所有 Skills

cuopt-skill-evolution

After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.

cuopt-numerical-optimization-api-cli

LP, MILP, and QP (beta) with cuOpt — CLI only (MPS/LP/QPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from an MPS or LP file via command line.

avoid-ai-writing

3.1Kresearch-knowledge

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.

conorbronsdon

tilegym-converting-cutile-to-julia

3.1Ktesting-qa

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.

predictingthepast

3.1Kresearch-knowledge

Ancient text restoration, attribution, dating, contextualization, and embedding via Aeneas (Latin) / Ithaca (Ancient Greek). Use when asked to "restore", "attribute", "date", "contextualize", "find parallels", "where was it written", "when was it written", "embed", or "analyze" an ancient text, inscription, or epigraphic document, or when the user mentions "Aeneas", or "Ithaca".

google-deepmind

tilegym-cutile-autotuning

3.1Ktesting-qa

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-converting-cutile-to-triton

3.1Ktesting-qa

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-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.

tao-train-nvpanoptix3d

NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation

tao-train-grounding-dino

3.1Kdevops-cloud

Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for

tao-train-action-recognition

Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for

tao-train-reid

Person re-identification (ReID). Learns discriminative embeddings to match the same person across different

tao-train-pose-classification

Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences

tao-analyze-gaps-vlm-bcq

Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions.

tao-train-visual-changenet

Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,

tao-train-metric-learning-recognition

3.1Kdevops-cloud

Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for

tao-train-mask2former

3.1Kdevops-cloud

Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with

tao-run-automl-deft-pipeline

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 on the DEFT-augmented dataset. Use when the user asks to "run the AOI workflow", "fine-tune my PCB AOI model end-to-end", "improve my AOI ChangeNet model", or "AOI workflow with AutoML" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. "run JUST the DEFT loop", "skip AutoML, only DEFT"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include "run the AOI workflow", "AOI end-to-end", "AutoML + DEFT", "AutoML then DEFT", "tune hyperparameters then DEFT", "DEFT with AutoML at both ends", "warm-start DEFT", "improve my AOI model".

tao-train-dino

DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with

tao-run-platform

TAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM,

tao-run-deft-aoi

Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and deployment gating until FAR / recall KPI targets are met. Use for prompts like "run the DEFT loop", "fine-tune until FAR below 0.1% at recall=100%", or "improve my AOI ChangeNet model with RCA and synthetic defects"; do not use for standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.