NVIDIA/TensorRT-LLM/ad-accuracy-debug A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/ad-accuracy-debug
Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline).
Home › Agent Skills
Agent Skills
Browse SKILL.md-based agent skills for Claude Code, Codex, Cursor, Gemini CLI and more.
Filters (1 active)
Category
Development and Testing65Product Management Skills by Pawel Huryn65Product Manager Skills by Dean Peters46Marketing Skills by Corey Haines32Specialized Domains32Productivity and Collaboration31Megatron-Bridge29TensorRT-LLM25NemoClaw23Marketing22Security Skills by Trail of Bits Team21Context Engineering19NeMo-RL14Megatron-Core12cuopt12Advertising Skills by Kim Barrett12video-search-and-summarization10Model-Optimizer8n8n Automation7TileGym7NeMo-Gym5NeMo-Evaluator-Launcher3deepstream2CUDA-Q1Language
Python25Activity
Active25Install method
SKILL.md25Results
NVIDIA/TensorRT-LLM/ad-add-fusion-transformation A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/ad-add-fusion-transformation
Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout.
NVIDIA/TensorRT-LLM/ad-conf-check A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/ad-conf-check
Check whether AutoDeploy YAML configs were actually applied by analyzing server logs and optionally graph dumps (AD_DUMP_GRAPHS_DIR).
NVIDIA/TensorRT-LLM/ad-graph-dump A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/ad-graph-dump
Enable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR.
NVIDIA/TensorRT-LLM/ad-layer-visualizer A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/ad-layer-visualizer
Visualize a specific transformer decoder layer from an AutoDeploy FX graph text dump as a hierarchical DOT/PNG diagram.
NVIDIA/TensorRT-LLM/ad-model-onboard A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/ad-model-onboard
Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.
NVIDIA/TensorRT-LLM/exec-local-compile A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/exec-local-compile
Compile TensorRT-LLM on a compute node inside a Docker container.
NVIDIA/TensorRT-LLM/exec-slurm-compile A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/exec-slurm-compile
Compile TensorRT-LLM on a SLURM cluster.
NVIDIA/TensorRT-LLM/kernel-cute-writing A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/kernel-cute-writing
Write and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations.
NVIDIA/TensorRT-LLM/kernel-tileir-optimization A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/kernel-tileir-optimization
Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+).
NVIDIA/TensorRT-LLM/kernel-triton-writing A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/kernel-triton-writing
ONLY for OpenAI Triton (@triton.jit) kernel development.
NVIDIA/TensorRT-LLM/perf-analysis A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/perf-analysis
Performance analysis coordination workflow.
NVIDIA/TensorRT-LLM/perf-host-analysis A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/perf-host-analysis
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces.
NVIDIA/TensorRT-LLM/perf-host-optimization A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/perf-host-optimization
Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned).
NVIDIA/TensorRT-LLM/perf-nsight-compute-analysis A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/perf-nsight-compute-analysis
Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp stall analysis, metr...
NVIDIA/TensorRT-LLM/perf-nsight-systems A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/perf-nsight-systems
Nsight Systems (nsys) CLI for system-level timeline profiling.
NVIDIA/TensorRT-LLM/perf-optimization A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/perf-optimization
Performance optimization coordination playbook.
NVIDIA/TensorRT-LLM/perf-torch-cuda-graphs A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/perf-torch-cuda-graphs
Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, m...
NVIDIA/TensorRT-LLM/perf-torch-sync-free A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/perf-torch-sync-free
Identify and eliminate host-device synchronizations in PyTorch code.
NVIDIA/TensorRT-LLM/perf-workload-profiling A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/perf-workload-profiling
Code instrumentation for timing workloads.
NVIDIA/TensorRT-LLM/trtllm-code-contribution A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/trtllm-code-contribution
Best practices for contributing code to TensorRT-LLM.
NVIDIA/TensorRT-LLM/trtllm-codebase-exploration A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/trtllm-codebase-exploration
Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations.
NVIDIA/TensorRT-LLM/trtllm-flashinfer-upgrade A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/trtllm-flashinfer-upgrade
Upgrade flashinfer-python version in TensorRT-LLM.
NVIDIA/TensorRT-LLM/trtllm-moe-develop A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/trtllm-moe-develop
Review, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability.
NVIDIA/TensorRT-LLM/trtllm-serve-config-guide A Agent Skill Active
NVIDIA/skills/skills/TensorRT-LLM/trtllm-serve-config-guide
Generate a source-backed starting `trtllm-serve --config` YAML for basic aggregate single-node PyTorch serving, aligned with checked-in TensorRT-LLM configs and deployment docs.