Top Agent Skills

Analyzes Stripe's design language, documenting its color system, typography, layout, and component patterns for use in design projects.

Recreates Dell.com's 1996 catalog-era design with a black page frame, flat color-block ribbon cards, chunky Helvetica-Black titles, Times Roman body copy, and hand-cut GIF stickers.

Documents Mistral AI's visual design system including sunset gradient color palette, typography pairing of PP Editorial Old with Inter, spacing tokens, and layout patterns across six page types.

Search the web and extract content from URLs using Exa, with support for academic and scientific sources.

Systematically repair a broken feature or module by scoping, tracing dependencies, diagnosing all issues, fixing them in order, and verifying end-to-end.

Design and implement programmatic SEO strategies to create search-optimized pages at scale using templates and data, avoiding thin content penalties.

Configures GKE storage including PVCs, PersistentVolumes, Filestore, and GCS FUSE with best practices for production workloads.

Manage custom Agent resources on the Gemini Enterprise Agent Platform via REST API, including creation, configuration, listing, updating, and deletion with support for files, skills, and tools.

Uploads audience members to Google products like Customer Match and mobile device ID audiences using the Data Manager API.

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning) with support for SFT, DPO, GRPO, KTO, RLOO, and reward model training via CLI commands.

Execute Azure deployments for already-prepared applications using azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery and verification.

Execute Kusto queries against Log Analytics workspaces and query metrics from Azure resources using the Azure Monitor Query SDK for Java.

Search Azure AI Search indexes using the Python SDK for full-text, vector, hybrid, and semantic search with AI enrichment.

Extract text, tables, key-value pairs, and structured fields from documents, receipts, invoices, and IDs using Azure AI Document Intelligence SDK for Java.

Architect and provision enterprise Azure infrastructure from workload descriptions, generating Bicep or Terraform for networking, identity, security, and multi-resource topologies aligned with the Well-Architected Framework.

Detect anomalies in time-series data using the Azure AI Anomaly Detector SDK for Java, with support for univariate and multivariate analysis, model training, and inference.

Transcribe short audio files (up to 60 seconds) using Azure Speech-to-Text REST API with Python, without requiring the Speech SDK.

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

Analyze images using Azure AI Vision SDK for Java, enabling captioning, OCR, object detection, tagging, and smart cropping.

Guides through interactive deployment of Azure OpenAI models with full control over version, SKU, capacity, content filtering, and advanced options.

Manage AWS S3 buckets and objects: create buckets, upload/download files, configure lifecycle policies, set up static websites, manage permissions, and implement cross-region replication.

Deploy and manage Docker containers on AWS ECS with Fargate or EC2, including task definitions, services, auto scaling, and troubleshooting.

Manage Amazon EKS clusters, node groups, IRSA, add-ons, and deployments using AWS CLI and eksctl.

Manage AWS API Gateway for creating, publishing, and securing REST, HTTP, and WebSocket APIs using CLI commands, SAM templates, and best practices.

Design, build, and manage AWS Step Functions state machines for serverless workflow orchestration, including error handling, parallel execution, and integration with AWS services.

Install cuOpt for Python, C, or REST server via pip, conda, or Docker, and verify the installation.

Manage NVIDIA Brev GPU instances for TAO training, evaluation, and inference using the Brev CLI and Docker.

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

Read and write large cuPyNumeric arrays to HDF5 files using Legate's parallel, distributed HDF5 I/O.

Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.

Copies overlay files and built artifacts into a staged BSP image for NVIDIA Jetson platforms, preparing it for flashing without modifying the workspace.

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.

Generates kernel device-tree overlay fragments to enable or disable individual PCIe controllers and configure lane count and link speed on Jetson Thor/Orin custom carriers.

Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit.

Inspects a Jetson Linux_for_Tegra BSP tree on the host PC and prints a concise summary including L4T version, board configs, and rootfs state.

Extracts selected metadata from a DICOM file and flags standard-tag PHI presence. Not for anonymization or clinical use.

Reclaim DRAM on NVIDIA Jetson devices by disabling unused display, camera, and DMA subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB layers for headless or no-camera deployments.

Configure fault tolerance, straggler detection, preemption, in-process restart, and re-run state machine for Megatron Bridge training jobs.

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

Captures a baseline snapshot of a Jetson device's module model, L4T version, kernel, OS version, and power mode for performance testing or verification.

Extract false-positive and false-negative gaps from VLM binary-classification-question predictions by comparing model responses against ground truth, producing a structured JSONL file and summary report for downstream root-cause analysis.

Trains, evaluates, exports, quantizes, and runs inference for a Grounding DINO model that detects objects described by text prompts without a fixed class vocabulary.

Generates custom safety policies for NVIDIA Nemotron content-safety guardrails, producing a Markdown policy, JSON taxonomy, and inference prompts from rough user input.

Performs deep root cause analysis on NVIDIA TAO Visual ChangeNet classification experiments, using image-evidence-driven investigation to diagnose model failures and produce actionable reports.

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

Start, query, and stop a TAO inference microservice for a specific network architecture by delegating container execution to the appropriate platform skill.

Accelerate pandas workflows with GPU DataFrames using cuDF and dask-cuDF for ETL, joins, groupby, and large-scale data processing.

Pull and verify the official Holoscan SDK container from NGC, selecting the correct CUDA/arch tag for the host GPU and validating with bundled Python and C++ examples.

Plan, debug, tune, evaluate, export, or deploy public Nemotron embedding and reranking retrieval recipes using the current checkout.

Converts NVIDIA TAO DAFT datasets between supported formats using the `tao-daft convert` CLI.

Fine-tune Cosmos Reason video QA models using supervised fine-tuning with FSDP parallelism, including dataset preparation, spec construction, and AutoML support.

Deploy and operate the VSS 3.2 GA RT-Embed Video Embedding microservice using Docker Compose, covering GPU prerequisites, REST API usage for file uploads, text/video embeddings, live RTSP streams, Redis/Kafka/OTel integration, and troubleshooting.

Reduce per-token latency on Jetson vLLM servers by appending speculative decoding configuration, with guidance on when to enable and how to benchmark the improvement.

Train, evaluate, export, and run inference for monocular depth estimation models using Metric Depth Anything v2 or Relative Depth Anything architectures via the TAO toolkit.

Trains, evaluates, exports, and runs inference on FoundationStereo models for stereo depth estimation and 3D reconstruction from stereo image pairs.

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Deploy a standalone RT-VLM dense-captioning microservice and exercise its REST API endpoints for file upload, caption generation, streaming, chat completions, and Kafka integration.

Train, evaluate, export, and run inference on TAO action-recognition models for classifying temporal actions in video clips using RGB, optical flow, or joint input.

Finetunes the NV-Generate-CTMR MR-brain diffusion UNet from user-supplied NIfTI training volumes using a wrapper that stages configs and delegates to upstream scripts.

Trains, evaluates, exports, quantizes, and runs inference for a Mask Grounding DINO model for open-set instance segmentation guided by text prompts.