New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Kermt Embed

by NVIDIA in NVIDIA/skills

Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint.

OfficialApache-2.0Auto-check passedAI & LLM Engineering

Install Kermt Embed

skills CLI
$ npx skills add NVIDIA/skills --skill kermt-embed -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NVIDIA/skills kermt-embed --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NVIDIA/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bionemo-kermt-embed .claude/skills/kermt-embed && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
kermt-embed
GitHub stars
3.5k
Used in
1 other repo
Token cost
~1.9k tokens
SKILL.md length
691 words
Files
15 (incl. scripts, references)
Skills in repo
380
Repo updated
First seen
Licence
Apache-2.0

At a glance

Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint.

  • Works in 7 steps: Pre-flight: container + system probe. → Compute run directory. → Resolve & validate the checkpoint. → …
  • Tasks that involve Embeddings
  • SKILL.md covers Skill and runtime paths, Downloads and local outputs, Hardware requirements and Inputs, plus 4 more sections
  • Runs Python and Shell scripts from its folder; calls jq and git; needs HF_TOKEN

What it does

Kermt Embed is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HFTOKEN if configured. Run containerized embedding extraction and write model bundles, per-readout .npy embeddings, canonical SMILES, and validity arrays to user-selected host directories.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts and reference files (for example `BENCHMARK.md`, `config/defaults_embed.json` and `config/released_model.json`). Compatibility notes: Requires docker, nvidia-container-toolkit, and a CUDA-capable NVIDIA GPU. Designed for Claude Code, Codex, and Nemotron.

It sits in AI & LLM Engineering, covering Embeddings, Drug discovery and cheminformatics and Model hubs and datasets. It works with Hugging Face, CUDA and NVIDIA AI Platform. The repository describes itself as: Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Embeddings
  • Tasks that involve Drug discovery and cheminformatics
  • Tasks that involve Model hubs and datasets

Example prompts

  • “/kermt-embed”

Requirements

  • Python 3
  • A Bash shell
  • Docker
  • Compatibility (from SKILL.md): Requires docker, nvidia-container-toolkit, and a CUDA-capable NVIDIA GPU. Designed for Claude Code, Codex, and Nemotron.

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Pre-flight: container + system probe.
  2. Compute run directory.
  3. Resolve & validate the checkpoint.
  4. Validate the data.
  5. Prepare the data (clean-only — no features step).
  6. Launch the runner (blocking).
  7. Report to the user.

What it can do on your machine

Read from SKILL.md and the folder at commit 0e0d506. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 7 files in scripts/ (Python and Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • jq
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • huggingface.co

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HF_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires docker, nvidia-container-toolkit, and a CUDA-capable NVIDIA GPU. Designed for Claude Code, Codex, and Nemotron.

    From compatibility in the SKILL.md frontmatter.

Context cost

Kermt Embed loads about 1.9k tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 91 tokens; SKILL.md has 691 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from NVIDIA/skills at commit 0e0d506, republished under its Apache-2.0 licence (© NVIDIA). 691 words, ~1,914 tokens.

Download SKILL.mdSave it as .claude/skills/kermt-embed/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.
name
kermt-embed
description
Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Run containerized embedding extraction and write model bundles, per-readout .npy embeddings, canonical SMILES, and validity arrays to user-selected host directories.
compatibility
Requires docker, nvidia-container-toolkit, and a CUDA-capable NVIDIA GPU. Designed for Claude Code, Codex, and Nemotron.
license
Apache-2.0
metadata.owner
evax@nvidia.com
metadata.classification
workflow-skill
metadata.risk_tier
skill

kermt-embed

Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. The skill is the workflow orchestrator: validate ckpt, validate CSV, clean SMILES, launch the runner blocking, return the per-readout .npy files.

Skill and runtime paths

Set SKILL_DIR to the absolute path of this installed skill directory. Export KERMT_REPO as the absolute path to the KERMT checkout used for model execution. The bundled container helper mounts that checkout at /workspace and this skill at /skill (read-only). Commands inside the container use /skill/scripts/; defaults are bundled in config/. See Released models for checkpoint bundle requirements.

