Overview of `workflows/catheter_navigation/` (fluorosim DRR, XPBD physics, vasculature digital twin).
Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing
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…
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backen — from…
Person re-identification (ReID). Learns discriminative embeddings to match the same person across different
Overview of `workflows/agentic/` (IsaacLab-Arena + GR00T/openpi). Use when the user asks what i4h workflow is, what's supported, or where to start.
Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences
Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.
Guide for developing the OpenShell TUI — a ratatui-based terminal UI for the OpenShell platform. Covers architecture, navigation, data fetching, theming, UX conventions, and…
Summarize a video by calling the VLM NIM or the Long Video Summarization (LVS) microservice directly.
Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for
Validate and monitor OpenShell GitHub issues and PRs using the gator:* state machine. Use when asked to triage issues/PRs for project validity, gate PRs, run gator, validate…
Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.
Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions.
SECURITY: the DOCA UROM Service binary has NO standalone access control (no authz list / `allowed_host` / `allowed_users` / `auth_token`) — access is governed ENTIRELY by DOCA…
Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval.
Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting.
Code style and quality rules for Megatron Bridge — ruff configuration, naming conventions, type hints, mypy rules, docstrings, copyright headers, logging, and the code review…
Author a new Jetson target-platform profile (reference_devkit + optional custom_carrier) and update the active pointer. Use to create a target; not for switching existing profiles.
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable
Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement…
Upgrade flashinfer-python version in TensorRT-LLM. Fetches the latest releases from GitHub (stable and nightly), compares with the current pinned version, lets the user pick a…
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimod — from…
Used for running NV-Segment-CTMR on CT or MRI NIfTI volumes and recording label-map evidence. Not for clinical interpretation.
Use SkillSpector to scan Claude Code, Codex, Gemini, MCP, and other agent skills for vulnerabilities, malicious patterns, prompt injection, data exfiltration, and supply-chain…
Search video archives using natural language — find events, objects, actions, and people across recorded video using fusion search (Cosmos Embed1 semantic search + CV attribute…
Detect and fix drift across agent-first infrastructure files. Ensures skill inventories, workflow chains, architecture tables, issue/PR templates, and cross-references stay…
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism config — from…
Per-pin SFIO / direction / initial-state configurator for a Jetson Orin or Thor custom carrier from the pinmux XLSM. Do NOT use for kernel-DT overlay or ODMDATA edits.
Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors.
Use when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled using live SDK APIs, authenticated NVIDIA samples, and NVIDIA…
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
Given a GitHub issue number, plan and implement the work described in the issue. Supports direct user requests and unattended queue processing through the `agent:*` workflow…
Generate video summary reports using the VSS video_search_frag extension with Long Video Summarization (LVS), Enterprise RAG knowledge retrieval, and human-in-the-loop parameter…
Enable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.
Switch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target; not for authoring profiles — use…
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain cla — from…
Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds
Compile a PyTorch model to a TensorRT engine via Torch-TensorRT — AOT or JIT — under the new strong-typing default.
Extract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in the profile.
Use 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.
Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline). Use when an AutoDeploy model's eval score is significantly below the reference…
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
Refresh golden values from a GitHub Actions workflow run (failing-only or all jobs), score the change with average normalized relative differences, and produce a PR-ready summary.
Runs the morning maintainer standup for NemoClaw. Triages the backlog, determines the day's target version, labels selected items, surfaces stragglers from previous versions, and…
Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do
Used for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr. Not for paired masks or production training data.
Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed
Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data without review.
Attempt to fix a security issue tracked in <tracker> by implementing the change in a public <upstream> PR.
Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for
Launch and supervise OpenShell gator agents. Use when starting gator on issues or PRs, checking gator sandboxes, building the gator sandbox image, restarting stuck gators,…
Configuration conventions for NeMo-RL. YAML is the single source of truth for defaults. Covers TypedDict usage, exemplar YAML updates, and forbidden default patterns.
Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use…
OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a
BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view
Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts