Skill UI

An adapter for generating short, browser-playable video assets using OpenRouter's asynchronous video generation API. This skill is designed for meta-skills to integrate dynamic multimedia content into web pages. It handles the full job lifecycle—submitting the request, polling for completion, and downloading the final MP4 asset—and adheres strictly to the required manifest reporting format.

Compiles an iOS Objective-C/Swift module into a flat device-slice .framework for a .ppmplugin bundle. Mac-only Xcode build, references React-Core headers only and never embeds React or uses CocoaPods. Leaves canonical ios/ sources untouched. Run after manifest generation and before plugin assembly.

Diagnose and fix failures in built .ppmplugin controls: crashes, silent no-ops, PCF errors, or incorrect behavior. Investigates symptoms through error codes, manifests, native modules, and dispatch to locate root causes, then applies approved surgical fixes. Use when a control breaks on device.

This skill is the final step in the plugin build pipeline. It takes the generated manifest and all staged binary artifacts (Android/iOS) from prior build steps. Its core function is to reconcile the declared entrypoints against the actual existence of binaries, ensuring consistency. It then zips these verified components into a single, statically verified, and ready-to-deliver .ppmplugin bundle.

This skill performs a static, read-only audit of a finished .ppmplugin bundle. It acts as a crucial verification gate, ensuring the bundle is structurally sound and ready for runtime deployment. It checks archive layout, manifest schema integrity, DEX/iOS structure, and adherence to native contract rules. By identifying critical failures locally, it dramatically speeds up the development cycle and prevents difficult-to-discover runtime deployment errors.

This skill compiles the Android Kotlin source code (Module.kt) into a runtime-loadable DEX binary required for a .ppmplugin. It executes the heavy-duty Gradle build process, managing toolchain dependencies (JDK 17+, Android SDK Build-Tools 35.0.0) and verifying manifest and package alignment. It outputs the actionable DEX binary, marking a critical step in the plugin creation workflow.

This skill generates the complete native source code for a third-party Platform Abstraction Module (PAM) control, including iOS Obj-C, Android Kotlin, required podspecs, and a manifest contract. It bypasses TypeScript layers, focusing purely on the native build surface and the dispatch contract (`manifest.json`). This is used by developers to scaffold the foundational, OS-specific code necessary for integrating custom, native modules into a React Native environment.

Automates the generation of the Power Apps Component Framework (PCF) companion dispatcher. This tool bridges third-party native modules (like .ppmplugin) to the Power Apps host environment by utilizing the window.PowerApps.NativeExtension.sendAsync global. It handles manifest updates, message contract generation, and structured logging, enabling seamless native-to-UI communication within the Power Apps ecosystem.

This skill serves as the recommended entry point for building and verifying third-party native plugins. It orchestrates a complete, multi-stage workflow, automatically detecting available Android and iOS targets, generating manifests, compiling binaries, assembling the bundle, and performing final audits. It ensures the output is a verified, shippable native plugin bundle.

This skill manages the `manifest.json` for a .ppmplugin bundle. It acts as a critical pre-flight gate by validating the manifest structure, reconciling declared entrypoints against the target platform(s), and generating a build-ready staged copy. It supports two modes: validating an existing committed manifest, or authoring the manifest entirely from source code if none exists. It ensures the plugin's descriptor is correct before the actual build process.

This document outlines the canonical contract for deploying model inference services on Itô compute. It details the secure handoff process of an immutable serving manifest after a compute booking is verified. The process enforces multiple strict gates, including entitlement checks, manifest integrity validation, idempotency key usage, and final health checks, ensuring robust and reliable deployment of advanced AI models.

This skill orchestrates advanced Machine Learning training workflows on dedicated compute clusters. It manages complex stages (pre-training, fine-tuning, RL) by ensuring strict adherence to immutable manifests, fresh booking entitlements, and multi-step confirmation gates. It acts as a canonical interface for job submission, emphasizing security, idempotency, and resource validation before execution.