Skill UI

Run MiniMax Code non-interactively via the `mcode exec` command to delegate coding tasks. Sets the project working directory and a finite timeout, checks CLI availability, enforces read-only permissions by default, and returns the final answer. Use when the user wants MiniMax Code to analyze code or modify the workspace on request.

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.

Web and app implementation guide for Command Center UI, covering dark monitoring dashboards, NOCs, global maps, topology views, alert hierarchy, and high-stakes data visualization.

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.

This skill guides you in implementing Command Query Responsibility Segregation (CQRS) patterns for scalable software architectures. It focuses on separating read and write models to optimize query performance and support event-sourced systems. Use this when you need to scale reads independently from writes or handle complex query scenarios. It is suitable for building high-performance reporting systems where detailed read/write data models are required.

This skill serves as an alias for the pr-writer workflow, specifically designed for users requesting legacy create-pr commands. It redirects pull request creation tasks to the canonical pr-writer process, ensuring consistency in writing and updating pull requests. It is not for general git operations but focuses on PR content. Users should confirm pr-writer installation before use.

Generate production-grade Cypress E2E and component tests in JavaScript or TypeScript. Supports local execution and TestMu AI cloud for cross-browser testing. Includes patterns for command chaining, selectors, network interception, and custom commands to ensure reliable automation.

Debugging tool for Kubernetes pod failures including CrashLoopBackOff, OOMKilled, and cascade failures. Provides commands to diagnose Redis issues, resource pressure, and service restarts in the crs namespace. Includes triage workflow, log analysis, and cascade detection for production cluster troubleshooting.

This skill enables the creation of production-ready Discord bots using Discord.js for JavaScript and Pycord for Python. It covers essential features including gateway intents, slash commands, interactive components, rate limiting, and sharding strategies to ensure scalability and performance in live environments.

This skill covers the full lifecycle of Docker containers, including building optimized images, managing container lifecycles, configuring networking and volumes, and implementing security best practices. It includes troubleshooting container issues, debugging, and deploying applications efficiently in development and production environments using Docker Engine commands and best practices.

Verify an AI agent's 'done, shipped, or fixed' claims against git ground truth using the DOS kernel's dos verify and dos commit-audit commands, instead of trusting the agent's own narration or self-report.

EAS Observe is an Expo Application Services product that tracks startup, navigation, and custom-event performance from production Expo apps. It requires a development or production build and is not available in Expo Go. Users can add instrumentation to collect metrics, query data via CLI commands, and analyze dashboards to identify performance bottlenecks like slow startup or main-thread contention.