Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Media
5,297 results · page 135 of 177
- View details
cv-cnn-rnn-video-classificationSkillMedia
Extract per-frame CNN features then classify the temporal sequence with stacked GRU layers and a boolean mask for variable-length video inputs
Ready to connect★ 61
- View details
cv-cumulative-sum-channelSkillMedia
Add a cumulative sum channel along the vertical axis to capture directional structural trends in grayscale images for segmentation
Ready to connect★ 61
- View details
cv-dot-annotation-blob-diff-extractionSkillMedia
Recover (x, y, class) point labels from color-coded dot-annotation image pairs via absdiff + blackout masking + Laplacian-of-Gaussian blob detection + center-pixel RGB classification
Ready to connect★ 61
- View details
cv-embedding-knn-regressionSkillMedia
GPU-accelerated k-NN regression on CLIP image embeddings using cosine distance and inverse-distance-power weighting to predict target embedding vectors
Ready to connect★ 61
- View details
cv-frame-prediction-averagingSkillMedia
Average per-frame sigmoid predictions across sampled video frames to produce a stable video-level classification probability
Ready to connect★ 61
- View details
cv-hair-overlay-augmentationSkillMedia
Overlay real hair PNGs (masked via threshold) onto dermoscopy images to simulate body-hair occlusion as a domain-specific augmentation
Ready to connect★ 61
- View details
cv-hu-windowingSkillMedia
Apply radiological windowing to HU images — clamp to center/width range for tissue-specific visualization (lung, bone, soft tissue)
Ready to connect★ 61
- View details
cv-isotropic-resize-with-paddingSkillMedia
Resize images preserving aspect ratio then zero-pad to a square to avoid distortion artifacts in face crops or object detection inputs
Ready to connect★ 61
- View details
cv-kmeans-dominant-color-extractionSkillMedia
Extract an image's dominant RGB color via k-means over pixel-color space and emit three dense features capturing the modal color of the subject
Ready to connect★ 61
- View details
cv-laplacian-variance-blur-scoreSkillMedia
Score image sharpness with the variance of the Laplacian (Pech-Pacheco) as a single scalar feature for downstream tabular models or as a hard blur filter
Ready to connect★ 61
- View details
cv-local-contrast-enhancementSkillMedia
Subtracts a Gaussian-blurred version of the image from itself to normalize local illumination and enhance fine structural details.
Ready to connect★ 61
- View details
cv-microscope-circular-mask-augSkillMedia
Mask the corners of a dermoscopy image with a random-radius black circle to mimic the dark vignette of a dermatoscope field of view
Ready to connect★ 61
- View details
cv-mixup-label-smoothingSkillMedia
Combines mixup augmentation (linear interpolation of image pairs and their labels) with label smoothing in a single training pipeline for regularization.
Ready to connect★ 61
- View details
cv-multi-efficientnet-shared-inputSkillMedia
Combine EfficientNetB0..B6 into one Keras model with a shared image input and one sigmoid head per backbone, training all N models in a single fit() call on TPU
Ready to connect★ 61
- View details
cv-multilabel-rare-class-image-oversamplingSkillMedia
Oversample multi-label images by giving each image a duplication multiplier equal to the max per-class multiplier among its labels, so every rare class gets repetition without exploding common-class counts — the standard fix for long-tail multi-label distributions where SMOTE / per-row oversampling
Ready to connect★ 61
- View details
cv-multimodal-prediction-unionSkillMedia
Combine match predictions from image embeddings, text similarity, and perceptual hash via set union for maximum recall
Ready to connect★ 61
- View details
cv-patch-grid-count-regressionSkillMedia
Tile a large aerial image into fixed-size patches, accumulate per-class point-annotation counts into a grid tensor aligned with the tiles, and train a small CNN to regress per-class object counts per patch under MSE
Ready to connect★ 61
- View details
cv-patient-level-stratified-kfoldSkillMedia
Stratifies CV folds at the patient level rather than image level, preventing data leakage when multiple images exist per patient.
Ready to connect★ 61
- View details
cv-per-class-score-thresholdSkillMedia
Apply class-specific confidence thresholds by inferring the dominant class per image and indexing into a per-class threshold array
Ready to connect★ 61
- View details
cv-phash-duplicate-groupingSkillMedia
Group near-duplicate images by perceptual hash (pHash) as a zero-cost baseline signal for product or image matching
Ready to connect★ 61
- View details
cv-raft-optical-flow-extractionSkillMedia
Extract dense per-pixel motion fields between consecutive video frames using a pretrained RAFT model, producing an HxWx2 flow tensor that can be channel-stacked with RGB or used as a standalone motion feature for action / impact / event detection
Ready to connect★ 61
- View details
cv-raster-to-svg-polygon-conversionSkillMedia
Converts a raster image to a size-bounded SVG via K-means color quantization, contour extraction, importance-ranked polygon assembly, and progressive simplification.
Ready to connect★ 61
- View details
cv-rgby-4channel-fluorescence-loaderSkillMedia
Load fluorescence microscopy images stored as 4 separate single-channel PNGs (red microtubules, green target protein, blue nucleus, yellow ER) into a single HxWx4 tensor, preserving the biological semantics of each channel rather than collapsing to RGB
Ready to connect★ 61
- View details
cv-semi-supervised-pretrained-backboneSkillMedia
Uses Facebook's semi-weakly supervised ImageNet-pretrained models (trained on 940M unlabeled images) as CNN backbones for stronger transfer learning than standard supervised pretraining.
Ready to connect★ 61
- View details
cv-sentence-transformer-target-encodingSkillMedia
Encode text prompts into fixed-length dense vectors using SentenceTransformer for cosine-similarity evaluation in image-to-text retrieval tasks
Ready to connect★ 61
- View details
cv-separate-pos-neg-dice-trackingSkillMedia
Track dice score separately for positive (mask-present) and negative (empty-mask) images to avoid division distortion
Ready to connect★ 61
- View details
govukSkillMedia
Draft, rewrite, or audit plain-language public-service content using an independently expressed interpretation of GOV.UK content design. Use for eligibility pages, government guidance, policy explanations, forms, transactions, public notices, and content that must help people make a decision or comp
Ready to connect★ 61
- View details
infographicSkillMedia
Generate professional infographics using Nano Banana MCP (Gemini AI image generation). Follows a guided flow — analyze content, suggest visualizable concepts, propose visualization approaches, then generate on-brand images. USE THIS SKILL WHEN user says "create infographic", "make a visual", "design
Ready to connect★ 61
- View details
infographic-v2SkillMedia
Generate professional infographics using Nano Banana MCP (Gemini AI image generation). Follows a guided flow - analyze content, suggest visualizable concepts, propose visualization approaches, then generate on-brand images. USE THIS SKILL WHEN user says "create infographic v2", "make a visual v2", "
Ready to connect★ 61
- View details
instant-uiSkillMedia
Build a BenAI-branded HTML page in the neo-brutalist instant-ui design language (cream background, near-black ink, 3px hard borders, 6px zero-blur shadows, a blue/green/amber gradient stripe, system font plus SF Mono, weight-900 headings). Use for any BenAI landing page, offer, sales, or pricing pag
Ready to connect★ 61
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,764 of the 55,196 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.