Downloads and local outputs

The optional released-model branch reads config/released_model.json for the Hugging Face repository, pinned revision, and filenames. The bundled scripts/fetch_released_model.py downloads the model bundle over HTTPS into the host directory the user selects. Public models work without credentials; if HF_TOKEN is set, the container helper forwards it for Hugging Face authentication. Prepared data, logs, and workflow results go into the chosen run directory.

Hardware requirements

  • GPUs: 1 (single-GPU).
  • VRAM: ≥ 4 GB for the default batch_size 64.
  • Disk: depends on output size — roughly a few MB per 1k molecules at hidden 800 per readout, so ~10–20 MB per 1k molecules across the 4 readouts. Plus a small canonical_smiles.npy + validity.npy per run.
  • Driver / CUDA: any host supporting CUDA 12.6.

Inputs

Required:

  • --csv <path> — SMILES CSV. First column is smiles; other columns are ignored (no targets needed).

Checkpoint (optional — defaults to the released model if omitted):

  • --ckpt <path> — any encoder-bearing checkpoint. Grover_base, cmim, hybrid, and finetuned ckpts are all accepted. The validator only refuses ckpts with no encoder. If omitted, the skill offers to download the released pretrained hybrid model nvidia/NV-KERMT-70M-v2 and embed with it — see "Resolve & validate the checkpoint" (workflow step 3).
  • --pretrained-release — explicit opt-in to use the released model without the interactive prompt (for non-interactive / agent runs). Mutually exclusive with --ckpt.
  • --model-dir <dir> — where to save the downloaded bundle (default $KERMT_REPO/models/NV-KERMT-70M-v2/). An already-complete bundle there is reused, not re-downloaded.

Optional:

  • --batch-size N — override the configured default (64).
  • --gpus 0 — single GPU id (default 0).
  • --from-prepare <dir> — skip the prepare step and reuse an existing prepare_data.json in <dir>.
Show full SKILL.md (398 more words)Show less

Workflow

Let $KERMT_REPO be the path to your kermt repo checkout.

  1. Pre-flight: container + system probe.

    "$SKILL_DIR/scripts/kermt_container.sh" check_system

  2. Compute run directory.

    RUN_DIR=$KERMT_REPO/runs/embed_$(date -u +%Y-%m-%dT%H-%M-%SZ)

  3. Resolve & validate the checkpoint.

    Resolve — only if --ckpt was omitted. Default to the released pretrained hybrid model nvidia/NV-KERMT-70M-v2:

    • Consent gate. Unless --pretrained-release was passed, ask the user: "No checkpoint given — download the released model nvidia/NV-KERMT-70M-v2 (NVIDIA Open Model License, https://huggingface.co/nvidia/NV-KERMT-70M-v2) and embed with it? [y/N]". Never download without an explicit yes (or --pretrained-release). If both --ckpt and --pretrained-release are given, abort — they conflict.
    • Save location. Default $KERMT_REPO/models/NV-KERMT-70M-v2/; honor --model-dir <dir> if given. An already-complete bundle is reused.
    • Download (foreground; ~282 MB on first fetch):
      "$SKILL_DIR/scripts/kermt_container.sh" run --model-dir <save-dir> -- \
    "python /skill/scripts/fetch_released_model.py --out /model"
      Parse the JSON; abort on ok: false (surface errors). On success set <user-ckpt> = <save-dir>/kermt_contrastive_v2.0.pt.

    Validate the resolved (or user-provided) ckpt:

    "$SKILL_DIR/scripts/kermt_container.sh" run --ckpt <user-ckpt> -- \
    "python /skill/scripts/check_checkpoint.py --mode embed --ckpt /ckpt"

    Parse JSON. Abort on ok: false. The validator only refuses encoder-less ckpts (rare).

  4. Validate the data.

    "$SKILL_DIR/scripts/kermt_container.sh" run --data <user-csv> -- \
    "python /skill/scripts/check_data.py --mode embed --csv /data/<basename>"

  5. Prepare the data (clean-only — no features step).

    "$SKILL_DIR/scripts/kermt_container.sh" run --data <user-csv> --run-dir $RUN_DIR -- \
    "python /skill/scripts/prepare_data.py --mode embed \\
         --csv /data/<basename> --out /runs/data"

    Outputs land at $RUN_DIR/data/prepare_data.json with a single clean_csv path. task/extract_embeddings.py featurizes from SMILES on the fly.

