le prompt gagnant", "transforme cette image en prompt", "rebuild this UI", "clone this design", "pixel-perfect spec", or any UI image with reconstruction intent. Multilingual chat reply, spec file in English. Do NOT use for design critique or aesthetic feedback — fidelity reconstruction only.

$ npx skills add ys-sites/video
Skill anzeigen→

chatgpt-images-for-claude

github.com

Generate or edit images with ChatGPT's image model straight from Claude Code, through the Codex CLI's built-in image_gen tool (ChatGPT sign-in, no OpenAI API key), then finish them to spec: exact pixel or print size, resolution/DPI, padding or margins, fit (contain/cover), background, upscale, and output format (PNG, JPG, WebP, TIFF, PDF). Every run is approved on a read-only HTML preview first. Use when: "generate an image", "make this in ChatGPT", "run this prompt through Codex", "create a poster/flyer/social graphic/ad image", "make a 1080x1350 version", "give me a print-ready PDF of this", "edit this photo with ChatGPT", "make 3 variations", "batch 12 images", "make a whole set of images from these prompts", or when prompts already exist and the user wants the images made instead of pasting them into the ChatGPT app. NOT for: video, or vector/logo work that belongs in SVG.

$ npx skills add intiquesoftware/chatgpt-images-for-claude
Skill anzeigen→

ascii-art

github.com

Turn any image, GIF or video into ASCII art or ASCII animation, as plain text, truecolor terminal output, HTML, PNG, GIF, WebP or MP4. Also animates still images with matrix-rain, decode, scan, glitch and wave effects. Also makes an ASCII animation from a short description such as "a running horse", using a freely licensed clip from Wikimedia Commons. Use when the user asks for ASCII art, an ASCII animation or video, a text-art version of an image, a terminal banner from a logo, or a "matrix" / retro text look.

$ npx skills add rasabaq/ascii-skill
Skill anzeigen→

screenshot-first-thumbnails

github.com

Builds finished YouTube thumbnails from real screenshots, photos and supplied characters, as cutout and overlay rather than a redrawn AI poster. Avatars, logos and pixel art stay locked. Defaults to 16:9 and keeps key art clear of the duration badge.

$ npx skills add viktorstriuk/screenshot-first-thumbnails
Skill anzeigen→

diretor-de-imagem

github.com

Directs AI image generation like a cinematographer. It interviews for use, subject, set, camera, lens, aperture, light, color and texture, then writes complete per-shot prompts for GPT Image or Gemini — product, fashion, flat-lay, lifestyle and multi-angle series — and revises one change at a time.

$ npx skills add thsjn/diretor-de-imagem
Skill anzeigen→

artifex

github.com

Make art out of code — a piece whose every mark comes from code rather than a traced reference, rendered from one source to an interactive page, a frame-exact MP4 film with its own soundtrack, a print-resolution still or a plotter-ready SVG, with checks that can actually fail. Use when asked to create generative, algorithmic or procedural art; a poster, plate, pattern, diagram-as-art, type specimen, data piece, abstract composition, illustration, creature, scene or object built out of code; an animated or growing piece, or an animated short with sound; a seeded artwork that can be re-rolled; an SVG for a pen plotter; or to debug, optimise or art-direct an existing piece. Not for chart libraries, dashboards, UI mockups, or image generation from a prompt.

$ npx skills add V-Songbird/artifex
Skill anzeigen→

nb-figure-studio

github.com

Unified scientific-figure workflow for creating, reading, auditing, revising, redesigning, and imitating data plots, multi-panel figures, vector schematics, graphical abstracts, and publication artwork. Use for 科研绘图、出图、审图、 翻修、仿图、论文配图、figure redesign, reference-style adaptation, or final-size export review. Do not use for dashboards, video, or purely statistical analysis that does not need a figure.

$ npx skills add zuoruidong/codex-skills
Skill anzeigen→

style-pack

github.com

Turns a style the user likes into a style pack — a guide, a module of functions that draw the style's marks, and a proof of each function — that another person can install and use in pieces of their own. Use when asked to package, save, share, export or publish a style, or to make a style installable. Not for drawing in a style (use the artifex skill) or for installing or trusting someone else's pack.

$ npx skills add V-Songbird/artifex
Skill anzeigen→

visualize

github.com

Use when a thought summary must become diagrams the user can see.

$ npx skills add Uniterra-Solutions/tidy-up-your-thoughts
Skill anzeigen→

etsy-pod-image-prompts

github.com

Create, revise, audit, or standardize image-generation prompts for Etsy print-on-demand product listings, including thumbnails, feature infographics, personalization guides, size/material close-ups, lifestyle scenes, and multi-panel images. Use when prompts must preserve an uploaded product reference, exact artwork, text, materials, construction, dimensions, personalization, or other product details, especially when product accuracy must override composition and styling.

$ npx skills add trevor94899234-maker/shineon-design-skills
Skill anzeigen→