development▌

Guide completion of development work by presenting clear options and handling chosen workflow.

This skill defines the mandatory conventions and behavioral rules for developing cross-platform applications with Avalonia UI and the Zafiro toolkit. These rules prioritize maintainability, correctness, and a functional-reactive approach.

This skill provides comprehensive guidelines for developing applications on Google Cloud Platform (GCP), covering serverless computing, data services, Infrastructure as Code with Terraform, and security best practices.

Patterns and practices for building games across platforms. Covers architecture, rendering, physics, AI, multiplayer, and optimization.

Build reliable webhook systems with event delivery, signature verification, retry logic, and dead-letter handling for asynchronous integrations.

Run QLTY checks during code writing to catch issues early.

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns. \n \n Provides three file ownership models (by directory, module, or layer) and enforces the cardinal rule: one owner per file to prevent merge conflicts \n Defines interface contracts as read-only coordination points between implementers, allowing shared boundaries without direct file conflicts \n Covers two integration patterns (vertical slice for independent features, ho

Create, debug, and deploy serverless cloud programs for web scraping, automation, and data processing. \n \n Supports JavaScript, TypeScript, and Python templates with integrated Crawlee, Playwright, and Cheerio libraries for HTTP and browser-based crawling \n Includes local testing via apify run with isolated storage, schema validation for inputs/outputs, and deployment to Apify platform via apify push \n Requires Apify CLI authentication and mandatory generatedBy metadata in .actor/actor.json

Event-driven automation for Claude Code plugins using prompt-based and command hooks. \n \n Supports 9 hook events (PreToolUse, PostToolUse, Stop, SubagentStop, UserPromptSubmit, SessionStart, SessionEnd, PreCompact, Notification) for validation, policy enforcement, and workflow automation \n Prompt-based hooks use LLM reasoning for context-aware decisions; command hooks execute bash scripts for deterministic checks \n Includes matchers for filtering by tool name (exact, regex, wildcard) and par

Role: Voice AI Architect