← All skills
kermt-finetune
92 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
By NVIDIA/skills (GitHub) · coding · 3,933 stars · scanned at commit 2630133
Finetune a pretrained KERMT encoder on a labeled CSV. Validate the checkpoint and data, prepare features, and run containerized training. Use a local checkpoint or optionally download a pinned Hugging Face model bundle using HF_TOKEN if configured. Write model bundles, prepared data, logs, and trained models to user-selected host directories.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.
Found in 16 places.
Show 13 more
- skills/bionemo-kermt-finetune/scripts/_utils.py, line 227
r = subprocess.run( - skills/bionemo-kermt-finetune/scripts/_utils.py, line 324
r = subprocess.run( - skills/bionemo-kermt-finetune/scripts/kermt_container.sh, line 118
r = subprocess.run(["docker", "info"], capture_output=True, text=True, timeout=10) - skills/bionemo-kermt-finetune/scripts/kermt_container.sh, line 131
r = subprocess.run( - skills/bionemo-kermt-finetune/scripts/kermt_container.sh, line 176
r = subprocess.run(["docker", "image", "inspect", image], capture_output=True, text=True, timeout=10) - skills/bionemo-kermt-finetune/scripts/kermt_container.sh, line 187
r = subprocess.run(["docker", "image", "inspect", img], capture_output=True) - skills/bionemo-kermt-finetune/scripts/kermt_container.sh, line 195
r = subprocess.run( - skills/bionemo-kermt-finetune/scripts/kermt_container.sh, line 376
conda run -n kermt --no-capture-output bash -c "$*" - skills/bionemo-kermt-finetune/scripts/kermt_container.sh, line 424
conda run -n kermt --no-capture-output bash -c "$*") || return $? - skills/bionemo-kermt-finetune/scripts/prepare_data.py, line 36
Each underlying script is invoked via `subprocess.run`. The PYTHONPATH=/workspace - skills/bionemo-kermt-finetune/scripts/prepare_data.py, line 106
proc = subprocess.run(cmd, capture_output=True, text=True) - skills/bionemo-kermt-finetune/scripts/run_finetune_local.py, line 399
proc = subprocess.run(argv, env=env, stdout=logf, stderr=subprocess.STDOUT) - skills/bionemo-kermt-finetune/scripts/run_finetune_local.py, line 408
description="Workstation finetune runner — wraps main.py finetune via subprocess."
Connects to the internet
The author does not mention this.
Found in 2 places.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'kermt-finetune' ] || [ -L ~/.agents/skills/'kermt-finetune' ]; then echo 'A skill folder named kermt-finetune already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/NVIDIA/skills' "$d" && git -C "$d" checkout --quiet '2630133f22e357f2005886567a39eddcc1b520e2' -- 'skills/bionemo-kermt-finetune' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/bionemo-kermt-finetune' ~/.agents/skills/'kermt-finetune' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'kermt-finetune' ~/.claude/skills/'kermt-finetune' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for NVIDIA/skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/NVIDIA/skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-11 | 2630133 | 92 |
| 2026-11-08 | fce3cca | 92 |
| 2026-11-07 | fce3cca | 82 |