Official Agent Skills

Coverage-guided fuzzer built into LLVM for C/C++ projects. Use for fuzzing C/C++ code that can be compiled with Clang.

Fuzz Rust projects with libFuzzer using cargo-fuzz, including harness writing, sanitizer integration, and coverage analysis.

Write high-quality YARA-X detection rules for malware identification, covering naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction.

Write effective fuzzing harnesses across languages to improve code coverage and find bugs in your system under test.

Measures code coverage during fuzzing to assess harness effectiveness and identify fuzzing blockers.

Provides React composition patterns to avoid boolean prop proliferation, build flexible component libraries, and design reusable APIs, including React 19 changes.

Provides guidance on enabling and optimizing GKE Cluster Autoscaler, including Node Auto Provisioning, troubleshooting scale-up/down issues, and best practices for capacity management.

Resolves, generates, and operates on media assets (audio, images, icons, logos, voice, color grades, LUTs) for HyperFrames projects, using a local cache and the HeyGen CLI for free-usage catalog search and TTS.

Turns a GitHub pull request into a code-change explainer video with changelog, feature reveal, or refactoring walkthrough built from the diff, commits, and files.

Performs repository-grounded threat modeling by enumerating trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, then writes a concise Markdown threat model.

Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files for AI coding agents, keeping them under 60 lines and referencing existing documentation.

Surveys available blocks from a local AEM Edge Delivery Services project and Block Collection to understand the block palette available for authoring, returning a block inventory with purposes to inform content modeling decisions.

Provides guidance for building and modifying content management systems across platforms like WordPress, Shopify, Drupal, and Webflow, covering themes, plugins, admin interfaces, media handling, content models, and static export workflows.

Modify, build, test, debug, and contribute to the NVIDIA cuOpt codebase (C++/CUDA, Python, server, CI). Includes guidance for solver internals, pull requests, DCO signoff, and code conventions.

Summarize recorded video clips using the LVS microservice with a VLM fallback, producing a narrative summary with timestamped events.

Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components.

Captures desktop screenshots on macOS, Linux, and Windows with support for full screen, specific apps, windows, and pixel regions.

Retrieves real-time Azure retail pricing from the public Azure Retail Prices API and estimates Copilot Studio agent credit consumption.

Guided multi-page redesign of an existing website through a four-phase pipeline — extract, direct, prototype, and migrate. Tracks progress incrementally per page so redesigns are resumable.

Generates AGENTS.md files for repository folders to provide coding agents with project-specific context including build commands, testing instructions, code style, project structure, and operational boundaries, only where AGENTS.md is missing.

Generates rich technical documentation pages with dark-mode Mermaid diagrams, source code citations, and first-principles depth.

Generate production-quality Python scripts for FreeCAD CAD application, covering geometry creation, parametric objects, GUI tools, and automation.

Routes user requests to specialist skills for AEM 6.5 LTS Dispatcher configuration, troubleshooting, performance tuning, security hardening, and lifecycle orchestration.

Create interactive, data-driven presentation slides using React, Vite, and Recharts with Sentry branding, built as a single distributable HTML file.

Fine-tune open models or Gemini models using Agent Platform infrastructure, from environment setup through data preparation, job configuration, monitoring, and deployment.

Interprets Culture Index survey data, behavioral profiles, and personality assessments from JSON or PDF. Supports individual profile interpretation, team composition analysis, burnout detection, hiring profiles, manager coaching, interview transcript analysis, and conflict mediation.

Debug local web or Electron apps interactively using a persistent Playwright session with js_repl, enabling fast iterative UI debugging and visual QA.

Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project, bypassing MCP tool base64 token limits.

Crawl a live website, extract its design system, brand surface, and page inventory, and save the snapshot under stardust/current/ for downstream redesign or migration.

Detects and triages explicitly-unbounded AEM queries (p.limit=-1 or setLimit(-1)) that cause OOMs, safely capping only where provably safe and escalating others for human pagination.

Provides a catalog of cinematic transition techniques (zoom-through, cut-the-curve, waterfall cut, etc.) with GSAP parameters for velocity-matched seams and in-scene motion.

