Skill UI

A critical safety mechanism designed to prevent destructive actions when working on or running autonomous agents in production systems. It offers multiple protective modes—Caution, Freeze, and Guard—to monitor and intercept dangerous commands (e.g., rm -rf, git push --force, or unauthorized file writes). This tool is essential for sensitive operations like migrations, deployments, or autonomous agent runs, ensuring code integrity and system stability.

A rigorous, multi-agent framework designed for high-stakes quality assurance. It mandates that an output must pass independent review from two separate, context-isolated agents before being finalized. This method is crucial for minimizing hallucination, ensuring regulatory compliance, and maintaining factual accuracy when generating content for deployment or public consumption.

A powerful tool for searching published, peer-reviewed academic literature from major venues like IEEE, ACM, and Springer. Unlike preprint archives (like ArXiv), this skill provides robust metadata, including citation counts, official publication venue details, and TLDR summaries. Use it when you need verified, finalized research papers and advanced filtering capabilities.

This tool measures whether coding agents adhere to predefined skills, rules, or operational definitions. It automatically generates multiple levels of scenario prompts (from supportive to competitive) and analyzes the full tool call timeline. By using LLMs to classify actions, it provides a detailed, self-contained compliance report and score, validating adherence even when the prompt is ambiguous.

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 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.

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.

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.

A comprehensive tool for monitoring deployed URLs to detect performance, functional, or structural regressions. It is essential to run after major deployments, PR merges, or dependency upgrades, checking metrics like HTTP status, API health, and Core Web Vitals against established baselines.

Checks AWS, Azure, and GCP configurations for IAM escalation paths, public storage exposure, open security groups, and IaC gaps, providing preventive findings with MITRE mapping for cloud posture management workflows.

Implements Cosign keyless signing with Fulcio certificates, Rekor log audit, and OIDC identity binding so container images and artifacts gain verifiable provenance within CI/CD pipelines.