New and Recently Updated Skills
Verified Agent Skills sorted by source update date. This is where newly published SKILL.md files should surface first.
Tao Train Optical Inspection
Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing
Tao Train Pointpillars
PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a
Tao Train Pose Classification
Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences
Tao Train Reid
Person re-identification (ReID). Learns discriminative embeddings to match the same person across different
Tao Train Rtdetr
RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with
Tao Train Segformer
SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature
Tao Train Single Step
Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset
Tao Train Sparse4d
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable
Tao Train Visual Changenet
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,
Tao Validate Dataset Format
Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do
Tilegym Adding Cutile Kernel
Add 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.
Tilegym Converting Cutile To Julia
Converts 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.
Tilegym Converting Cutile To Triton
Converts 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.
Tilegym Cutile Autotuning
Use 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.
Tilegym Cutile Python
Expert 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.
Tilegym 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.
Tilegym Monkey Patch Kernels To Transformers
Integrate 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.
Vss Ask Video
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.
Vss Deploy Dense Captioning
Use 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.
Vss Deploy Detection Tracking 2d
Use 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.
Vss Deploy Detection Tracking 3d
Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video files, and RTSP streams, and chains to `vss-generate-video-calibration` when calibration is missing. Use `vss-deploy-profile` for the full warehouse blueprint and `vss-deploy-detection-tracking-2d` for single-camera 2D detection.
Vss Deploy Profile
Use 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.
Vss Deploy Video Embedding
Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown.
Vss Generate Video Calibration
Use 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.
Vss Generate Video Report
Use 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.
Vss Manage Alerts
Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.
Vss Manage Video Io Storage
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.
Vss Query Analytics
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.
Vss Search Archive
Use 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).
Vss Setup Behavior Analytics
Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
Vss Setup Video Analytics Api
Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
Vss Summarize Video
Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.
Warp Compile Time Optimizer
Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start or stalls at the first wp.launch; seconds of compiling before real work begins; JIT modules recompiling on every run or every CI job. Only applies when the code being optimized uses Warp kernels. Not for steady-state kernel runtime, memory, correctness, building Warp itself from source, or nvcc/C++ build times.
Warp Debug Gradients
Use to diagnose and fix incorrect gradients in differentiable Warp programs. Anything trained, optimized, calibrated, or fit through Warp kernels depends on wp.Tape gradients, so treat any misbehavior of such a workflow as a gradient problem until proven otherwise — use this when training diverges or NaNs, won't train at all, stalls or plateaus above the expected loss, converges to a wrong or biased answer, is worse than a reference implementation, works at small scale but fails at production scale, or fails a QA/validation recheck. Also for explicit symptoms — exploding, NaN/inf, zero, or subtly wrong gradients, suspected wp.Tape/backward issues, gradcheck failures — but users usually describe only the surface symptom ("the sim explodes", "the fit gets dragged toward outliers") without mentioning gradients: make that leap. Not for forward-only Warp work, build/install problems, or autograd issues in other frameworks without Warp.
Warp Eval
Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-heavy loops, many small launches, host fallbacks, or large intermediates. CPU-only code and absent GPU dependencies are normal unless NVIDIA is prohibited. Exclude required cross-vendor or CPU-only deployment, vendor-lowered dense or NN layers, general Warp API questions, and already-selected Warp kernels. Contribution policy alone is not exclusion.
Asc Ad Hoc Distribution
Prepare, publish, resume, and verify private iOS release-testing installs with asc distribute. Use when distributing an IPA to registered devices outside TestFlight, reconciling ad hoc profiles, publishing through caller-owned S3-compatible storage, or diagnosing a resumable private distribution run.
Asc Analytics Reports
Collect, download, and verify App Store Connect Analytics reports with asc. Use when users need to discover analytics report requests, select report instances by processing date or granularity, download every segment, or verify downloaded files against Apple's size and MD5 metadata before analysis.
Asc App Create Ui
Create a new App Store Connect app record via browser automation. Use when there is no public API for app creation and you need an agent to drive the New App form.
Asc Apple Ads
Use when managing Apple Ads with asc, including OAuth profiles, ad-account discovery, Platform API v1 campaigns and targeting, reports, assets, recommendations, guarded mutations, raw requests, and Campaign Management API v5 migration.
Asc Aso Audit
Run an offline ASO audit on canonical App Store metadata under `./metadata` and surface keyword gaps using Astro MCP. Use after pulling metadata with `asc metadata pull`.
Asc Build Lifecycle
Track build processing, find latest builds, and clean up old builds with asc. Use when managing build retention or waiting on processing.
Asc Cli Usage
Guidance for using asc cli in this repo (flags, output formats, pagination, auth, and discovery). Use when asked to run or design asc commands or interact with App Store Connect via the CLI.
Asc Crash Triage
Triage TestFlight crashes, beta feedback, and performance diagnostics using asc. Use when the user asks about TF crashes, TestFlight crash reports, beta tester feedback, app hangs, disk writes, launch diagnostics, or wants a crash summary for a build or app.
Asc Id Resolver
Resolve App Store Connect IDs (apps, builds, app and digital-goods versions, groups, testers) from human-friendly names using asc. Use when commands require IDs.
Asc Localize Metadata
Automatically translate and sync App Store metadata (description, keywords, what's new, subtitle) to multiple languages using LLM translation and asc CLI. Use when asked to localize an app's App Store listing, translate app descriptions, or add new languages to App Store Connect.
Asc Metadata Sync
Sync, validate, and apply App Store metadata with the current asc canonical metadata workflow. Use when updating metadata, localizations, keywords, or migrating legacy fastlane metadata.
Asc Notarization
Archive, export, and notarize macOS apps using xcodebuild and asc. Use when you need to prepare a macOS app for distribution outside the App Store with Developer ID signing and Apple notarization.
Asc Ppp Pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.