Sets up Google's agents-cli toolkit and guides through the full agent development lifecycle: scaffold, build, evaluate, deploy, publish, and monitor on Gemini Enterprise Agent Platform.

Manage machine learning models in the Agent Platform Model Registry: list, describe, upload, update, and delete models and their versions.

Estimates the memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub, using HTTP Range requests without downloading weights.

Build applications that programmatically interact with GitHub Copilot using the Copilot SDK, supporting session management, custom tools, streaming, hooks, MCP servers, and deployment across Node.js, Python, Go, and .NET.

Conducts multi-turn iterative deep research on specific topics within a codebase, tracing actual code paths and grounding every claim in evidence.

Diagnose and resolve issues with Azure Event Hubs and Service Bus SDKs, including connection failures, authentication errors, message processing problems, and SDK configuration.

Build multichannel agents for Microsoft 365, Teams, and Copilot Studio using the Microsoft Agents SDK with aiohttp hosting, AgentApplication routing, streaming responses, and MSAL-based authentication.

Provides CRUD operations for Azure Cosmos DB NoSQL API from Rust, including document management, container operations, and globally distributed data access.

Publish events to Azure Event Grid using CloudEvents or EventGridEvent schemas, with support for sync and async clients, namespace topics, and DefaultAzureCredential authentication.

Build enterprise agents for Microsoft 365, Teams, and Copilot Studio using the Microsoft 365 Agents SDK with Express hosting, AgentApplication routing, streaming responses, and Copilot Studio client integrations.

Provides code samples and best practices for using the Azure Tables SDK for Python to perform NoSQL key-value storage, entity CRUD, batch operations, and queries against Azure Storage Tables or Cosmos DB Table API.

Send and receive high-throughput event streams using Azure Event Hubs with .NET, including batch sending, buffered producers, and checkpoint-based processing.

Queries video analytics incidents, alerts, metrics, and sensor data from Elasticsearch via the VA-MCP server.

Debug and fix failing GitHub Actions PR checks by inspecting logs, summarizing failures, and implementing fixes after approval.

Creates a new blank Figma or FigJam file in the user's drafts folder, resolving the plan key automatically.

Connects Figma design components to their code implementations using Figma's Code Connect feature, analyzing design structure and scanning codebases for matching components.

Wire UI controls to ViewModel properties with compile-time safety, change notification, and minimal overhead using .NET MAUI data bindings.

Build .NET MVVM ViewModels with CommunityToolkit.Mvvm source generators, base classes, and commands for WPF, WinUI, MAUI, Uno, and Avalonia.

Design, build, and optimize Microsoft Fabric Lakehouse solutions with guidance on core concepts, components, security, shortcuts, and performance optimization.

Runs a complete quality engineering audit on any codebase, deriving behavioral requirements, generating spec-traced tests, performing multi-pass code review, and producing a consolidated bug report with verified patches.

Scans TON (The Open Network) smart contracts for 3 critical vulnerabilities including integer-as-boolean misuse, fake Jetton contracts, and forward TON without gas checks. Use when auditing FunC contracts.

Maintain durable session memory across agent disconnects by writing structured checkpoints to the repo's session directory, enabling context recovery.

Scaffold, implement, deploy, and debug Adobe Runtime actions with consistent layout, validation, and error handling.

Resize photos and videos to exact pixel dimensions, aspect ratios, or named sizes using Adobe tools.

Add real-time voice conversations to a custom agent runtime using ElevenLabs Speech Engine, handling WebSocket servers, browser clients, and interruption-aware streaming.

Ranks any list of impediments and their countermeasures using a value-stream scoring model (ROI, Cost to Implement, Ease of Deployment, Risk Factor) and a fixed prioritization formula.

Evaluates Google Cloud workloads against the Reliability pillar of the Well-Architected Framework, providing actionable recommendations for building, deploying, and managing reliable systems.

Routes Azure VM and Virtual Machine Scale Set (VMSS) requests to the right workflow for recommendation, creation, troubleshooting, capacity reservation, and essential machine management.

Plan, create, and configure production-ready Azure Kubernetes Service (AKS) clusters, covering Day-0 decisions, SKU selection, networking, security, and operations.