Skill UI

A Python utility to preview conservative tool-name translations and copy complete local skill bundles for manual adaptation to Google Antigravity. Supports Claude Code, Cursor, Codex, and generic agent skill directories. Ensures safe migration with dry-run modes and workspace installation.

Write, review, and refactor SwiftUI for iOS or macOS, covering data flow, view composition, performance, identity, environment, localization, animation, API migration, and Instruments traces.

A comprehensive guide detailing how to refactor large, complex SwiftUI views into smaller, more stable, and explicit components. It emphasizes adopting a lightweight state approach (favoring local state and environment variables over excessive view model layers) to improve data flow, readability, and overall code maintainability in modern iOS development.

This skill provides comprehensive testing approaches for Temporal workflows using pytest. It covers unit testing with time-skipping, integration testing with mocked activities, replay testing for determinism, and local development setup. It helps achieve high test coverage and fast feedback loops for Python-based Temporal applications.

This skill enables authorized security testing of desktop thick clients. It focuses on local storage, update channels, IPC, traffic interception, and client-side trust-boundary review. Techniques include reverse engineering, network analysis, and vulnerability assessment for C/S architectures like Electron or .NET.

Tree Ring Memory is a local-first framework for managing AI agent memory lifecycles. It enables recall, evidence recording, auditing, and forgetting without dumping transcripts. Built with Rust and SQLite, it supports scoped memory, privacy, and durable project knowledge consolidation. Ideal for developers managing AI agent projects securely.

This guide provides comprehensive patterns for optimizing Turborepo build pipelines within monorepos. It covers local and remote caching strategies, including integration with Vercel and self-hosted solutions. Use it when setting up new monorepos, improving CI/CD performance, or debugging complex build dependency issues.

Unship is a dedicated local workflow for front-end developers to compare multiple AI-generated UI alternatives (such as layouts, copy, or flows) directly within a running application environment. Instead of committing to one generated version, it adds temporary source-level variants, allowing for visual comparison. After the user selects the final version, the skill automatically cleans up all unused temporary code and attributes, ensuring a clean, production-ready codebase. Note: This tool is for local iteration only, not for production A/B testing or analytics.

Generates WebdriverIO automation tests in JavaScript or TypeScript for local or cloud environments. Supports LambdaTest integration, Page Object Model, and various test frameworks like Mocha, Jasmine, and Cucumber. Ideal for end-to-end browser testing and CI/CD pipelines.

This skill fetches raw text transcripts from any YouTube video. It prioritizes using the DeepAPI service for reliable, server-side scraping, which bypasses local bot detection issues. If DeepAPI fails or the API key is unavailable, it gracefully falls back to using the local `yt-dlp` tool. The output is always saved as a clean, unformatted .txt file.

Translate and synchronize application JSON locale files using source-key usage, project terminology, and focused validation. Use when adding keys or languages, updating source copy, or reviewing missing and stale translations.

Deploy a Dockerfile, source folder, or existing image to Cloudish as a running container at a live HTTPS URL. Builds happen server-side with no local Docker, with persistent volumes, env vars, build logs, and confirmation before spending credits.