Official Agent Skills

Detect harmful user-generated and AI-generated content in text and images using Azure AI Content Safety SDK for Python.

Analyze text with Azure AI Language service for sentiment, entities, key phrases, language detection, PII redaction, and healthcare NLP using the Python SDK.

Transcribe audio to text using Azure AI Transcription SDK with real-time and batch support, including timestamps and diarization.

Manage Azure App Configuration settings, feature flags, and snapshots using the Python SDK with Entra ID authentication.

Store, retrieve, and manage secrets in Azure Key Vault using the official Rust SDK.

Manage container images, artifacts, and repositories in Azure Container Registry using the Python SDK.

Manage Azure API Center resources including services, workspaces, APIs, versions, definitions, environments, and deployments using the .NET SDK.

Analyze text and images for harmful content using Azure AI Content Safety, with customizable blocklists and severity thresholds.

Manage Azure File Shares using the official TypeScript/JavaScript SDK. Create and delete shares, directories, and files; upload, download, and copy files; set metadata and HTTP headers.

Extract semantic content from documents, images, audio, and video using Azure AI Content Understanding SDK for Python.

Translate Word, PDF, Excel, PowerPoint, and other documents at scale using Azure AI Document Translation SDK with format preservation.

Create and manage persistent AI agents with threads, messages, runs, and tools using the Azure AI Agents SDK for .NET.

Manage Weights & Biases ML experiment tracking instances on Azure using the .NET SDK. Create, configure, list, update, and delete W&B instances with marketplace integration and SSO.

Send real-time messages and manage WebSocket connections using Azure Web PubSub Service SDK for Python.

Manage Microsoft Playwright Testing workspaces via Azure Resource Manager: create, update, delete workspaces, check name availability, and manage quotas using the .NET SDK.

Provision and manage Azure Durable Task Scheduler resources, task hubs, and retention policies using the .NET Azure Resource Manager SDK.

Coordinate the end-to-end pipeline from CAD or source assets to SimReady USD assets, including conversion, material and physics assignment, validation, conformance, and optional packaging.

Runs AutoMagicCalib calibration on local MP4s, RTSP streams, or a bundled sample dataset, and deploys the AMC microservice when needed.

Diagnose and optimize slow-loading, high-memory, or low-FPS USD scenes using a structured workflow with profiling, validation, and mutation phases.

Identifies the weakest samples per ground-truth label in NVIDIA TAO VCN Classify experiments by running a Docker container that performs threshold sweep, weakness scoring, and per-lighting expansion, then surfaces top-K weak samples for downstream augmentation or relabeling.

Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks.

Install skills from a curated list or any GitHub repository, including private repos, using helper scripts.

Search Notion pages, synthesize findings, and publish structured briefs, summaries, comparisons, or reports with citations and source links.

Integrate verified email retrieval into Android apps using the Credential Manager API and OpenID4VP for secure, OTP-less email verification.

Integrates the Play Engage SDK into Android apps, generating boilerplate code for entity mapping, data publishing, and debugging.

Analyzes .NET Framework CLR activation logs to diagnose runtime loading failures, version selection issues, and Feature-on-Demand dialog behavior.

Migrate .NET 9 projects to .NET 10 by updating target frameworks, resolving breaking changes, and fixing build errors.

Resolves native backtrace frames from .NET Android app crashes to function names, source files, and line numbers using ELF BuildIds and Microsoft's symbol server.

Build native UI with @expo/ui: real SwiftUI on iOS and Jetpack Compose on Android, rendered from React in Expo or React Native apps. Covers universal cross-platform components, drop-in replacements for community libraries, and platform-specific SwiftUI and Jetpack Compose trees.

Apply design, canon, and modules to every page in the inventory to produce a deployable static HTML site. Per-page, incremental, and idempotent.

Search reference implementations and code examples from Adobe's Block Collection and community Block Party for AEM Edge Delivery blocks, plugins, and build tools.

Optimize SQL queries, indexes, and database performance across MySQL, PostgreSQL, SQL Server, and Oracle with execution plan analysis and universal tuning techniques.

Validates Bicep deployments to Azure before execution, including syntax checks, what-if analysis, and permission verification.

Generate or edit images via OpenRouter using the Gemini 3 Pro Image model, with support for prompt-only generation, single-image edits, and multi-image compositing at 1K/2K/4K resolutions.

Build and modify Minecraft server plugins for Paper, Spigot, or Bukkit, covering plugin.yml setup, commands, listeners, schedulers, player state, team/arena systems, persistent progression, economy, configuration, and Adventure text.

Debug failing Power Automate cloud flows by inspecting action-level inputs and outputs through the FlowStudio MCP server.

Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes.

Identifies Oracle-to-PostgreSQL migration risks by cross-referencing code against known behavioral differences. Use when planning a database migration, reviewing migration artifacts, or validating integration test coverage.

Creates structured bug reports for defects found during Oracle-to-PostgreSQL migration, documenting behavioral differences with severity, root cause, and remediation steps.

Triage mutation testing results by combining survived mutants, unnecessary test statements, and code graph analysis to identify false positives, missing test coverage, and fuzzing targets.

Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes in API designs, configuration schemas, and cryptographic library ergonomics.

Provides expertise for analyzing DWARF debug files and understanding the DWARF debug format (v3-v5). Triggers when understanding DWARF information, interacting with DWARF files, answering DWARF-related questions, or working with code that parses DWARF data.

Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis and control-flow verification. Use for auditing C/C++/Rust code handling secrets, keys, passwords, or other sensitive data.

Validate cryptographic implementations against known attacks and edge cases using Wycheproof test vectors.

Generates minimal macOS Seatbelt sandbox configurations to isolate and restrict applications with allowlist-based profiles.

Analyzes smart contract codebases against Trail of Bits' secure development guidelines, generating documentation, reviewing architecture and upgradeability patterns, assessing implementation quality, identifying pitfalls, and providing prioritized recommendations.

Guides through a 5-step secure development workflow for smart contracts, including automated scanning with Slither, special feature validation, visual security diagrams, security property documentation, and manual review.

Scans Algorand smart contracts for 11 common vulnerabilities including rekeying attacks, unchecked transaction fees, missing field validations, and access control issues.

Diagnose and fix connectivity issues with the Claude in Chrome MCP extension, including native host conflicts between Claude.app and Claude Code CLI.

Deploy applications and websites to Vercel as preview or production deployments, with support for git-based workflows, CLI authentication, and no-auth fallback.

Turn a music track into a beat-synced video — lyric video, slideshow, or kinetic promo — with optional user-supplied images or videos cut onto the same beat grid.

Add captions or subtitles to a single-subject talking-head video without editing the footage, using a catalog of visual identities.

Conducts systematic security code reviews to identify exploitable vulnerabilities, reporting only high-confidence findings after researching the codebase.

Test and debug local web applications using Playwright browser automation, including UI verification, screenshot capture, and console log inspection.

Find and own a defensible market position by testing positioning claims, running crawl-walk-run rollouts, and auditing competitor messaging.

Convert frontend code (Vite, React, etc.) into a Stitch Design by extracting static HTML, analyzing the design system, and uploading to Stitch.

Analyzes codebases to generate comprehensive architectural documentation, including technology stack detection, visual diagrams, and implementation patterns.

Add governance, safety, and trust controls to AI agent systems with policy enforcement, intent classification, and audit trails.

Analyzes Android apps to identify user workflows for AppFunctions, generates Kotlin code to expose them to the Android system, and refines KDoc documentation for AI agent compatibility.

Optimize PostgreSQL databases with advanced features, performance tuning, and best practices for JSONB, full-text search, window functions, and indexing.