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 156 of 180.

Official skills first, then community.

Best match / quality.

Analyzes user-requested Screenpipe history windows to detect repeated research workflows, match existing scientific skills, and stage new skill drafts or composition recipes for review. Requires a reachable Screenpipe HTTP API, normally on

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

hermes skills install K-Dense-AI/scientific-agent-skills/skills/autoskill
AI models & providers · Web, research & browsingSource (opens in a new tab)

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preserva

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

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

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

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

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

Bayesian parameter estimation with MCMC (emcee) and probabilistic programming (PyMC). Posterior distributions, corner plots, model evidence, convergence diagnostics. Use when you need full posterior distributions, not just point estimates.

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

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

Compare BioIR vs OSS folding performance: model.forward() latency, GPU use, lDDT and DockQ with matched inputs. Use for benchmark setup, execution or audits; excludes affinity heads and Ray throughput.

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

hermes skills install clawhub/bioir-bench-perf-oss
AI models & providersSource (opens in a new tab)

Compare BioIR vs OSS folding performance: model.forward() latency, GPU use, lDDT and DockQ with matched inputs. Use for benchmark setup, execution or audits; excludes affinity heads and Ray throughput.

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

hermes skills install NVIDIA/skills/skills/bioir-bench-perf-oss
AI models & providersSource (opens in a new tab)

A highly advanced AI LLM transcending conventional AI. 'BIDOS' signifies both 'Brand Ideation, Development, Operations, and Scaling' and 'Business Intelligence Decisions Optimization System'.

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

hermes skills install lobehub/bidosx-2-v-2
AI models & providers · Work & businessSource (opens in a new tab)

Use when a user describes a custom CDF Orchestration pipeline ; a specific ordered combination of stages such as augmentation only, auto-labeling only, detection+captioning only, or image attribute augmentation without full auto-labeling ;

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

hermes skills install NVIDIA/skills/skills/cdf-orchestration-write-dag
AI models & providers · Images, video, music & 3DSource (opens in a new tab)

Pins down the RDKit definitions that differ between conventions before computing molecular descriptors, including Lipinski donor and acceptor counts (Lipinski.NumHDonors and NumHAcceptors versus rdMolDescriptors.CalcNumLipinskiHBD and HBA),

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

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

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For

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

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

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For

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

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

Performs constraint-based metabolic modeling with COBRApy, including FBA, pFBA, FVA, gene knockouts, flux sampling, growth media, production envelopes, gap filling, and SBML model validation for systems biology and metabolic engineering.

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

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

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/biology/cobrapy
AI models & providersSource (opens in a new tab)

Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.

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

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

Fine-tune LLMs on Google Colab GPUs directly from openscience. Connects to Colab runtimes via WebSocket bridge for remote training with Unsloth. Supports SFT, GRPO, DPO, vision, and TTS workflows on free T4 to Pro A100 GPUs.

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/ml-training/colab-finetuning
AI models & providers · Chat apps & voiceSource (opens in a new tab)

Compare runs, artifacts, methods, models, or claims on a fair and explicit decision basis.

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

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

Use when picking the search_space= argument for Search(). Covers the three provider classes (PtxasSearchSpace, NvccSearchSpace, LocalSearchSpaceBin), how to pin a version/variant/tag, the attention-focused 'att' variant for attention kernel

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

hermes skills install NVIDIA/skills/skills/compileiq-search-space
AI models & providers · Web, research & browsingSource (opens in a new tab)

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human l

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

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

Use when writing, running, debugging or upgrading Python code that uses NVIDIA cuML (GPU machine learning), cuml.accel (zero-code-change GPU acceleration of scikit-learn, umap-learn and hdbscan), or GPU UMAP/HDBSCAN/RandomForest/KMeans/SVC,

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

hermes skills install NVIDIA/skills/skills/cuml
Memory & notes · AI models & providersSource (opens in a new tab)

Builds molecular property prediction and MoleculeNet workflows with DeepChem, including SMILES featurization, scaffold or grouped holdouts, masked labels, graph models and explicit pretrained encoder transfer. Used for ADMET, toxicity, solu

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

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

Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments wit

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

hermes skills install synthetic-sciences/openscience/backend/cli/skills/chemistry/deepchem
AI models & providers · Automation & multi-agentSource (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.