  6. Launch the runner (blocking).

    "$SKILL_DIR/scripts/kermt_container.sh" run \\
    --ckpt <user-ckpt> --run-dir $RUN_DIR -- \\
    "python /skill/scripts/run_extract_embeddings.py \\
         --ckpt /ckpt \\
         --prepare-manifest /runs/data/prepare_data.json \\
         --out /runs \\
         [--gpus 0 --batch-size N]"

  7. Report to the user.

    • Embeddings directory: $RUN_DIR/out/
      • atom_from_atom.npy, bond_from_atom.npy, atom_from_bond.npy, bond_from_bond.npy (the 4 standard readouts; each shape (N_rows, hidden_size))
      • metadata.pkl — pickle of a dict containing canonical_smiles (RDKit-canonicalized SMILES per row), valid (boolean per-row: did RDKit parse it), plus other run metadata.
    • Manifest: $RUN_DIR/run.json
    • Log: $RUN_DIR/logs/embed.log

Hard rules

  • Never download the released model without consent. When --ckpt is omitted, download nvidia/NV-KERMT-70M-v2 only after an explicit user "yes" or an explicit --pretrained-release flag. --ckpt and --pretrained-release are mutually exclusive.
  • Never modify the user's ckpt. The runner reads-only via task/extract_embeddings.py's --checkpoint <path> flag.
  • Arch comes from the ckpt. No --hidden-size flag etc. on this runner; task/extract_embeddings.py reads arch from the ckpt's saved_args.

Common errors

  • prepare_data manifest is missing required output 'clean_csv' → prepare ran with --skip-clean but no source CSV given. Re-run prepare without it.
  • --gpus '0,1' is single-GPU only → pass a single id.

Replayability

bash
$(jq -r .cmd_replay $RUN_DIR/run.json)

If ok_to_replay: false (dirty kermt repo worktree at launch time), pin the commit via repo.commit and git checkout it first.

© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 14 other files (scripts, references) in skills/bionemo-kermt-embed of NVIDIA/skills.

  • SKILL.md
  • BENCHMARK.md
  • config/defaults_embed.json
  • config/released_model.json
  • evals/evals.json
  • references/released-models.md
  • scripts/_utils.py
  • scripts/check_checkpoint.py
  • scripts/check_data.py
  • scripts/fetch_released_model.py
  • scripts/kermt_container.sh
  • scripts/prepare_data.py
  • scripts/run_extract_embeddings.py
  • skill-card.md
  • skill.oms.sig

Open the folder on GitHubat commit 0e0d506

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in NVIDIA/skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Kermt Embed next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Kermt Embed compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kermt Embed this skillNVIDIA/skills3.5k1 repos~1.9kAutomated safety check: PassApache-2.0
Esmfold2JimLiu/science-skills2274 repos~2.5kAutomated safety check: PassApache-2.0
SageMaker Serving Image Selectionhuggingface/skills11k1 repos~4.6kAutomated safety check: PassApache-2.0
Hugging Face Local Modelshuggingface/skills11k3 repos~945Automated safety check: PassApache-2.0
Megakernel OptimizationRightNow-AI/AutoMegaKernel148—~1.8kAutomated safety check: PassMIT
Hugging Face ZeroGPUhuggingface/skills11k2 repos~4.6kAutomated safety check: PassApache-2.0

Similar skills

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    227 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • SageMaker Serving Image Selection

    huggingface/skills

    Official

    Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

    11k GitHub starsUsed in 1 repo~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Hugging Face Local Models

    huggingface/skills

    Official

    Finds llama.cpp-compatible GGUF models on the Hugging Face Hub, picks a quantization for your hardware and launches them with llama-cli or llama-server.

    11k GitHub starsUsed in 3 repos~945 tokens
    AI & LLM EngineeringAuto-check passed

  • Megakernel Optimization

    RightNow-AI/AutoMegaKernel

    A skill your agent uses when optimizing or generating a CUDA megakernel for a HuggingFace Llama-family model with AutoMegaKernel (AMK), drives the correctness-gated propose - eval - keep/revert loop…

    148 GitHub stars~1.8k tokensUpdated 19 days ago
    AI & LLM EngineeringAuto-check passed

  • Hugging Face ZeroGPU

    huggingface/skills

    Official

    Covers the rules for writing Gradio Spaces on ZeroGPU hardware: the @spaces.GPU decorator, duration and quota tuning, process isolation and CUDA build limits.

