Skill directory
Agent skills
Focused instruction packs that teach a coding agent one job well. Browse the catalog and use any of them inside a RiverX project.
18,175Skills
1,902Publishers
249Official
Tao Train Rtdetrnvidia/skillsRT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with025Tao Train Segformernvidia/skillsSegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature023Tao Train Single Stepnvidia/skillsStandard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset07Tao Train Sparse4dnvidia/skillsSparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable023Tao Train Visual Changenetnvidia/skillsVisual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,041Tao Validate Dataset Formatnvidia/skillsRun `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do06Tilegym Adding Cutile Kernelnvidia/skillsAdd a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.05Tilegym Converting Cutile To Julianvidia/skillsConverts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when converting, porting, or translating cuTile Python kernels to Julia cuTile.jl, or debugging/optimizing existing Julia cuTile translations.017Tilegym Converting Cutile To Tritonnvidia/skillsConverts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.025Tilegym Cutile Autotuningnvidia/skillsUse when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.018Tilegym Cutile Pythonnvidia/skillsExpert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.037Tilegym Improve Cutile Kernel Perfnvidia/skillsIteratively 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.011Tilegym Monkey Patch Kernels To Transformersnvidia/skillsIntegrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.010Vss Ask Videonvidia/skillsUse 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.06Vss Deploy Dense Captioningnvidia/skillsUse this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.011Vss Deploy Detection Tracking 2dnvidia/skillsUse this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM, embedding, or analytics — use the matching vss-* skill.051Vss Deploy Detection Tracking 3dnvidia/skills>014Vss Deploy Profilenvidia/skillsUse to select, configure, deploy, verify, debug, or tear down a VSS profile (base, search, lvs, warehouse, edge). Not for standalone microservices — use the vss-deploy-* skill.030Vss Deploy Video Embeddingnvidia/skills>012Vss Generate Video Calibrationnvidia/skillsUse to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Do not use for non-AMC calibration or runtime analytics.012Vss Generate Video Reportnvidia/skillsUse this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.08Vss Manage Alertsnvidia/skillsUse for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.020Vss Manage Video Io Storagenvidia/skillsUse to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.011Vss Query Analyticsnvidia/skillsUse 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.06Vss Search Archivenvidia/skillsUse this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).08Vss Setup Behavior Analyticsnvidia/skillsUse to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.011Vss Setup Video Analytics APInvidia/skillsUse to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.09Vss Summarize Videonvidia/skillsUse to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.014
Skills, installed in one click
Start building freePut a skill to work
Open any project, search the Skills panel in the chat, and the agent picks it up from there.