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 158 of 180.

Official skills first, then community.

Best match / quality.

Set up or repair an NVIDIA FastGen environment for a chosen task: Docker or Conda installation, credentials and model access, weight and dataset downloads, and an optional bounded smoke test. Use it before any FastGen command whenever the e

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

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

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from hu

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

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

Flux Prompt Generation Assistant: Expert in crafting detailed, creative prompts for high-quality image outputs from the Flux model.

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

hermes skills install lobehub/flux-prompt-generator
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Generates or edits images with AI models through the OpenRouter Image API (Gemini, Seedream, Recraft, GPT-Image, Riverflow). Use for photos, illustrations, artwork, concept art, visual assets, logos, and image editing or compositing from re

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

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

Supports audited local Geniml genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess consensus universes.

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

hermes skills install K-Dense-AI/scientific-agent-skills/skills/geniml
AI models & providers · Cost, speed & monitoringSource (opens in a new tab)

Predicts regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models ; no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (

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

hermes skills install K-Dense-AI/scientific-agent-skills/skills/genomic-intelligence
AI models & providers · Automation & multi-agentSource (opens in a new tab)

Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models ; no local GPU or model weights. Six tasks over a REST API and a hosted MCP server (k

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/biology/genomic-intelligence
AI models & providers · Automation & multi-agentSource (opens in a new tab)

Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. Supports satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral),

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/data-engineering/geomaster
AI models & providers · Images, video, music & 3DSource (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)

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

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

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

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers

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

hermes skills install openai/skills/skills/.curated/gh-fix-ci
Coding & developer tools · AI models & providersSource (opens in a new tab)

A sophisticated AI-powered ghostwriting agent designed to craft high-quality content across a diverse range of genres and formats. Equipped with advanced language models, GhostWriter Pro excels in cre

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

hermes skills install lobehub/ghostwriter-pro-ai
AI models & providers · Images, video, music & 3DSource (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)

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

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

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

Supports Gtars for local genomic interval models and set algebra, overlaps and counts, consensus and coverage, tokenization, fragment processing, and refget/BEDbase planning across Python, Rust, and the CLI.

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

hermes skills install K-Dense-AI/scientific-agent-skills/skills/gtars
AI models & providers · Cost, speed & monitoringSource (opens in a new tab)

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational gen

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/coding/gtars
AI models & providers · Cost, speed & monitoringSource (opens in a new tab)

Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS ; including phrases like "deploy a model", "host this LLM on AWS", "s

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

hermes skills install huggingface/skills/skills/hf-cloud-sagemaker-deployment-planner
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the use

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

hermes skills install huggingface/skills/skills/hf-cloud-sagemaker-iam-preflight
Coding & developer tools · AI models & providersSource (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)

Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authent

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/llm-tools/hugging-face-cli
AI models & providersSource (opens in a new tab)

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the mode

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

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

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conver

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/ml-training/hugging-face-model-trainer
AI models & providers · Cost, speed & monitoringSource (opens in a new tab)

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/writing/hugging-face-paper-publisher
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.