    11k GitHub starsUsed in 2 repos~4.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Cosmos3 Post Training

    NVIDIA/cosmos-framework

    Official

    Guide users through Cosmos3 supervised fine-tuning (SFT) post-training: preparing the example dataset and Wan2.2 VAE, converting the base checkpoint to DCP, launching distributed training (paired…

    556 GitHub stars~2.7k tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed

More from NVIDIA/skills

All 380 skills in this repo

  • Vss Deploy Detection Tracking 2D

    NVIDIA/skills

    Official

    A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice.

    3.5k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed

  • HSB IP Def File Tool

    NVIDIA/skills

    Official

    Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.

    3.5k GitHub stars~2.9k tokensUpdated today
    Auto-check passed

  • Isaac Sim Mission Control Showcase

    NVIDIA/skills

    Official

    Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.

    3.5k GitHub stars~4.8k tokensUpdated today
    Auto-check passed

  • Defect Image Generation with Cosmos AnomalyGen

    NVIDIA/skills

    Official

    Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling.

    3.5k GitHub stars~5k tokensUpdated today
    Auto-check: notes

  • Physical AI Video Augmentation on OSMO

    NVIDIA/skills

    Official

    Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download.

    3.5k GitHub stars~4.7k tokensUpdated today
    Auto-check: notes

  • TAO Detection KPI Analysis

    NVIDIA/skills

    Official

    Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV.

    3.5k GitHub stars~2.7k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about Kermt Embed

What does Kermt Embed do?

Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. Kermt Embed is an agent skill from NVIDIA/skills, published by the product's own GitHub organization. Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint.

When should I use Kermt Embed?

Kermt Embed fits situations like: tasks that involve Embeddings; tasks that involve Drug discovery and cheminformatics; tasks that involve Model hubs and datasets.

How do I install Kermt Embed in Claude Code?

Run `npx skills add NVIDIA/skills --skill kermt-embed -a claude-code`. Or copy the skill folder (skills/bionemo-kermt-embed in NVIDIA/skills) into .claude/skills/kermt-embed in your project. Claude Code loads it when a task matches its description.

How do I install Kermt Embed in Codex?

Run `npx skills add NVIDIA/skills --skill kermt-embed -a codex`. Or copy the skill folder (skills/bionemo-kermt-embed in NVIDIA/skills) into .agents/skills/kermt-embed in your project. Codex loads it when a task matches its description.

Can I use Kermt Embed in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NVIDIA/skills --skill kermt-embed -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kermt-embed, .gemini/skills/kermt-embed, .github/skills/kermt-embed and .opencode/skills/kermt-embed in your project.

What does Kermt Embed need to run?

Going by SKILL.md and its folder, Kermt Embed needs Python and a shell for the scripts in its folder, the command-line tools its instructions call (jq and git) and credentials named HF_TOKEN. Our summary lists: Python 3; A Bash shell; Docker. Compatibility (from SKILL.md): Requires docker, nvidia-container-toolkit, and a CUDA-capable NVIDIA GPU. Designed for Claude Code, Codex, and Nemotron..

Does Kermt Embed access the network?

SKILL.md names 1 domain. As links in the text: huggingface.co. This is read from the text; nothing was executed.

Is Kermt Embed safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Kermt Embed use?

Kermt Embed is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kermt Embed use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 409 tokens, read only when the agent opens those files.

What are the alternatives to Kermt Embed?

Skills that share tags, products or a category with Kermt Embed: Esmfold2 (JimLiu/science-skills, 227 stars), SageMaker Serving Image Selection (huggingface/skills, 11k stars), Hugging Face Local Models (huggingface/skills, 11k stars) and Megakernel Optimization (RightNow-AI/AutoMegaKernel, 148 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kermt Embed?

NVIDIA (a GitHub organization, an official publisher) maintains it in NVIDIA/skills, which has 3,534 GitHub stars. The repository holds 380 skills in this directory. The repository was last updated on October 7, 2026.

Source: NVIDIA/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.