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

49 official + 11,588 community matches. Page 413 of 485.

Official skills first, then community.

Best match / quality.

Provides access to a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server ; no local GPUs required. Tamarind bundles popular open-source models for structure pr

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

hermes skills install K-Dense-AI/scientific-agent-skills/skills/tamarind
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server ; no local GPUs required. Tamarind bundles popular open-source models for structure prediction (Al

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/biology/tamarind
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall / FAR / PASS-NO_PASS metrics,

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

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

Run TAO Data Services object-detection gap analysis from ground-truth and inference annotations. Use when an object detection workflow needs to identify weak images by comparing model predictions against ground truth using per-class recall,

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

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

Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed inference", "export Cosmos-Embed1", "embe

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

hermes skills install NVIDIA/skills/skills/tao-finetune-cosmos-embed
Images, video, music & 3D · Languages & regionsSource (opens in a new tab)

Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH or packaged backend image, optionally plans explicit clean source builds, prepares checkpoin

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

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

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / L

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

hermes skills install NVIDIA/skills/skills/tao-finetune-huggingface-model
Web, research & browsing · Images, video, music & 3DSource (opens in a new tab)

InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment. Use when the user asks to "fine-tune IV2CLIP", "run video_clip train/ev

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

hermes skills install NVIDIA/skills/skills/tao-finetune-video-clip
Coding & developer tools · Images, video, music & 3DSource (opens in a new tab)

Full PAIDF AnomalyGen pipeline ; fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and search per-sample (guidance, crop_ratio) parameters. Three modes: full (Phase 0→7: finetune then

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

hermes skills install NVIDIA/skills/skills/tao-generate-anomalies
Web, research & browsing · Images, video, music & 3DSource (opens in a new tab)

Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint. Use when a workflow needs embeddings before nearest-neighbor or unique-neighbor mining, or when th

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

hermes skills install NVIDIA/skills/skills/tao-generate-image-embeddings
Automation & multi-agent · Images, video, music & 3DSource (opens in a new tab)

Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotatio

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

hermes skills install NVIDIA/skills/skills/tao-generate-image-grounding
Images, video, music & 3DSource (opens in a new tab)

Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring expressions, and (optionally) verified expressions via VLM distillation. Use when the us

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

hermes skills install NVIDIA/skills/skills/tao-generate-referring-expressions
Images, video, music & 3DSource (opens in a new tab)

Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data ; multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when

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

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

The mandatory pre-launch gate and four-verb execution contract for every TAO workflow or action. Invoke BEFORE launching anything side-effecting ; AutoML, train, evaluate, inference, export, TensorRT engine generation, or DEFT/application w

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

hermes skills install NVIDIA/skills/skills/tao-launch-workflow
Automation & multi-agent · Images, video, music & 3DSource (opens in a new tab)

Runs the DEFT embed-then-mine workflow for VCN AOI iterations ; embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour source images for downstream augmentation. Use as the immediate next step after `tao-r

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

hermes skills install NVIDIA/skills/skills/tao-mine-aoi-images
Automation & multi-agent · Images, video, music & 3DSource (opens in a new tab)

Run TAO Data Services TMM unique-neighbor matching mining from embedding parquet files for object detection workflows. Use when an object detection workflow needs to mine a bijectively-assigned set of unique source images closest to target

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

hermes skills install NVIDIA/skills/skills/tao-mine-od-images
Automation & multi-agent · Images, video, music & 3DSource (opens in a new tab)

Prepare normalized object-detection false negatives, source masks, and clean-image embedding inputs for AnomalyGenNext. Use when turning box-level FN gaps into a frozen, pair-preserving preparation plan. Do not use for training or generatio

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

hermes skills install NVIDIA/skills/skills/tao-prepare-anomalygennext-inputs
Images, video, music & 3DSource (opens in a new tab)

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 against a customer-de

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

hermes skills install NVIDIA/skills/skills/tao-run-deft-aoi
Automation & multi-agent · Images, video, music & 3DSource (opens in a new tab)

Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly requested: evaluate the base model on Proxy and frozen Benchmark splits, mine real image pair

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

hermes skills install NVIDIA/skills/skills/tao-run-deft-aoi-cosmos3
Automation & multi-agent · Images, video, music & 3DSource (opens in a new tab)

Run the mining-based DEFT improvement workflow for ITS Cosmos-Reason binary video questions, focused on the non-reasoning classification/evaluation path. Use when the user asks for a DEFT CR ITS mining workflow, traffic-camera Cosmos Reason

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

hermes skills install NVIDIA/skills/skills/tao-run-deft-cr-its-mining
Automation & multi-agent · Images, video, music & 3DSource (opens in a new tab)

Run the full DEFT smart-data-augmentation loop for NVIDIA TAO Grounding DINO object detection: zero-shot baseline inference, KPI analysis, per-class gap analysis, SigLIP embedding of weak images, unique-neighbor mining against a source pool

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

hermes skills install NVIDIA/skills/skills/tao-run-deft-object-detection
Automation & multi-agent · Images, video, music & 3DSource (opens in a new tab)

Run a binary industrial-inspection DEFT loop with TAO RT-DETR: measure on frozen KPI/test roles, mine gap-similar real and clean images with SigLIP, accumulate admitted COCO data, retrain from one base checkpoint, and select by KPI AP50. Us

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

hermes skills install NVIDIA/skills/skills/tao-run-deft-od-aoi
Automation & multi-agent · Images, video, music & 3DSource (opens in a new tab)

Run iterative improvement for NVIDIA TAO CLIP / SigLIP image-text retrieval on attribute-labelled data. Use when a request combines retrieval evaluation, weak-attribute or caption-pair mining, repeated retraining, and a stopping condition b

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

hermes skills install NVIDIA/skills/skills/tao-run-deft-pas
Web, research & browsing · Images, video, music & 3DSource (opens in a new tab)

Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill. Handles container image resolution, job-payload JSON construct

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

hermes skills install NVIDIA/skills/skills/tao-run-inference-service
Automation & multi-agent · Images, video, music & 3DSource (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.