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 402 of 564
- View details
Contract Risk ReviewSkillDev tools
Contract risk review: systematic identification of legal risks in contract text, risk assessment, and output of revision suggestions
Ready to connect★ 61
- View details
contract-amendmentSkillDev tools
Skill for automatically drafting a working-condition amendment agreement used when changing the terms of an existing employment contract. Includes changes to wages, workplace, job duties, and working hours, branching for fewer than 5 / 5 or more employees, and validation against the 2026 minimum wag
Ready to connect★ 61
- View details
Counterfactual ReasoningSkillDev tools
Trigger this skill when you need to assess 'how the legal outcome would differ if a certain fact/act/condition did not exist or had changed'. Typical trigger scenarios include: causation analysis (but-for causation — whether the harm would still have occurred without the act), allocation of fault an
Ready to connect★ 61
- View details
cv-3d-center-crop-zero-padSkillDev tools
Select center slices from a 3D volume and zero-pad along depth when the scan has fewer slices than the target count
Ready to connect★ 61
- View details
cv-albumentations-detection-augmentationSkillDev tools
Applies albumentations augmentations to object detection data while preserving bbox-label correspondence via BboxParams.
Ready to connect★ 61
- View details
cv-batch-all-contrastive-lossSkillDev tools
All-vs-all contrastive loss comparing every pair in a batch (N^2 pairs) with margin and compactification regularizer
Ready to connect★ 61
- View details
cv-bbox-augmentation-retry-loopSkillDev tools
Wrap albumentations bbox transforms in a 10-attempt retry loop that re-rolls the augmentation when all boxes get cropped out, preventing empty-target samples from poisoning the detection loss with NaN gradients
Ready to connect★ 61
- View details
cv-bce-dice-combined-lossSkillDev tools
Combines BCE-with-logits and soft Dice loss with configurable weights for binary and multilabel segmentation training.
Ready to connect★ 61
- View details
cv-bigru-slice-feature-aggregatorSkillDev tools
Two-stage CT classifier where a 2D CNN dumps per-slice features once, then a bidirectional GRU runs over the slice sequence to produce both per-slice predictions (TimeDistributed head) and an exam-level prediction (avg+max pooled head) — turns expensive 3D CNN training into cheap sequence modeling
Ready to connect★ 61
- View details
cv-black-slice-replacementSkillDev tools
Detect all-black DICOM/MRI slices (mean==0) and replace them by randomly sampling a non-black slice from the same series
Ready to connect★ 61
- View details
cv-brovey-pansharpeningSkillDev tools
Fuse low-resolution multispectral bands with a high-resolution panchromatic band using the Brovey transform to produce sharp multi-band imagery
Ready to connect★ 61
- View details
cv-class-balanced-epoch-undersamplingSkillDev tools
Dynamically undersample majority class each epoch with per-class keep probabilities for stochastic balance
Ready to connect★ 61
- View details
cv-classifier-gated-detection-postprocessSkillDev tools
Uses a binary classifier's probability to gate object detector outputs in three tiers: keep detections, append a no-finding box, or replace all detections.
Ready to connect★ 61
- View details
cv-cnn-encoder-spatial-feature-mapSkillDev tools
Strips the global pool and FC head from a pretrained CNN to expose spatial feature maps (H x W x C) for attention-based decoding.
Ready to connect★ 61
- View details
cv-coco-annotation-conversionSkillDev tools
Convert per-instance RLE or polygon annotations to COCO JSON format for seamless use with Detectron2 and MMDetection
Ready to connect★ 61
- View details
cv-combinatorial-deletion-point-matchingSkillDev tools
Match two unequal-length point sets by enumerating which points to drop from the longer set, searching over deletion combinations
Ready to connect★ 61
- View details
cv-concat-tile-feature-poolingSkillDev tools
Passes N tiles independently through a shared CNN backbone, concatenates their feature maps spatially, then pools for classification — a lightweight multi-instance learning approach.
Ready to connect★ 61
- View details
cv-confidence-threshold-multilabelSkillDev tools
Assigns multiple labels per sample using a confidence threshold on sigmoid outputs with a fallback negative class.
Ready to connect★ 61
- View details
cv-connected-components-centroid-extractionSkillDev tools
Extracts object centers from 3D segmentation masks using connected-component labeling and centroid computation.
Ready to connect★ 61
- View details
cv-conv1d-lstm-stroke-classifierSkillDev tools
Stack 1D convolutions for local feature extraction before bidirectional LSTMs to classify variable-length stroke sequences into hundreds of doodle categories
Ready to connect★ 61
- View details
cv-cross-view-count-consistency-filterSkillDev tools
Drop false-positive detections by requiring matched per-frame box counts across paired synchronized camera views (Endzone vs Sideline) — if both views see the same scene at the same instant, true events should appear in both
Ready to connect★ 61
- View details
cv-ct-z-stack-orientation-flipSkillDev tools
Detect inverted CT slice ordering by comparing ImagePositionPatient[2] (the Z coordinate) of the first and last DICOM slice in a series, flipping the volume along axis 0 when needed so every patient ends up in canonical head→feet order
Ready to connect★ 61
- View details
cv-deepsort-majority-vote-relabelSkillDev tools
Run DeepSort on per-frame detections then overwrite each track cluster's label with the most common mapped label across the track's lifetime
Ready to connect★ 61
- View details
cv-dice-lossSkillDev tools
Dice coefficient loss for pixel-level segmentation that directly optimizes the overlap between predicted and ground-truth masks.
Ready to connect★ 61
- View details
cv-dicom-hounsfield-normalizationSkillDev tools
Convert raw DICOM pixel arrays to Hounsfield Units using per-slice RescaleSlope/RescaleIntercept, with outside-scanner clamping
Ready to connect★ 61
- View details
cv-dicom-ipp-z-slice-sortSkillDev tools
Order DICOM slices into a coherent 3D volume by sorting on ImagePositionPatient[2] (the Z coordinate in patient space), with a filename-integer fallback for series whose tag is missing — never trust filename alphabetical order, never trust InstanceNumber
Ready to connect★ 61
- View details
cv-dicom-orientation-detectionSkillDev tools
Decodes MRI scan plane (axial, coronal, sagittal) from DICOM ImageOrientationPatient direction cosine vectors.
Ready to connect★ 61
- View details
cv-dual-view-reshape-forwardSkillDev tools
Reshape dual-view stacked channels into doubled batch dimension for shared backbone, then concatenate with tabular features for classification
Ready to connect★ 61
- View details
cv-efficientdet-headnet-swapSkillDev tools
Load EfficientDet pretrained on COCO with the original 90-class head, then swap in a fresh HeadNet with your own num_classes — keeps the BiFPN feature pyramid pretrained and only retrains the classification head, the canonical transfer-learning recipe for the effdet PyTorch port
Ready to connect★ 61
- View details
cv-epoch-prediction-averagingSkillDev tools
Collect test predictions each epoch via callback and combine with exponentially increasing weights favoring later epochs
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.