Official Agent Skills

Build real-time voice AI applications with bidirectional WebSocket communication using the Azure AI Voice Live SDK for JavaScript/TypeScript.

Export OpenTelemetry traces, metrics, and logs to Azure Monitor/Application Insights using the deprecated exporter or the recommended autoconfigure package.

Launch distributed Megatron-LM training jobs on a SLURM cluster with a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules, container conventions, monitoring, and per-rank failure diagnosis.

Score a clinical ASR manifest against a chosen NIM, produce a five-section KER leaderboard, and route the user via a post-eval decision tree.

Capture a full DevTools-protocol trace of any browser automation, bisect the stream into per-page searchable buckets, and attach a trace to an in-progress session for debugging.

Generate spoken audio for narration, voiceovers, IVR prompts, and accessibility reads using the OpenAI Audio API with bundled CLI and built-in voices.

Configure and collect crash dumps for modern .NET applications (CoreCLR and NativeAOT) on Linux, macOS, and Windows, including containers.

Add light/dark mode, custom branded themes, and runtime theme switching to .NET MAUI apps using AppThemeBinding, ResourceDictionary swapping, and system theme detection APIs.

Detects and fixes common MSBuild anti-patterns in .csproj, .vbproj, .fsproj, .props, .targets, and .proj files, covering Exec misuse, unquoted conditions, hardcoded paths, and more.

Provides file paths to language-specific reference files for polyglot test analysis skills, enabling framework-aware detection of test markers, assertions, and patterns across .NET, Python, TypeScript, Java, Go, Ruby, Rust, Swift, Kotlin, PowerShell, and C++.

Build and install Expo development clients on physical devices and simulators using EAS Build for testing native code changes.

Query EAS Update health metrics from the CLI: crash rates, install/launch counts, unique users, payload size, and embedded vs OTA user splits per channel.

Detect and fix code-quality and correctness issues in AEM as a Cloud Service projects locally, without external services or network calls.

Generates a concise, executive-ready performance summary covering key metrics, trends, and what's driving movement, using Adobe Analytics data.

Create, modify, review, and harden configuration for the Adobe Dispatcher Apache HTTP Server module and Apache HTTPD in AEM 6.5 LTS environments only.

Provides advisory guidance for the Adobe Dispatcher Apache HTTP Server module and related HTTPD configuration in AEM 6.5 / AMS workflows, with public-doc citations and AMS-specific MCP verification plans.

Debug AEM Workflow issues on AEM 6.5 LTS and AMS including stuck workflows, failed steps, missing Inbox tasks, launcher failures, stale instances, thread pool exhaustion, queue backlogs, purge failures, and permissions errors.

Publish, unpublish, replicate, activate, or deactivate content on AEM 6.5 LTS publish instances using Quick Publish, Manage Publication, tree activation, package replication, workflow-based approval, scheduled activation, or the Replication API.

Archive non-actionable noise from the Sentry javascript project issue queue, using untilEscalating mode with documented categories.

Creates and runs LLM-as-judge evaluators on Arize, including managing tasks, column mappings, and continuous monitoring.

Run an AI-readiness assessment on the current repository and generate a static HTML dashboard at reports/index.html.

Bootstrap and run a multi-agent AI development team with parallel chats for planning, development, QA, and DevOps.

Parses Simplicité log files from raw .txt format, filters fields to reduce noise, and outputs structured JSON for efficient AI context usage.

Analyze content sequences from page structure to determine whether each should be default content or a specific block, and validate block selection for AEM Edge Delivery Services imports.

Installs and configures the official Google Ads MCP Server to connect AI assistants to Google Ads accounts for querying campaigns and retrieving reporting metrics using natural language.

Manage Oracle Cloud Infrastructure Internet of Things Platform resources: domains, digital twin models, adapters, instances, relationships, and device publish flows. Includes discovery, inspection, safe lifecycle operations, and troubleshooting.

Generates Angular code and provides architectural guidance for projects, components, services, reactivity, forms, dependency injection, routing, SSR, accessibility, animations, styling, testing, and CLI tooling.

