> Generate unified, on-brand Instagram Reel covers for Yuval (YUV.AI Neon Phoenix system) — the signature look is a giant Hebrew headline BEHIND the subject cutout + a punch line IN FRONT (depth effect), on rich black with a dim neural-net field, series-colored chip + phoenix mark. Use whenever Yuval asks for an Instagram/Reel/TikTok/YouTube cover, thumbnail, עטיפה, קאבר, תמבנייל, cover image for a video, or wants his Instagram grid to look consistent. One command per cover; background removal included in the pipeline.
npx skills add https://github.com/hoodini/ai-agents-skills --skill yuv-reel-covers
Unified Reel-cover system so the Instagram grid reads as ONE brand. Canvas 1080×1920, all key
content inside the 3:4 grid-crop safe zone (y 285–1635).
Reverse-engineered from the SHELLY sports-editorial + cinematic posters Yuval loves. Two new
templates in gen_cover.py: editorial (giant skewed condensed type front/behind the cutout,
✦ ticker strips, power-word stack + line icons, neon yellow #E9FF3D on vivid sky/sunset/ink) and
cinema (pink/cyan split-light duotone, white type behind the head). Auto-fits type to width,
Hebrew (Rubik 900) and English (Anton) both supported.
Includes an AI PROMPTS tab that writes Midjourney/Flux/Nano-Banana-2 prompts in the exact
style (prompts.md has the master formulas + the hybrid pipeline).
py gen_cover.py editorial --bg sky --cutout assets/yuval-cutout.png --back "STEAL MY|PROMPTS" --ticker "ALL DAY,EVERY PLAY,NO LIMITS" --stack "FOCUS,ENERGY,DISCIPLINE,VICTORY" --tag "AI" --cut-h 1060 --out my-coverbehind / stack) — legacy, still available below.#0A0A0A ground + dim neural-net field + vignette. Never white, never a raw screenshot.pink #FF1464 = news / hot takes / Claude · cyan #00E5FF = tutorials / dev · amber #F9AD45 = fun / wildlife.
behind template (the signature): giant Rubik-900 headline (1–3 words, auto-sized), one wordin the series color, partially BEHIND the subject cutout; punch line IN FRONT at chest level
(--front-top, default 1285). Cutout gets a series-color rim glow.
stack template (no photo): giant glowing Anton/Rubik stacked text + Rubik subtitle — fortool/code covers (e.g. "CLAUDE CODE / המדריך המלא").
@yuval_770 · YUV.AI bottom-center, small mono.# 0) prereqs: Node 22+, FFmpeg. Builder is pure-stdlib Python (py on Windows, python3 on Mac).
# 1) one-time per new photo — local AI background removal:
npx --yes hyperframes@latest remove-background photo.png -o assets/cutout.png
# 2) generate a cover (renders headless via HyperFrames -> PNG):
py gen_cover.py behind --img assets/cutout.png --back "קלוד דסקטופ" --front "משנה הכל!" `
--accent-back 1 --color pink --tag "CLAUDE · AI" --out my-cover
py gen_cover.py stack --back "CLAUDE CODE" --sub "המדריך המלא" --accent-back -2 --color cyan --tag DEV --out cc
Args: --accent-back N = which word of the BACK text gets the series color (-1 none, -2 all);
--size-back overrides auto-fit; --front-top moves the front line (keep at chest, never the face).
A default cutout of Yuval (studio) ships in assets/yuval-cutout.png.
--front-top if the photo differs.nothing critical above y=285 or below y=1635.
builders/fetch_hebrew_fonts.py from yuv-video-director if needed.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Take hoodini/yuv-reel-covers from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference npx.
Without those the skill loads but fails at the first command.