Skills

An auto-generated agent skill from the Aradotso trending-skills collection, derived from GitHub's trending open-source projects and installable via the skills.sh registry.

A Claude Code skill suite with 9+ sub-skills for Playwright testing, including test generation, flaky test fixing, Cypress/Selenium migration, TestRail and BrowserStack integration, and 55 ready-to-use templates.

A collection of 112 reusable agent skills for AI coding assistants, providing specialized knowledge and workflows organized by category.

Generates referring expression annotations with NVIDIA TAO Toolkit, producing natural language descriptions that identify specific objects in images for training vision-language understanding models.

Mines AOI (Automated Optical Inspection) images within NVIDIA TAO Toolkit's data pipeline, selecting and curating the most informative samples from inspection datasets for efficient model training.

Runs NVIDIA TAO Toolkit workflows on Slurm-managed HPC clusters, enabling large-scale distributed training of vision AI models across multi-node GPU environments in research and enterprise settings.

Trains Mask Auto Label models through NVIDIA TAO Toolkit, automating segmentation mask generation for vision AI datasets using pretrained models and low-code workflows.

Trains NVDINOv2 self-supervised vision models using NVIDIA TAO Toolkit, leveraging NVIDIA's optimized DINOv2 variant for feature extraction and transfer learning across vision tasks.

Trains OCRNet semantic segmentation models with NVIDIA TAO Toolkit, fine-tuning pretrained models for pixel-level scene understanding with custom data and exporting optimized models for deployment.

Trains PointPillars 3D object detection models through NVIDIA TAO Toolkit, processing LiDAR point cloud data for autonomous driving and robotics with optimized models for edge deployment.

A comprehensive security and compliance skill suite providing 10 specialized commands and 5 multi-step workflows for OWASP scanning, CVE detection, GDPR/SOC2 audits, threat modeling (STRIDE), penetration test reporting, secret detection, IAM audits, and incident response playbooks.

Capacitor agent skills for mobile app development, providing tools and workflows for building reactive mobile backends with live updates via Capgo.

Provides development skills for Subframe, a UI design tool featuring a drag-and-drop visual editor with React + Tailwind code export and AI-powered design and prototyping features.

A Claude Code skill from the engineering domain that provides structured workflows and decision frameworks for Docker container development, configuration, and deployment.

Fintech domain module within an AI-powered Rust development assistant featuring a meta-cognition framework for building financial technology applications.

A scientific resource discovery skill that provides a curated catalog of datasets, models, blog posts, and interactive Spaces across 17 scientific domains on Hugging Face, with usage patterns for datasets, transformers, and gradio_client libraries.

An open-source alternative to Claude Cowork/Codex that runs agents, skills, and MCP locally with a desktop app, and supports WhatsApp/Slack/Telegram connectors.

A POWERFUL-tier Claude Code skill that performs blast radius analysis, security scanning, and coverage delta assessment for pull request reviews with structured workflows.

A collection of Claude Code skills covering framework-specific development expertise including FastAPI, Python, and other technologies with best practices.

Part of the DuckDB Skills plugin for Claude Code, this skill reads and explores data files using DuckDB's powerful data ingestion capabilities for formats like CSV, Parquet, JSON, and more.

Trains Deformable DETR object detection models with NVIDIA TAO Toolkit, leveraging deformable attention mechanisms for efficient end-to-end detection that can be exported for production deployment.

Trains Depth Anything V2 monocular depth estimation models using NVIDIA TAO Toolkit, fine-tuning this state-of-the-art depth model with custom data for robust depth prediction across diverse scenes.

Trains Fast Foundation Stereo depth estimation models via NVIDIA TAO Toolkit, optimizing pretrained stereo vision models with custom data for real-time depth perception in edge deployments.

Trains Mask Grounding DINO models via NVIDIA TAO Toolkit, combining open-set object detection with instance segmentation to detect and segment objects from text prompts using custom training data.

Trains Mask2Former universal segmentation models using NVIDIA TAO Toolkit, supporting panoptic, instance, and semantic segmentation with a unified architecture fine-tuned on custom datasets.

Trains NVPanoptix3D panoptic segmentation models through NVIDIA TAO Toolkit, producing unified 3D scene understanding with both semantic and instance-level segmentation for autonomous systems.

A skill for training, evaluating, and deploying RT-DETR (Real-Time Detection Transformer) models for 2D object detection, with support for distillation, quantization, and AutoML-enabled training workflows.

An auto-generated agent skill for Terraform-based data engineering infrastructure, part of the Aradotso data-skills collection that scans GitHub every 30 minutes for trending data engineering repositories and creates installable agent skills.

A Sentry internal skill that removes assigned mypy typing exclusion modules in small scoped batches, fixes the typing issues, runs validation, and produces a structured completion summary.

Creates Freqtrade quantitative trading strategies using AiCoin indicators, with support for backtesting, hyperparameter optimization (hyperopt), and live bot deployment for cryptocurrency trading.