Manage datasets, tables, and jobs in BigQuery. Run SQL queries, manage BigQuery resources, and perform basic data ingestion and analysis.

Deploy and manage Cloud Run services, jobs, and worker pools on Google Cloud.

Finetune the NV-Generate-CTMR MAISI VAE/autoencoder on user-supplied CT or MRI NIfTI volumes using a staged config and datalist workflow.

Train, evaluate, export, quantize, and run inference for a Deformable DETR 2D object detection model using TAO, with deformable attention for efficient multi-scale feature processing.

Validates NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors using the `tao-daft validate` CLI tool.

Runs a three-phase AOI training pipeline: AutoML HPO baseline, DEFT iterative data improvement, and AutoML refinement on the augmented dataset.

Convert single-node PyTorch distributed scripts into multi-node Slurm sbatch jobs and debug common multi-node failures, covering srun-native and torch.distributed approaches, container setup, NCCL timeouts, and interactive allocation.

Bootstraps a clinical ASR evaluation environment by verifying NVIDIA_API_KEY, installing Python dependencies, and running a smoke test against hosted TTS/ASR services.

Create Earth2Studio prognostic model wrappers that time-step weather forecasts forward, with triple-inheritance classes, tests, and documentation.

Adapt Android app UIs to phones, tablets, foldables, desktops, and other devices using Compose, including window size handling, multi-pane layouts, and adaptive navigation.

Set up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling across iOS, Android, and Web.

Reconcile a converted or built web page against its source prototype using pixel/layout and structural content diffs to catch fidelity regressions.

Analyzes a multi-step conversion funnel in Adobe Customer Journey Analytics to find where users drop off and which steps have the worst leakage.

Install, configure, and troubleshoot the Adobe AEM CLI (@adobe/aem-cli) for local Edge Delivery development, including dev server, import server, content sync, TLS, and proxy setup.

Generate comprehensive authoring guides for content authors taking over an AEM Edge Delivery Services project, covering blocks, templates, configurations, and publishing workflows.

Guides implementation of AEM Edge Delivery blocks with JavaScript decoration and CSS styling, following established patterns and best practices.

Searches for existing content pages containing a specific block in AEM Edge Delivery Services, reporting URLs with occurrences and variants to help identify test content during development.

Generates structured HTML from authoring analysis for AEM Edge Delivery Services, creating section structure, applying block tables, handling metadata, and managing images folder.

Orchestrate a content-driven development workflow for AEM Edge Delivery Services, ensuring code is built against real content with author-friendly content models.

Downloads, exports, and inspects Arize traces and spans to debug LLM application behavior using the ax CLI.

Configure and manage GitHub secret scanning, push protection, custom patterns, and alert remediation.

Finds the minimal Azure role that meets desired permissions and generates CLI commands or Bicep code to assign it.

Bulk-migrate repo labels and Project V2 fields into GitHub org-level issue fields (single select, text, number, date).

Migrate React class component lifecycle methods (componentWillMount, componentWillReceiveProps, componentWillUpdate) to React 18.3.1 compliant patterns with decision trees and before/after code examples.

Safely analyzes and cleans up local git branches and worktrees by categorizing them as merged, squash-merged, superseded, or active work.

Projects external audit findings from SARIF static analysis results and weAudit annotation files onto Trailmark code graphs as annotations and subgraphs, enabling cross-referencing with pre-analysis data like blast radius and taint.

Detect memory errors like buffer overflows and use-after-free bugs in C/C++ code during fuzzing and testing using AddressSanitizer.

Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations, detecting attack vectors where attacker-controlled input reaches AI agents in CI/CD pipelines.

Add smooth, native-feeling page transitions and animations to React apps using the browser's View Transition API, with support for shared elements, enter/exit animations, and directional navigation.

Selects the correct SageMaker serving container image URI for HuggingFace model deployments, prioritizing HuggingFace-curated Deep Learning Containers over generic alternatives.

Model and solve LP, MILP, and QP problems using NVIDIA cuOpt's GPU-accelerated solver via Python, C/C++, or CLI interfaces.

Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud, enabling interaction from environments without local simulators.