Official Agent Skills
Skills published by verified organisations. Every one is reviewed before listing, and the publisher's identity is checked, not just claimed.
- nvidia BundleDoca Dpa Hl Tracer
Use this skill when the user runs doca_dpa_hl_tracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR submission, completion drain) — picking TRACE vs CRIT, tuning the JSON config (file-size limits + file_size_limit_policy, thread priorities/cores), decoding against the matching DPA-side ELF, or diagnosing empty/noisy captures. Trigger even when the user does not explicitly mention "DOCA DPA tracer" or "high-level tracer" — typical implicit phrasings include "DPA kernel returns wrong result but host completions look clean", "kernel-entry to first-comm latency is huge", "RDMA WR to drain gap on the DPA", "trace file truncated mid-run", "TRACE doubled my DPA latency", or "tracer wrote a file but parser shows zero events". Refuse and route elsewhere for writing DPA kernels, DPA-Comms/DPA-Verbs programming, raw per-cycle DPA profiling, host-side doca-dpa debugging, or production DPA telemetry — those belong to other skills.
23k - nvidia BundlePaidf Auto Labeling
Use when a user needs to get started with PAIDF Auto-Labeling, plan a scenario, run or debug a shipped cookbook, author prompts or cookbooks, migrate a pipeline, or configure a stage. Confirm critical inputs (data path, output path, endpoints) and ask when any are missing. This is a router: read the matching reference instead of inventing a workflow.
23k - nvidia BundleHolohub App Lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.
23k - nvidia BundleDoca Flow Dpa Provider
Use this skill when the user is doing hands-on DOCA Flow DPA Provider work — exporting a `doca-flow` pipe or external resource (index-selector/memory) into BlueField DPA address space so a DPACC-built kernel can read counters, mutate hash-pipe entries, and update/read memory or index-selector resources inline with Flow. Covers per-port `doca_flow_dpa_ctx`, three queue types (general/resources-write/resources-read), the order-sensitive export handshake (`_export_prepare` → add entries → `_export` → `_get_device_addr`), and DPA-side device API. Trigger even when the user does not say "DOCA Flow DPA Provider" — implicit phrasings include "DPA kernel never sees entries in the exported pipe", "BAD_STATE from `_pipe_export`", "how do I disable a hash entry from a DPA kernel", "DPA memory read returns no value", or "DPA-side post keeps returning AGAIN". Refuse and route elsewhere for `doca-flow` pipe construction, generic host-side DPA (`doca-dpa`), or DPA-side kernel-writing — those belong to other skills.
23k - nvidia BundleNemo Relay Plugin Build
Use this skill when building or packaging reusable NeMo Relay runtime behavior as an embedded configuration component or a manifest-backed `rust_dynamic` native or `worker` gRPC plugin, with deterministic validation and rollback-safe registration.
23k - nvidia BundleDoca Gpunetio Ib Write Bw
Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server benchmark — a CUDA kernel on the client posts RDMA WRITE work requests through the doca-gpunetio device-side surface to measure sustained GPU-driven WRITE bandwidth on a GPU+IB-device pair. Trigger even when the user does not explicitly mention "doca-gpunetio-ib-write-bw" or "GPUNetIO" — typical implicit phrasings include "measure WRITE BW when the GPU posts the WRs", "BW swings between runs on the same flags", "is the NIC saturated or am I CPU-bound on the CUDA kernel", "meson compile fails for the GPUNetIO bw tool", "nvidia_peermem isn't picking up my GPU buffer", or "GPU-initiated WRITE throughput vs CPU-initiated perftest". Refuse and route elsewhere for general doca-gpunetio library work, DOCA install, the GPU-initiated WRITE latency analog, the CPU-initiated upstream perftest, or application-level end-to-end throughput — those belong to other skills.
23k - nvidia BundlePaidf Orchestration Write Dag
Use when a user describes a custom PAIDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-labeling only, detection+captioning only, or image attribute augmentation without full auto-labeling — that no existing DAG in airflow/dags/workflows/ covers, and asks for a new Kubernetes DAG. Also use to check that a generated or existing DAG's model/container/prompt choices match an external spec document (e.g. a PAIDF `launchable.md`).
