Skill UI

The RunAPI CLI serves as the dedicated execution layer for interacting with RunAPI's suite of advanced AI models. It allows developers to programmatically generate multimodal content, including images, videos, and music/audio, directly from the terminal or CI/CD pipeline. Users can submit one-off jobs, manage asynchronous tasks, and pass complex JSON request bodies to various services like Suno, Claude, and Gemini, making it essential for robust AI automation workflows.

Practical guide for pre-caching fonts, images, animations, and initial data in Flutter and Flutter Web to reduce jank, font swaps, and startup delays. Covers Google Fonts, asset/network images, multiple image preloading, and app-start preloader patterns.

This meta-skill acts as a watchdog for long-running processes, such as CI image builds or overnight model fine-tunes. It utilizes a sub-agent to continuously monitor the output via tmux, automatically diagnose failures, propose corrective fixes, and persist the entire resolution process to memory. It is designed for robust, automated debugging of complex system tasks.

This skill captures a fully self-contained static HTML snapshot from any running web application (e.g., React, Vue, Next.js). Using Puppeteer, it renders the live DOM, automatically inlining all CSS styles and converting images, assets, and backgrounds to base64 data URIs. This ensures the generated HTML file is completely self-sufficient and requires no external network connection, making it perfect for sharing UI states, creating documentation, or preparing assets for offline viewing.

A comprehensive skill for generating new design screens from text prompts or images, and iteratively editing existing designs. It incorporates advanced prompt enhancement, design tokens, and professional UI/UX terminology to ensure professional, structured, and context-aware design output for web and mobile platforms.

This skill enables the upload of various local assets, including images (PNG, JPG, WEBP), extracted HTML, and design markdown files, directly to a designated Stitch project. Crucially, it bypasses the token limits associated with standard MCP tool calls by using a dedicated HTTP upload script. Use this when visual assets or large design documentation need to be integrated into your Stitch design system.

A utility to render high-quality, static title or ending cards as PNG images. It supports centered headlines, optional subtitles, and configurable solid-color backgrounds. Crucially, it handles complex CJK fonts with glyph verification, ensuring robust and professional output without relying on LLMs or network connectivity. Ideal for generating consistent opening/closing visuals for short-form video content.

This comprehensive guide covers the process of creating, analyzing, and securing Software Bills of Materials (SBOMs). It utilizes Syft to generate standards-compliant SBOMs (CycloneDX or SPDX) from container images and filesystems. The workflow details correlating these SBOMs with known CVEs using Grype for vulnerability analysis, and subsequently signing the artifacts with Cosign. This process is crucial for establishing supply chain trust, ensuring dependency visibility, and integrating vulnerability gating into CI/CD pipelines.

Trivy is an open-source, comprehensive security scanner designed for DevSecOps. It assesses container images, Infrastructure-as-Code (Terraform, K8s), filesystems, and SBOMs for vulnerabilities (CVEs), misconfigurations, hardcoded secrets, and license compliance. It is essential for implementing 'shift-left' security gates in CI/CD pipelines, ensuring that code and infrastructure are secure before deployment.

This skill enables users to upload local images, such as screenshots or before-and-after comparisons, directly to GitHub using the GitHub CLI. It bypasses the lack of a public image upload API by mimicking the web UI's internal attachment flow, generating canonical `user-attachments` URLs. These URLs can then be seamlessly embedded into Pull Requests, Issues, or comments from the terminal.

Use this comprehensive skill for interacting with the Gemini API. It supports a wide range of advanced AI tasks, including text generation, multi-turn chat, multimodal understanding, image/video creation, function calling, and structured output. Provides modern SDKs for robust application development in Python and JavaScript/TypeScript.

Neon Object Storage provides S3-compatible, branch-aware object storage directly integrated with your Neon Postgres project. It ensures that files (images, documents, user uploads) remain perfectly synchronized with the database schema across all development branches (dev, preview, staging, production). Use this skill when you need a single backend for both database rows and file assets, eliminating the need for separate cloud storage providers.