← All skills
molfeat
80 / 100 · Low risk
Fine to try.
By stanfish06/skillquarium (GitHub) · other · 12 stars · scanned at commit f748ea9
Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
Works with any agent that supports SKILL.md skills.
What this skill can do
Downloads and installs other software
The author does not mention this.
Found in 19 places.
Show 16 more
- skills/molfeat/SKILL.md, line 516
uv pip install "molfeat[dgl]==0.11.0" # For GIN models (0.11.0 only; removed in 1.0.0) - skills/molfeat/SKILL.md, line 517
uv pip install "molfeat[graphormer]==0.11.0" # For Graphormer (0.11.0 only; removed in 1.0.0) - skills/molfeat/references/available_featurizers.md, line 268
- **DGL models** (gin-*, jtvae, Python 3.10 only): `uv pip install "molfeat[dgl]==0.11.0"` (upstream recommends `dgl<=2.0`) - skills/molfeat/references/available_featurizers.md, line 269
- **Graphormer** (Python 3.10 only): `uv pip install "molfeat[graphormer]==0.11.0"` - skills/molfeat/references/available_featurizers.md, line 270
- **Transformers** (ChemBERTa, ChemGPT, MolT5): `uv pip install "molfeat[transformer]==1.0.0"` - skills/molfeat/references/available_featurizers.md, line 271
- **FCD**: `uv pip install "molfeat[fcd]==1.0.0"` - skills/molfeat/references/available_featurizers.md, line 272
- **PyTorch Geometric**: `uv pip install "molfeat[pyg]==1.0.0"` - skills/molfeat/references/available_featurizers.md, line 273
- **Visualization**: `uv pip install "molfeat[viz]==1.0.0"` - skills/molfeat/references/available_featurizers.md, line 275
- **All pip extras** (excludes dgl/graphormer): `uv pip install "molfeat[all]==1.0.0"` - skills/molfeat/references/examples.md, line 10
uv pip install "molfeat==1.0.0" - skills/molfeat/references/examples.md, line 13
uv pip install "molfeat[all]==1.0.0" - skills/molfeat/references/examples.md, line 16
uv pip install "molfeat[transformer]==1.0.0" # For ChemBERTa, ChemGPT - skills/molfeat/references/examples.md, line 17
uv pip install "molfeat[pyg]==1.0.0" # For PyTorch Geometric - skills/molfeat/references/examples.md, line 18
uv pip install "molfeat[viz]==1.0.0" # For NGLView widgets - skills/molfeat/references/examples.md, line 26
uv pip install "molfeat[dgl]==0.11.0" # For GNN models - skills/molfeat/references/examples.md, line 27
uv pip install "molfeat[graphormer]==0.11.0" # For Graphormer
Runs commands on your computer
The author does not mention this.
Found in 4 places.
Show 1 more
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'molfeat' ] || [ -L ~/.agents/skills/'molfeat' ]; then echo 'A skill folder named molfeat already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/stanfish06/skillquarium' "$d" && git -C "$d" checkout --quiet 'f748ea91aa51ce8fc42c27c809dba73a8377b1d5' -- 'skills/molfeat' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/molfeat' ~/.agents/skills/'molfeat' && 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/'molfeat' ~/.claude/skills/'molfeat' (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 stanfish06/skillquarium shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/stanfish06/skillquarium/)
Score history
| Date | Version | Score |
|---|
| 2026-11-08 | f748ea9 | 80 |