Pharma ML Tools

What it does

When your agent uses it

• The user asks for datamol
• Compound-library triage
• Dataset preparation
• Chemistry-ML baselines beyond simple descriptor calculation

Example prompts

• “/pharma-ml-tools”

Requirements

• Python 3

Workflow steps

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

1. 1Normalize the input table first and identify the exact SMILES column.
2. 2Run datamol_library_profile.py before building models so duplicates, invalid structures, and scaffold concentration are visible.
3. 3Use medchem_screen.py before large docking or QSAR jobs to flag problematic chemotypes.
4. 4Use molfeat_featurize.py when the user needs model-ready features rather than only descriptor summaries.
5. 5Use pytdc_dataset_fetch.py when the user needs reproducible public benchmark datasets rather than ad hoc CSV collection.
6. 6Keep outputs under a dedicated directory such as ./pharma_ml/.

What it can do on your machine

Read from SKILL.md and the folder at commit 960a6e0. 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 script files (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3

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

• Network

  No URLs in SKILL.md.

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

• Credentials

  Names no API keys, tokens, secrets or passwords.

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

Context cost

Pharma ML Tools loads about 1.3k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 406 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~94

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

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

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from DrugClaw/DrugClaw at commit 960a6e0, republished under its Apache-2.0 licence (© DrugClaw). 406 words, ~1,260 tokens.

name

pharma-ml-tools

description

Pharmaceutical machine-learning workflow guide for library profiling, molecular featurization, benchmark dataset fetch, medicinal-chemistry filtering, and optional pose-generation handoff. Use when the user asks for datamol, molfeat, PyTDC, medchem, compound-library triage, dataset preparation, or chemistry-ML baselines beyond simple descriptor calculation.

source

drugclaw

updated_at

2026-03-11

which python3 || true
python3 - <<'PY'
mods = ["pandas", "numpy", "datamol", "molfeat", "medchem"]
for name in mods:
    try:
        __import__(name)
        print(f"{name}: ok")
    except Exception as exc:
        print(f"{name}: missing ({exc})")
try:
    import tdc
    print("PyTDC: ok")
except Exception as exc:
    print(f"PyTDC: missing ({exc})")
PY

python3 templates/datamol_library_profile.py \
  --input libraries/kinase_hits.csv \
  --smiles-column smiles \
  --id-column compound_id \
  --output pharma_ml/kinase_hits_profile.csv \
  --summary pharma_ml/kinase_hits_profile.json

python3 templates/molfeat_featurize.py \
  --input libraries/kinase_hits.csv \
  --smiles-column smiles \
  --id-column compound_id \
  --featurizer ecfp \
  --output pharma_ml/kinase_hits_ecfp.csv \
  --summary pharma_ml/kinase_hits_ecfp.json

python3 templates/pytdc_dataset_fetch.py \
  --task adme \
  --dataset Caco2_Wang \
  --split-method scaffold \
  --out-dir pharma_ml/caco2_wang

python3 templates/medchem_screen.py \
  --input libraries/kinase_hits.csv \
  --smiles-column smiles \
  --id-column compound_id \
  --output pharma_ml/kinase_hits_medchem.csv \
  --summary pharma_ml/kinase_hits_medchem.json

© DrugClaw, 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 4 other files in skills/pharma/pharma-ml-tools of DrugClaw/DrugClaw.

• SKILL.md
• templates/datamol_library_profile.py
• templates/medchem_screen.py
• templates/molfeat_featurize.py
• templates/pytdc_dataset_fetch.py

Open the folder on GitHubat commit 960a6e0