23k - nvidia BundleTilegym Improve Cutile Kernel Perf
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
23k - nvidia BundleNemo Automodel Distributed Training
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
23k - nvidia BundlePhysical AI Video Data Augmentation
Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. Trigger keywords: video data augmentation, data enrichment, auto labeling, VDA demo, OSMO workflow, pseudo labeling.
23k - nvidia BundleNemo Relay Debug Runtime Integration
Use this skill when NeMo Relay is installed or imported but application-side runtime behavior is missing or incorrect, including load failures, inactive scopes, missing events, and plugin or adaptive wiring problems.
23k - nvidia BundlePhysical AI Image Attribute Augmentation
Run the PAIDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented dataset generation. Select for requests about image attribute augmentation, person attribute search, person re-identification data, clothing augmentation, attribute captions, augmentation payloads, run status, or result retrieval. Runs environment setup first when controller readiness is unknown. Not for video or defect-image generation.
23k - nvidia BundleCudaq Guide 2
Use for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.
23k - nvidia BundleNv Segment Ct 2
Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.
23k - nvidia BundleVss Ask Video 2
Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.
23k - nvidia BundleDeepstream Dev 2
NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
23k - nvidia BundleVss Query Analytics 2
Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.
23k - nvidia BundleDynamo Recipe Runner 2
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
23k - nvidia BundleEarth2studio Discover 2
Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.
23k - nvidia BundleNemo Mbridge Perf Moe Comm Overlap 2
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
23k - huggingface BundleHuggingface Spaces 3
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
11.4k - microsoft BundleAzure Local Multi Rack
Plan, deploy, operate, and troubleshoot multi-rack (rack scale) deployments of Azure Local — preintegrated racks scaling to hundreds of machines, built on Network Fabric Controller, Cluster Manager, SAN storage, and managed network fabric. Use for the Microsoft.NetworkCloud and Microsoft.ManagedNetworkFabric control plane. NOT for standard 1-16 node Azure Local, and NOT for rack-aware clusters (two racks as availability zones, up to 8 nodes, synchronous replication) — those are standard scale. WHEN: multi-rack, rack scale Azure Local, aggregation rack, compute rack, Network Fabric Controller, NFC, Cluster Manager, network fabric, isolation domain, az networkcloud, az networkfabric, multi-rack logical network, multi-rack Arc VM.
195k - dotnet BundleMigrate Nunit To Mstest
Convert .NET tests from NUnit 3/4 to MSTest v4 while preserving VSTest or MTP. Use for replacing NUnit/NUnit3TestAdapter packages, Test/TestCase/ TestCaseSource/Values attributes, constraint assertions, SetUp/TearDown, OneTimeSetUp, SetUpFixture, FixtureLifeCycle, TestContext, categories, retries, timeouts, and NUnit parallelization. Also use when a "convert NUnit to MSTest" request may already be migrated: inspect and report the no-op. Do not use for NUnit version upgrades, xUnit/TUnit conversion, MSTest upgrades, or runner-only VSTest-to-MTP migration.
22.1k - adobe BundleDispatcher 2
Single entry point for all AEM as a Cloud Service Dispatcher skills. Covers config authoring, technical advisory, incident response, performance tuning, security hardening, and full lifecycle orchestration for the Adobe Dispatcher Apache HTTP Server module and its HTTPD/dispatcher configuration.
1.6k - adobe BundleAem Workflow 2
Single entry point for all AEM as a Cloud Service Workflow skills. Covers workflow model design, custom process step and participant chooser development, launcher configuration, workflow triggering, and production support including debugging stuck/failed workflows, triaging incidents with Cloud Manager logs, thread pool analysis, and Sling Job diagnostics for the Granite Workflow Engine.
1.6k - google BundleGoogle Analytics Data API Basics 2
Manages Google Analytics reporting data, enables the Analytics Data API via the Cloud CLI, and creates reports using the Google Analytics Data API (v1beta). Use when you need to interact with Google Analytics properties, run customized analytics reports, query metrics (like activeUsers, screenPageViews) and dimensions (like city, date), check metrics and dimensions compatibility, or verify API enablement. Don't use for Google Analytics Admin API operations (e.g., creating properties, managing users) or for front-end tracking installation.
