Skill UI

Design AI agent architectures through requirements discovery, or audit and diagnose architectural flaws in existing agents. Architecture only; excludes implementation and general code review. Deliver justified decisions, verification methods, PDF reports, and visualizations.

This skill functions as a specialized Brazilian criminal lawyer, focusing on Maria da Penha law, domestic violence, femicide, and protective measures. It assists with police inquiries and criminal actions. Use it for legal queries related to Brazilian criminal justice. Do not use for general tasks or non-legal matters.

This skill covers deploying and managing Azure Virtual Machines using Azure CLI. It includes creating Linux and Windows VMs, configuring availability sets, managing managed disks, and generating custom images. It also provides guidance on selecting appropriate VM sizes for different workloads like general purpose, memory-intensive, or GPU tasks. Essential for DevOps engineers and cloud administrators working on Azure infrastructure.

CRED-OMEGA serves as an enterprise operational CISO engine for comprehensive credential and secret management. It integrates with AI coding tools to secure API keys and vaults. Use this skill for specialized security tasks involving credential governance, secret handling, and enterprise security compliance. Avoid for general assistance or when simpler tools are available.

This skill helps developers create highly focused, folder-specific documentation (`CLAUDE.md` and `AGENTS.md`). It systematically analyzes all files in a target directory to extract project purpose, operational constraints, naming conventions, and critical decisions. This deep context ensures that future AI agents (like Claude or Codex) operate with localized knowledge, preventing them from relying on global, generalized instructions and improving their accuracy in that specific domain.

This skill enables querying nutritional information, comparing food items, and performing calculations based on structured food data. It supports database retrieval, portion conversion, and classification filtering for precise nutritional analysis rather than general text suggestions.

Routes ambiguous data-observability requests to the appropriate Monte Carlo skill or workflow. Activates reactively for unclear alerts, incidents, coverage gaps, or general data quality issues, asking clarifying questions first to avoid premature tool calls.

General-purpose browser automation skill using Playwright. Auto-detects local dev servers, writes custom test scripts to /tmp, and executes them with a visible browser. Supports responsive testing, login flows, form submissions, and link checking.

General reverse-engineering methodology for compiled, obfuscated, packed, or virtualized binaries. Covers GDB, Frida, angr, Unicorn, and Qiling static/dynamic workflows across languages and platforms, with anti-analysis countermeasures and CTF patterns.