Skill UI

Build content moderation applications using the Azure AI Content Safety SDK for Java. Covers text and image analysis, harm categories, severity levels, and blocklist management.

Python SDK for Azure AI Content Safety that detects harmful text and image content across hate, sexual, violence and self-harm categories, with severity scoring and custom blocklist management.

Analyze text and images for harmful content using Azure AI Content Safety REST SDK for TypeScript, with customizable blocklists and severity levels.

This guide provides comprehensive techniques for writing highly robust, production-grade Bash scripts. It covers advanced error handling, input validation, and safety best practices essential for building reliable CI/CD pipelines, system administration utilities, and mission-critical automation scripts that must handle edge cases gracefully.

This skill guides authorized security assessments and bug bounty engagements. It covers scope definition, evidence collection, impact validation, and reporting. It enforces mandatory authorization checks before testing to ensure legal compliance and safety. It helps organize the workflow for finding and reporting vulnerabilities responsibly.

An adversarial AI skill designed to hunt down bugs, logic errors, and security flaws in any codebase. Unlike standard reviews, it actively tries to break the code to ensure correctness. It covers logic errors, null safety, edge cases, security vulnerabilities, and more. Use this for deep correctness passes rather than style reviews.

Detects error propagation and chain failures in agent workflows. Identifies vulnerabilities like single-point breakdowns, unbounded retries, and unsafe data propagation to ensure system stability and safety during multi-step operations.

Expert guidance on AWS CloudFormation template optimization, nested stacks, drift detection, and production-ready patterns. Use when writing or reviewing CF templates for maintainability, cost, and safety.

This skill enables non-interactive execution of the Antigravity CLI for coding tasks. It involves setting the working directory, checking CLI availability, and running tasks via JSON output format. Users must handle authentication separately and respect permission settings. It parses JSON status fields to determine success or failure. Safety measures include avoiding interactive modes, not handling credentials, and managing file permissions within the workspace. Use this when delegating coding work to Antigravity.

This skill enables non-interactive execution of Qwen Code for coding tasks within the Code Mate environment. It involves setting the working directory, verifying tool availability, and running specific commands with JSON output format. Users should delegate coding work to Qwen Code using this method. Authentication and permissions must be configured properly, avoiding credential exposure. It supports restricted approval behavior and limits tool calls for safety.

Orchestrator skill for delegating a bounded coding task to the Command Code CLI implementer, then reviewing its diff and landing the commit yourself. Covers brief writing, dispatch, prerequisites and safety limits.

Evaluate, adapt, and safely install Context Kit personal context artifacts for Claude Code or adjacent agent workflows. Includes safety rules, installation review checklist, and best practices for local-first storage.