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: Dev tools
16,902 results · page 403 of 564
- View details
cv-exam-level-label-hierarchy-aggregationSkillDev tools
Aggregate per-slice predictions into exam-level labels that satisfy a competition's mutual-exclusion hierarchy (positive vs negative vs indeterminate), using a top-down rule cascade — first decide the exam class, then conditionally rescale the dependent labels so the submission stays internally cons
Ready to connect★ 61
- View details
cv-exam-sequence-padded-mask-lossSkillDev tools
Pad variable-length per-slice sequences to a fixed batch length, carry a 0/1 mask alongside, and multiply per-slice BCE by the mask before reducing — gives correct per-exam loss with batched training and zero contamination from padding tokens
Ready to connect★ 61
- View details
cv-frame-differencing-temporal-encodingSkillDev tools
Encode motion and velocity by computing per-channel pixel differences between consecutive frames instead of stacking raw frames for RL visual observations
Ready to connect★ 61
- View details
cv-frozen-batchnorm-finetuningSkillDev tools
Unfreezes backbone layers for fine-tuning while keeping BatchNorm layers frozen to preserve pretrained running statistics.
Ready to connect★ 61
- View details
cv-gaussian-sphere-target-generationSkillDev tools
Generates 3D segmentation training targets by placing Gaussian spheres at annotated point coordinates.
Ready to connect★ 61
- View details
cv-gem-poolingSkillDev tools
Replaces global average pooling with Generalized Mean (GeM) pooling, using a learnable or fixed exponent to emphasize high-activation regions.
Ready to connect★ 61
- View details
cv-gradient-accumulationSkillDev tools
Accumulates gradients over multiple mini-batches before stepping the optimizer, simulating larger effective batch sizes.
Ready to connect★ 61
- View details
cv-greedy-mask-overlap-resolutionSkillDev tools
Resolve overlapping instance masks by greedily assigning contested pixels to higher-confidence predictions using a running occupancy map
Ready to connect★ 61
- View details
cv-hungarian-matching-detection-evalSkillDev tools
Evaluates 3D object detection by matching predicted and ground-truth coordinates via the Hungarian algorithm, then computing F-beta score.
Ready to connect★ 61
- View details
cv-isotropic-voxel-resamplingSkillDev tools
Resample 3D CT volumes to uniform voxel spacing using scipy zoom, normalizing physical dimensions across scanners
Ready to connect★ 61
- View details
cv-keypoint-aware-raster-augmentationSkillDev tools
Use albumentations keypoint_params to jointly augment BEV rasters and trajectory target points so the spatial transform stays consistent
Ready to connect★ 61
- View details
cv-lateralized-label-flip-tta-disableSkillDev tools
Disable horizontal-flip augmentation (both train-time and TTA) when label columns encode left/right anatomy — flipping silently corrupts the targets because "Left ICA" must map to "Right ICA" after a flip, not stay as "Left ICA"
Ready to connect★ 61
- View details
cv-lovasz-hinge-lossSkillDev tools
Lovasz hinge loss that directly optimizes IoU for binary segmentation by computing a convex surrogate via sorted prediction errors and cumulative Jaccard gradients.
Ready to connect★ 61
- View details
cv-map-iou-precision-sweepSkillDev tools
Compute mean Average Precision by sweeping IoU thresholds from 0.5 to 0.95 on RLE-encoded instance masks using pycocotools
Ready to connect★ 61
- View details
cv-mask-to-polygon-contour-hierarchySkillDev tools
Convert binary segmentation masks to Shapely MultiPolygons using cv2 contour hierarchy to correctly handle interior holes, with Douglas-Peucker simplification
Ready to connect★ 61
- View details
cv-metadata-injection-bottleneckSkillDev tools
Inject scalar metadata (depth, position, clinical features) into U-Net bottleneck via RepeatVector and Reshape for metadata-aware segmentation
Ready to connect★ 61
- View details
cv-morphological-lung-segmentationSkillDev tools
Segment lung regions from CT using HU thresholding, connected-component labeling, and morphological opening
Ready to connect★ 61
- View details
cv-multi-annotator-bbox-consensusSkillDev tools
Merges overlapping same-class bounding boxes from multiple annotators into a consensus box using IoU-based matching and intersection.
Ready to connect★ 61
- View details
cv-multi-window-channel-stackingSkillDev tools
Stack multiple CT window settings (brain, subdural, bone) as separate RGB channels for CNN input
Ready to connect★ 61
- View details
cv-multichannel-to-rgb-adaptationSkillDev tools
Composites multi-channel imagery (microscopy, satellite) into 3-channel RGB for pretrained CNN backbones.
Ready to connect★ 61
- View details
cv-nested-unet-dense-skip-connectionsSkillDev tools
UNet++ dense cross-depth skip connections that propagate deeper decoder features into all shallower decoder levels
Ready to connect★ 61
- View details
cv-numeric-categorical-auto-detectionSkillDev tools
Auto-detect whether a generated data series is numeric or categorical by measuring the fraction of digit characters in the concatenated values
Ready to connect★ 61
- View details
cv-open-set-distance-cutoffSkillDev tools
Assign an unknown/novel class when all nearest-neighbor distances exceed a tuned cutoff threshold for open-set recognition
Ready to connect★ 61
- View details
cv-optimized-ordinal-thresholdsSkillDev tools
Uses Nelder-Mead optimization to find per-class decision thresholds that maximize Quadratic Weighted Kappa for regression-to-ordinal conversion.
Ready to connect★ 61
- View details
cv-ordinal-multilabel-encodingSkillDev tools
Encodes ordinal classes as cumulative binary labels (class N activates labels 0..N), enabling sigmoid + BCE training for ordinal regression.
Ready to connect★ 61
- View details
cv-pack-padded-sequence-lossSkillDev tools
Uses pack_padded_sequence to exclude padding tokens from cross-entropy loss in variable-length sequence generation.
Ready to connect★ 61
- View details
cv-pairwise-tracking-feature-mergeSkillDev tools
Double left-join on tracking data to create pairwise features (positions, velocities, distance) for both entities in an interaction pair
Ready to connect★ 61
- View details
cv-per-class-soft-f1-threshold-fittingSkillDev tools
Optimize per-class decision thresholds for macro-F1 by replacing the non-differentiable hard threshold with a sigmoid-sharpened soft-F1 surrogate and fitting the per-class threshold vector via least-squares — averaged over multiple random validation splits to suppress overfitting on rare classes
Ready to connect★ 61
- View details
cv-per-organ-multihead-sigmoid-softmaxSkillDev tools
Single CNN backbone with one shallow Dense neck per organ and mixed sigmoid (binary) + softmax (multi-class severity) heads, trained with a dict of losses so each organ is calibrated independently while sharing visual features
Ready to connect★ 61
- View details
cv-per-patient-slice-maxpool-aggregationSkillDev tools
Aggregate per-slice CNN predictions into a single patient-level injury score by mean-pooling across TTA copies first, then max-pooling across slices — the worst-slice wins, which matches the medical reality that one bad slice is enough to grade the patient
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.
53,789 of the 54,221 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.