Skill UI

Tests and validates ransomware recovery procedures by exercising backup restores, measuring RTO/RPO, checking sequencing, and verifying clean restores plus post-restore security hardening to ensure resilience.

Tmux is a powerful terminal multiplexer that enables users to manage multiple sessions, windows, and panes within a single terminal connection. It is essential for maintaining persistent connections on remote servers (surviving SSH disconnects), running long-term background jobs, and automating complex, multi-pane workflows directly from shell scripts, significantly enhancing remote development efficiency.

This skill intercepts the response flow before generation, allowing the user to explicitly control the desired depth, length, and token usage of the AI's answer. It estimates the complexity of the input prompt and presents multiple options (e.g., 25%, 50%, 75%, 100%), ensuring the output matches the user's need, whether they require a brief summary or a comprehensive, detailed analysis.

This skill provides interactive, periodic monitoring of deep learning training runs. It continuously checks critical metrics—such as loss trends, evaluation scores, and gradient norms—against defined baselines to detect signs of divergence, NaN values, plateaus, or general instability. It delivers a structured report and recommends whether to continue, wait, or stop the training process, ensuring computational resources are not wasted on failing models.

Run Hugging Face models directly in JavaScript/TypeScript for text, vision, and speech tasks without backend servers, using Transformers.js in Node.js or modern browsers with WebGPU, quantization, and pipeline abstractions for efficient inference.

This skill provides a comprehensive framework for validating the integrity and recoverability of critical data backups. It goes beyond simple file checks by implementing cryptographic hash verification (SHA-256), simulating automated restore tests in isolated environments, detecting silent data corruption (bit rot), and scanning for signs of ransomware artifacts. It is crucial for ensuring data reliability against cyberattacks and hardware failures, adhering to standards like NIST CSF.

This skill automates the process of renting, configuring, and managing GPU instances on vast.ai for deep learning and AI tasks. It analyzes the task requirements (VRAM, GPU count, estimated time) from the experiment plan or user input, searches for the most cost-effective and reliable GPU offers, and manages the entire resource lifecycle, ensuring efficient and economic AI training.

Viboscope helps discover compatible people for various life aspects—from cofounders and project partners to friends and romantic interests. It builds a comprehensive psychological profile across 10 validated dimensions (including Big Five, Values, and Work Style) and calculates mathematical compatibility scores, providing detailed insights into why connections are strong. Ideal for professional networking, team building, or personal relationships.

Adversarial Code Reviewer enforces three hostile personas to expose blind spots before merging, deduplicating findings, promoting shared issues, and issuing BLOCK/CONCERNS/CLEAN judgments after diff or file inspection.

Assesses AI/ML systems for prompt injection, jailbreak, model inversion, data poisoning, and agent tool abuse using MITRE ATLAS mapping, signature detection, and scoring metrics before deployment.

This skill provides programmatic access to Alpha Vantage's extensive global financial dataset. It enables the retrieval of historical and real-time data across diverse asset classes, including equities, options, forex, cryptocurrencies, commodities, and key economic indicators. Ideal for quantitative research, market trend analysis, and building financial dashboards.

Guides business leaders through capital expenditure decisions, comparing ROI, payback, NPV, IRR, and opportunity costs for equipment, hires, software, real estate, or service lines so every dollar is justified before deployment.