Agent Building Agent Skills

Integrate Azure OpenAI and OpenAI services in .NET applications for chat completions, embeddings, image generation, audio transcription, and assistants.

Manage Azure AI Foundry projects with .NET SDK: create and run agents, manage connections, datasets, deployments, evaluations, and indexes.

Build AI applications using the Azure AI Projects SDK for TypeScript, managing agents, connections, deployments, datasets, indexes, and evaluations.

Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK, with support for function tools, hosted tools, MCP servers, conversation threads, and streaming responses.

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

Create, run, and analyze evaluation suites for Microsoft 365 Copilot declarative agents using the @microsoft/m365-copilot-eval CLI.

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

Analyze conversation intent and entities using the Azure AI Language Conversations Python SDK with best practices for authentication and error handling.

Access AWS Bedrock foundation models for generative AI, including text generation, embeddings, and image generation, with CLI and Python examples.

Guide users through installing CUDA-Q, writing quantum kernels, running GPU-accelerated simulations, connecting to QPU hardware, and exploring built-in applications.

Runs deep research queries through a reachable NVIDIA AI-Q Blueprint backend, handling health checks, job submission, polling, and report retrieval.

Ask visual questions about video clips using a VSS agent's video_understanding tool, requiring a fresh look at frames rather than prior metadata or search results.

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

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.

Guides users through installing, configuring, and calling the NVIDIA cuOpt SDK for routing and optimization problems, with emphasis on clarifying requirements and safe execution.

Serve LLMs and VLMs on NVIDIA Jetson devices using vLLM or SGLang with optimized Docker containers and quantization presets.

Automates the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models, including baseline evaluation, RCA, synthetic defect generation, data mining, retraining, and deployment gating until KPI targets are met.

Submit and monitor GPU training jobs on Brev, SLURM, Docker, or Kubernetes using the TAO Execution SDK, with job handles, S3 I/O wrapping, and multi-node distributed training.

Write, review, and migrate code using NVIDIA DALI's imperative dynamic-mode API for efficient data loading and preprocessing.

Guides AI coding assistants to the official NemoClaw documentation via MCP server or Markdown files for installation, configuration, operation, and troubleshooting.

Generates or updates a governance skill card for an existing agent skill directory by analyzing source signals, building a grounded JSON context, and rendering a deterministic markdown card.

Detects generalizable learnings from problem-solving interactions and proposes skill updates to improve future performance.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Write high-performance GPU kernels using cuTile's tile-based programming model with validation and optimization, including deep agent orchestration for complex multi-kernel tasks.

Provides storage and environment conventions for NeMo-RL agents on Brev instances, ensuring large experiment outputs go to /ephemeral and secrets are loaded from .env.

Solve vehicle routing problems (TSP, VRP, PDP) using NVIDIA cuOpt's Python API with cost matrices, time windows, capacity constraints, and pickup-delivery pairs.

Routes NuRec/Neural Reconstruction requests to the correct upstream NVIDIA skill (datasets, conversion, training, rendering, object harvesting, frame cleanup).

Builds reliable browser automation skills through iterative experimentation, running an inner agent to browse sites and improving navigation instructions until tasks pass consistently.

Build a local browser agent that enforces a domain allowlist via CDP Fetch interception, using a safe_browser tool that owns the Playwright session and blocks off-domain requests.

Compare coding agents head-to-head on reproducible tasks with pass rate, cost, time, and consistency metrics.

Build persistent multi-agent operating systems on Claude Code with kernel architecture, specialist agents, slash commands, file-based memory, and scheduled automation.

Search the web, code, companies, and people using the Exa MCP server for current information and technical research.

Provides a formal evaluation framework for Claude Code sessions, implementing eval-driven development (EDD) principles to define pass/fail criteria, measure reliability with pass@k metrics, and create regression test suites.

Turn model work into a production ML system with data contracts, repeatable training, measurable quality gates, deployable artifacts, and operational monitoring.

Uses two independent review agents to verify output quality, requiring both to pass before shipping.

Automatically measures whether coding agents follow skills, rules, or agent definitions by generating scenarios at multiple prompt strictness levels, running agents, classifying tool calls, and reporting compliance rates with full timelines.