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

12 official + 5,727 community matches. Page 218 of 239.

Official skills first, then community.

Best match / quality.

Use this skill when the user is dealing with the DOCA environment around their workload ; verifying an install is healthy, preparing the build env (pkg-config, headers, LD_LIBRARY_PATH, hugepages, devlink, representors), debugging env-class

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

hermes skills install NVIDIA/skills/skills/doca-setup
Memory & notes · Work & businessSource (opens in a new tab)

Not for writing library code (name that library skill). Use this skill whenever another DOCA skill says "prefer the structured tool per doca-structured-tools-contract", or when the user wants a one-shot answer consolidating what multiple ma

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

hermes skills install NVIDIA/skills/skills/doca-structured-tools-contract
Memory & notes · Coding & developer toolsSource (opens in a new tab)

Changing DOCA versions safely: upgrading or downgrading the host DOCA packages, refreshing the BlueField BFB, bumping the NGC DOCA container tag, or rolling back, with the discipline detect -> report -> ASK -> only then a guided upgrade. Tr

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

hermes skills install NVIDIA/skills/skills/doca-upgrade
Memory & notes · Automation & multi-agentSource (opens in a new tab)

Host-side DOCA UROM library (doca_urom_*): offload an HPC / UCX / MPI application's remote memory operations (puts, gets, atomics, collectives) from the host CPU onto a BlueField DPU. Trigger on "MPI all-reduce burning host CPU", "push UCX

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

hermes skills install NVIDIA/skills/skills/doca-urom
Memory & notes · Images, video, music & 3DSource (opens in a new tab)

Operate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using `doca-urom`: pull the NGC image, choose the UCX component, size queues, configure Comch

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

hermes skills install NVIDIA/skills/skills/doca-urom-svc
Memory & notes · Images, video, music & 3DSource (opens in a new tab)

NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call. Use local NIM containers for confidential or proprietary data. Run a complete computational drug discovery pipeline

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

hermes skills install NVIDIA/skills/skills/bionemo-drug-discovery-pipeline

Specializes in bilingual education, analyzing English word meanings, example sentences, roots and affixes, historical background, and memory techniques

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

hermes skills install lobehub/epoch-ai-language-teacher
Memory & notes · Languages & regionsSource (opens in a new tab)

Detects host inventory and effective CPU, memory, disk, scheduler, container, and accelerator limits when a user asks for resource-aware planning or before a clearly resource-sensitive local workload. Produces a redacted JSON snapshot and c

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

hermes skills install K-Dense-AI/scientific-agent-skills/skills/get-available-resources
Memory & notes · Automation & multi-agentSource (opens in a new tab)

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic re

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

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

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs

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

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

Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen ; including when the user says "de

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

hermes skills install huggingface/skills/skills/hf-cloud-serving-image-selection
Memory & notes · Images, video, music & 3DSource (opens in a new tab)

Estimate the GPU memory needed to run a Hugging Face model (weights, KV cache and inference overhead) and whether it fits on given GPUs, without downloading it. Use when asked how much VRAM a model needs, whether it fits on a GPU, the longe

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

hermes skills install huggingface/skills/skills/hf-mem
Memory & notes · AI models & providersSource (opens in a new tab)

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

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

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

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

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

hermes skills install NVIDIA/skills/skills/jetson-diagnostic
Memory & notes · Everyday life & funSource (opens in a new tab)

Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree. Use after init-image / init-source; not for editing profile fields.

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

hermes skills install NVIDIA/skills/skills/jetson-generate-kb
Memory & notes · Images, video, music & 3DSource (opens in a new tab)

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

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

hermes skills install NVIDIA/skills/skills/jetson-inference-mem-tune
Memory & notes · AI models & providersSource (opens in a new tab)

Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.

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

hermes skills install NVIDIA/skills/skills/jetson-memory-audit
Memory & notes · Cost, speed & monitoringSource (opens in a new tab)

Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not for CPU/GPU frequency tuning.

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

hermes skills install NVIDIA/skills/skills/jetson-optimize-memory
Memory & notes · Coding & developer toolsSource (opens in a new tab)

Use when installing, repairing, reusing, inspecting, or verifying readiness of the native NVIDIA Video Codec SDK or PyNvVideoCodec on Jetson, including the one-frame encode/decode smoke test with official samples, and when interpreting what

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

hermes skills install NVIDIA/skills/skills/jetson-video-setup
Memory & notes · Images, video, music & 3DSource (opens in a new tab)

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Cov

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/ml-training/knowledge-distillation
Memory & notes · 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.