Every Hermes skill, in one place

185 official skills from the Hermes Agent repository plus 101,376 community entries. Community index checked 2026-11-20 (UTC). Read community skills at their original sources.

Open baoyu-article-illustrator in the official library

Community index generated 2026-11-20 (UTC), checked 2026-11-20 (UTC).

Skill results

34 official + 4,295 community matches. Page 167 of 180.

Official skills first, then community.

Best match / quality.

PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then applies 2D detection ; used in autonomous driving and robotics. Use when training, evaluating, ex

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-pointpillars
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences into action categories from pose-keypoint data. Use when training, evaluating, exporting, or running inference for a TAO pose-cla

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-pose-classification
AI models & providersSource (opens in a new tab)

Person re-identification (ReID). Learns discriminative embeddings to match the same person across different camera views, based on metric learning. Use when training, evaluating, exporting, or running inference for a TAO person re-identific

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-reid
AI models & providersSource (opens in a new tab)

RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, evaluating, distilling,

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-rtdetr
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time segmentation tasks. Use when training, evaluating, exporting, quantizing, or running inference for

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-segformer
AI models & providersSource (opens in a new tab)

Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset without iterative data augmentation, AutoML, or DEFT loops. Trigger phrases include "single train run", "train then evaluate then

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-single-step
AI models & providers · Automation & multi-agentSource (opens in a new tab)

Prepare calibrated multi-camera data and train, evaluate, run inference, export, or quantize TAO Sparse4D 3D detection and tracking models. Includes 2D-to-3D geometric distillation with released LTT weights. Use for Sparse4D adaptation and

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-sparse4d
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for PCB defect detection or visual inspection, comparing image pairs for PASS/NO_PASS

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-train-visual-changenet
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Port a published computer vision paper's official code and training recipe onto a customer's own dataset, or diagnose why such a transfer produced bad numbers. Use this whenever someone wants to reproduce a CV paper, run a paper's repo on t

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tao-validate-recipe-transfer
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Simulates biochemical kinetic models from SBML or Antimony with Tellurium and libRoadRunner, checks model units, compares deterministic parameter perturbations, and exports and replays SBML plus SED-ML COMBINE archives. Use for reaction-net

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install K-Dense-AI/scientific-agent-skills/skills/tellurium
AI models & providersSource (opens in a new tab)

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install synthetic-sciences/openscience/backend/cli/skills/ml-training/tensorboard
Coding & developer tools · AI models & providersSource (opens in a new tab)

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install synthetic-sciences/openscience/backend/cli/skills/ml-inference/tensorrt-llm
Coding & developer tools · AI models & providersSource (opens in a new tab)

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.

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tilegym-cutile-python
AI models & providers · Automation & multi-agentSource (opens in a new tab)

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

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install NVIDIA/skills/skills/tilegym-monkey-patch-kernels-to-transformers
AI models & providersSource (opens in a new tab)

Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install synthetic-sciences/openscience/backend/cli/skills/coding/timesfm-forecasting
Coding & developer tools · AI models & providersSource (opens in a new tab)

Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastru

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install synthetic-sciences/openscience/backend/cli/skills/cloud-compute/tinker
AI models & providers · Languages & regionsSource (opens in a new tab)

Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provi

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install synthetic-sciences/openscience/backend/cli/skills/cloud-compute/tinker-training-cost
AI models & providers · Cost, speed & monitoringSource (opens in a new tab)

Supports PyTorch Geometric (PyG) graph neural networks ; node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not fo

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install K-Dense-AI/scientific-agent-skills/skills/torch-geometric
AI models & providersSource (opens in a new tab)

Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code im

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install K-Dense-AI/scientific-agent-skills/skills/torchdrug
Memory & notes · AI models & providersSource (opens in a new tab)

PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction,

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install synthetic-sciences/openscience/backend/cli/skills/chemistry/torchdrug
Memory & notes · AI models & providersSource (opens in a new tab)

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install huggingface/skills/skills/train-sentence-transformers
AI models & providers · Cost, speed & monitoringSource (opens in a new tab)

Build training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. Use when formatting production logs into SFT data, distilling from frontier APIs, or preparing data for fine-tuni

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install synthetic-sciences/openscience/backend/cli/skills/ml-training/training-data-pipeline
AI models & providersSource (opens in a new tab)

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/c

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install synthetic-sciences/openscience/backend/cli/skills/ml-training/megatron-core
AI models & providers · Languages & regionsSource (opens in a new tab)

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patte

Community skill. Read the source first. Listed does not mean tested with Hermes.

hermes skills install synthetic-sciences/openscience/backend/cli/skills/ml-training/transformer-lens
AI models & providers · Web, research & browsingSource (opens in a new tab)

Entries with unclear source links are withheld. Some restricted-license records have source links only. Full skill instructions stay at the original source.