Agent Skill

Kermt Infer skill

kermt-inferNVIDIA/skillsskills/bionemo-kermt-infer/SKILL.md

Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to kermt-finetune), validates the CSV, prepares the data (clean + rdkit_2d features), then launches main.py predict inside the kermt container (blocking, minutes-scale).

3.7kApache-2.0

always on

89 tokname + description

once used

1,453 tokSKILL.md body

bundled files

116 scripts

repo stars

3.7kGitHub

Install the Kermt Infer skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/NVIDIA/skills --skill kermt-infer

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/NVIDIA/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -R /tmp/skills/skills/bionemo-kermt-infer ~/.claude/skills/kermt-infer

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

When	What loads	Cost
Every session	Name and description	89 tok
When the agent uses it	The SKILL.md instructions	1,453 tok
Only if opened	11 bundled files (136 KB)	varies

Until it is used, kermt-infer costs about 15× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 150 skills from NVIDIA/skills would load 20,796 tokens of descriptions. Skills vs MCP study

Checks

Ships scripts the agent can run. Read them before installing.
The name doesn't match its folder name, as the specification requires.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

kermt-infer
Skill and runtime paths
Hardware requirements
Inputs
Workflow
Hard rules
Common errors
Replayability

More skills from NVIDIA/skills

All skills in this repo

accelerated-computing-cudfNVIDIA/skills
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
3.7k2356 tok idle · 2,307 in use
ambient-healthcare-agent-with-nemotron-voice-agentNVIDIA/skills
Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling workflows without a separate backend.
3.7k1744 tok idle · 2,849 in use
amc-run-rtsp-calibrationNVIDIA/skills
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.
3.7k159 tok idle · 4,607 in use
amc-run-sample-calibrationNVIDIA/skills
Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
3.7k164 tok idle · 3,627 in use
amc-run-video-calibrationNVIDIA/skills
Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to `amc-run-rtsp-calibration`.
3.7k157 tok idle · 4,576 in use
amc-setup-calibration-stackNVIDIA/skills
Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.
3.7k67 tok idle · 4,277 in use
boltz2-nimNVIDIA/skills
Use Boltz2 NIM for biomolecular structure prediction and binding affinity. Invoke for Boltz2, protein structures, protein-ligand/DNA/RNA complexes, SMILES or CCD ligands, pIC50/IC50 affinity scoring, mmCIF output, hosted NVIDIA API calls, or local Docker deployment.
3.7k71 tok idle · 1,433 in use
cdf-anomalygenNVIDIA/skills
Use when running the CDF AnomalyGen pipeline over a defect dataset — mask placement, fine-tuning, synthetic defect-image generation (SDG), evaluation, quality refinement, and pseudo-labeling — even when the user names only one stage.
3.7k54 tok idle · 9,563 in use