24.3k - google BundleGoogle Analytics Admin API Basics 2
Manages Google Analytics account and property settings, enables the Analytics Admin API via the Cloud CLI, lists accounts and properties, and manages data streams, custom dimensions, conversion events, and integrations. Use when you need to programmatically configure Google Analytics accounts, provision properties, manage data retention, configure Measurement Protocol secrets, or manage Firebase and Google Ads links.
24.3k - adobe BundleCommerce App Init 2
Scaffold a new Adobe Commerce app using the aio-commerce-sdk. Creates the base project structure and app.commerce.config file with metadata. Use when the user wants to create a new Commerce app from scratch or initialize a bare Commerce app project. After scaffolding, chains to appbuilder-project-init for Developer Console setup (project, workspace, API subscriptions) when the user wants to deploy. Does not configure extensibility domains — use commerce-app-eventing, commerce-app-webhooks, commerce-app-business-config, commerce-app-admin-ui, or commerce-app-storage for that.
1.6k - adobe SkillWorkflow Triaging 2
Triage AEM Workflow issues on AEM 6.5 LTS and AMS by classifying symptoms, gathering the right logs and metrics, and mapping to runbooks or Splunk searches. Use when the user asks for workflow activity/errors on a 6.5 host, needs to classify a Jira ticket, or wants to know what to collect for workflow debugging.
1.6k - adobe BundleAnalyze And Plan 2
Use this when you need to define acceptance criteria, write requirements, scope work, or create a definition of done for AEM Edge Delivery Services (EDS) tasks such as new blocks, variants, behavior modifications, CSS-only changes, or bug fixes. Covers analyzing development requirements, producing task breakdowns, identifying edge cases, and documenting the analysis.
1.6k - adobe BundleCommerce App Eventing 2
Add or modify Commerce and external event subscriptions, configure event field extraction and filter rules in an Adobe Commerce app. Use when the user wants to set up event-driven workflows triggered by Commerce operations (such as order placement or catalog changes) or third-party systems. Requires a base app initialized with commerce-app-init.
1.6k - adobe BundleCommerce App Webhooks 2
Add or modify webhook interceptors in an Adobe Commerce app. Use when the user wants to intercept Commerce operations to validate input, append data, or modify behavior — before or after execution. Requires a base app initialized with commerce-app-init.
1.6k - adobe BundleTechnical Advisory 2
Provide advisory guidance for the Adobe Dispatcher Apache HTTP Server module and related HTTPD configuration in AEMaaCS cloud workflows only, with public-doc citations and cloud-specific MCP verification plans. Use for conceptual questions such as `statfileslevel`, filter rules, URL decomposition, cache invalidation behavior, rewrite behavior, and security headers.
1.6k - adobe BundleWorkflow Debugging 2
Debug AEM Workflow issues on AEM as a Cloud Service — stuck workflows, failed steps, missing Inbox tasks, launcher failures, stale instances, thread pool exhaustion, queue backlogs, purge failures, and permissions errors. Use when the user reports workflow problems on Cloud Service, asks why a workflow is stuck or failed, needs step-by-step troubleshooting, or provides thread dumps, configuration status output, or Sling Job console output for analysis.
1.6k - adobe BundleUnbounded Query 2
AEM Cloud Service expert skill — handle an explicitly-unbounded query (`p.limit=-1` predicate or JCR `setLimit(-1)`): bound it when capping is provably safe, otherwise flag it for human pagination. Use for "bound my query", "unbounded query", "query causing OOM", or a scan that flags `p.limit=-1`. Top CSO OOM cause: an unbounded result set traversed in a loop fills the heap and saturates the instance. The analyzer locates the explicit markers; the recipe triages each by how the result is consumed — single-result → 1, already-bounded list → N, iterate-all on the request path → escalate. Never silently cap a result the caller reads in full.
1.6k - adobe SkillAdobe Anydocx
MANDATORY when a Word/DOCX task's source content is an uploaded PDF — including when the PDF's text is already extracted and visible in the conversation. Covers: 'convert this pdf to word/docx', 'turn this pdf into a word document'. Requires viewing THIS file before defaulting to hand-authoring a document with python-docx. Route to adobe-anypdf's pdf_export (target_format: docx) first. Do NOT use this file when there is no PDF source — a from-scratch document request, or editing an existing .docx, is the public docx skill's job, not this one.
1.6k