Skill UI

This skill allows users to manage Box cloud storage as if it were a local filesystem. It supports two modes: transparent auto-syncing via hooks (on Write/Edit) and explicit operations using the Box CLI. It provides structured workflows for document management, collaborative syncing, and reliable version control.

A comprehensive provider for integrating Eufy security cameras (supporting local P2P or cloud connectivity). This tool facilitates stable RTSP streaming for live monitoring and efficiently captures event-triggered video clips. It is designed for advanced systems that require continuous video feeds and reliable event-based data input for AI analysis and monitoring solutions.

This tool provides comprehensive integration for Reolink security cameras, supporting both RTSP streaming and HTTP API access. It allows users to discover cameras via ONVIF, capture live streams, take snapshots, and even capture motion-triggered video clips. It is ideal for developers building robust, networked surveillance or monitoring systems.

This skill provides comprehensive integration for TP-Link Tapo cameras (models like C200, C310, etc.). It supports streaming via RTSP and ONVIF protocols, allowing users to discover cameras on the network, capture motion-triggered video clips, and maintain stable live video feeds. Setup requires basic network credentials and Python environment setup.

Zero-context verification that every bibliographic entry in a paper is real, correctly attributed, and used in a context the cited paper actually supports. Catches hallucinated authors, wrong years, fabricated venues, title drift, phantom DOIs, and wrong-context citations. Run before submission after the LaTeX draft and bib file are finalized.

This guide sets up a fast, cost-effective local development loop for building applications powered by the Anthropic API (Claude). It includes instructions for hot reloading, cost-saving tips (e.g., using Haiku, token limits), and mock client implementation for robust unit testing. It supports both TypeScript/Node.js and Python environments, streamlining the AI development workflow.

Drafts patent claims for an invention based on an invention disclosure, prior art report, and novelty assessment. Supports CN, US, and EP claim formats, producing independent and dependent claims that define the legal scope of patent protection.

Builds a robust, automated workflow to export critical sales data—including forecasts, quota details, adjustments, and CRM totals—from Clari CRM to a designated data warehouse. The pipeline supports multiple targets like Snowflake, BigQuery, and PostgreSQL, ensuring that real-time revenue intelligence is available for advanced analytics and business reporting.

This bundle is designed to collect comprehensive diagnostics for CoreWeave clusters, including GPU node status, Kubernetes Pod logs, event history, and API connectivity. It aggregates critical cluster-level resource allocation and failure data into a single, actionable archive. Use it when preparing a support ticket to expedite the diagnosis of complex infrastructure issues like stuck pods, OOM errors, or resource bottlenecks.

A comprehensive tool for creating high-quality training datasets for custom object detection and segmentation models. It supports multiple advanced annotation methods including BBox drawing, SAM2 pixel-perfect segmentation, and DINOv3 visual grounding. Features include AI auto-detection, object tracking, and standardized COCO format export, streamlining the entire data pipeline from capture to training.

Search and progressively read open-access academic papers through DeepXiv. Supports layered paper access, section-level reading, trending papers, and web search. Ideal for researchers who want to avoid loading full papers too early.

This skill provides real-time monocular depth estimation using advanced models like Depth Anything v2. It transforms live camera feeds by generating colorized depth maps, enabling depth overlays and detailed scene understanding. Crucially, it supports a 'privacy mode' that anonymizes visual identities by using depth-only transformation, preserving only the spatial layout and movement patterns for secure monitoring purposes. Optimized for both CoreML on macOS and PyTorch on other platforms.