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

52 official + 12,194 community matches. Page 424 of 511.

Official skills first, then community.

Best match / quality.

Run AnomalyGenNext 1.1 inference from a native testcase or a prepared generation plan, then publish validated fine-grained and binary COCO labels. Use for synthetic object-detection defect generation, not model training.

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

hermes skills install NVIDIA/skills/skills/tao-generate-od-defects
Coding & developer tools · AI models & providersSource (opens in a new tab)

Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to "integrate a HuggingFace model into TAO", "add an HF model t

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

hermes skills install NVIDIA/skills/skills/tao-port-huggingface-model
Coding & developer tools · AI models & providersSource (opens in a new tab)

Run iterative DINOv3 SSL DEFT data selection and retraining from an unlabeled pool, using GRIT or multi-task weakness and fixed-encoder retrieval. Use for active-learning-style DINOv3 mining, not plain pretraining/fine-tuning (tao-train-din

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

hermes skills install NVIDIA/skills/skills/tao-run-dinov3-ssl-deft
Coding & developer tools · Automation & multi-agentSource (opens in a new tab)

The Docker execution platform for TAO jobs ; a local daemon or a remote GPU box via DOCKER_HOST=ssh://user@host. Implements the four-verb consumer contract (submit/status/logs/cancel) over the docker CLI, wired to the job-record, tao-data-i

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

hermes skills install NVIDIA/skills/skills/tao-run-on-docker
Coding & developer toolsSource (opens in a new tab)

Run a Python training/eval script directly in an existing local virtualenv ; no docker, no container. Implements the four-verb consumer contract (submit/status/logs/cancel) over a vendored process-lifecycle runner with durable on-disk state

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

hermes skills install NVIDIA/skills/skills/tao-run-on-virtualenv
Coding & developer tools · AI models & providersSource (opens in a new tab)

Host setup for TAO GPU backends. Checks and, after user approval, installs minimum-compatible NVIDIA driver, CUDA Toolkit, and NVIDIA Container Toolkit versions for Docker/local-Docker and Kubernetes GPU worker hosts. TAO-wide defaults can

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

hermes skills install NVIDIA/skills/skills/tao-setup-nvidia-gpu-host
Coding & developer tools · AI models & providersSource (opens in a new tab)

Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided detection ; detects objects described by text prompts without a fixed class vocabulary. Use when training, evaluating,

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

hermes skills install NVIDIA/skills/skills/tao-train-grounding-dino
Coding & developer tools · AI models & providersSource (opens in a new tab)

Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations; supports pretrain and finetune stages. Use when training, evaluating, exporting, or runni

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

hermes skills install NVIDIA/skills/skills/tao-train-mask-auto-encoder
Coding & developer toolsSource (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)

Find low-value or duplicate tests and the test-only code they keep alive. Use for: audit the test suite, find low-value tests. (gstack)

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

hermes skills install garrytan/gstack/test-audit
Coding & developer toolsSource (opens in a new tab)

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 c

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

hermes skills install NVIDIA/skills/skills/tilegym-adding-cutile-kernel
Coding & developer toolsSource (opens in a new tab)

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,

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

hermes skills install NVIDIA/skills/skills/tilegym-converting-cutile-to-julia
Memory & notes · Coding & developer toolsSource (opens in a new tab)

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.lau

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

hermes skills install NVIDIA/skills/skills/tilegym-converting-cutile-to-triton
Coding & developer tools · Languages & regionsSource (opens in a new tab)

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

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

hermes skills install NVIDIA/skills/skills/tilegym-improve-cutile-kernel-perf
Coding & developer toolsSource (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)

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/coding/torch_geometric
Coding & developer toolsSource (opens in a new tab)

Deploy a user's ONNX file as a working Triton Inference Server endpoint, end to end. Use when the user has a .onnx file and wants it served, wants a config.pbtxt generated from the ONNX graph, or wants to debug a Triton load or inference fa

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

hermes skills install clawhub/triton-onnx-model-repository
Coding & developer tools · AI models & providersSource (opens in a new tab)

Deploy a user's ONNX file as a working Triton Inference Server endpoint, end to end. Use when the user has a .onnx file and wants it served, wants a config.pbtxt generated from the ONNX graph, or wants to debug a Triton load or inference fa

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

hermes skills install NVIDIA/skills/skills/triton-onnx-model-repository
Coding & developer tools · AI models & providersSource (opens in a new tab)

Deploy a user's PyTorch model as a working Triton Inference Server endpoint, end to end. Use when the user has a TorchScript .pt file or a PT2 archive (.pt2 from torch.export + AOT Inductor) and wants it served, wants a config.pbtxt written

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

hermes skills install clawhub/triton-pytorch-model-repository
Coding & developer tools · AI models & providersSource (opens in a new tab)

Deploy a user's PyTorch model as a working Triton Inference Server endpoint, end to end. Use when the user has a TorchScript .pt file or a PT2 archive (.pt2 from torch.export + AOT Inductor) and wants it served, wants a config.pbtxt written

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

hermes skills install NVIDIA/skills/skills/triton-pytorch-model-repository
Coding & developer tools · AI models & providersSource (opens in a new tab)

Post-train LLMs with TRL (Transformers Reinforcement Learning) ; SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.

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

hermes skills install huggingface/skills/skills/trl-training
Coding & developer tools · AI models & providersSource (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.