Bio DB Tools

What it does

When your agent uses it

• The user asks to look up protein annotations
• Population frequencies
• Pathway knowledge
• Public datasets

Example prompts

• “/bio-db-tools”

Requirements

• Python 3

Workflow steps

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

1. 1Save both a machine-readable result file and a short summary JSON.
2. 2Report the exact database, query string, species, and any filters used.
3. 3Prefer exact identifiers when available: UniProt accession, PDB ID, Ensembl ID, rsID, ClinVar query, Reactome stable ID.
4. 4Return direct links for the user whenever the database exposes stable pages.
5. 5Distinguish clearly between
6. 6If the remote API returns nothing, say that explicitly instead of inferring a biological conclusion.
7. 7Treat these sources as lookup surfaces, not experimental validation.

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

Bio DB Tools loads about 1.4k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 367 words of instructions outside code blocks.

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

~93

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

~1.4k

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). 367 words, ~1,383 tokens.

name

bio-db-tools

description

Query public biology databases and APIs including UniProt, RCSB PDB, AlphaFold DB, ClinVar, dbSNP, gnomAD, Ensembl, GEO, InterPro, KEGG, OpenTargets, Reactome, and STRING. Use when the user asks to look up protein annotations, structures, variants, population frequencies, pathway knowledge, public datasets, interaction networks, or disease-target evidence.

source

drugclaw

updated_at

2026-03-10

which python3 || true
python3 - <<'PY'
mods = ["requests"]
for name in mods:
    try:
        __import__(name)
        print(f"{name}: ok")
    except Exception as exc:
        print(f"{name}: missing ({exc})")
PY

python3 templates/bio_db_lookup.py uniprot \
  --query TP53 \
  --organism-id 9606 \
  --output bio/uniprot_tp53.csv \
  --summary bio/uniprot_tp53.json

python3 templates/bio_db_lookup.py pdb \
  --query "EGFR kinase inhibitor" \
  --limit 5 \
  --output bio/pdb_egfr.csv \
  --summary bio/pdb_egfr.json

python3 templates/bio_db_lookup.py clinvar \
  --query 'BRCA1[gene] AND clinsig_pathogenic[prop]' \
  --output bio/clinvar_brca1.csv \
  --summary bio/clinvar_brca1.json

python3 templates/bio_db_lookup.py gnomad \
  --mode gene-constraint \
  --gene-symbol BRCA1 \
  --output bio/gnomad_brca1.csv \
  --summary bio/gnomad_brca1.json

python3 templates/bio_db_lookup.py reactome \
  --mode enrichment \
  --gene BRCA1 --gene BRCA2 --gene TP53 --gene ATM \
  --output bio/reactome_dna_repair.csv \
  --summary bio/reactome_dna_repair.json

python3 templates/bio_db_lookup.py uniprot \
  --accession P04637 \
  --output bio/uniprot_p04637.csv \
  --summary bio/uniprot_p04637.json

python3 templates/bio_db_lookup.py pdb \
  --pdb-id 6LU7 \
  --output bio/pdb_6lu7.csv \
  --summary bio/pdb_6lu7.json

python3 templates/bio_db_lookup.py alphafold \
  --uniprot-id P04637 \
  --download bio/AF-P04637-F1-model.pdb \
  --output bio/alphafold_tp53.csv \
  --summary bio/alphafold_tp53.json

python3 templates/bio_db_lookup.py dbsnp \
  --rsid rs429358 \
  --output bio/dbsnp_rs429358.csv \
  --summary bio/dbsnp_rs429358.json

python3 templates/bio_db_lookup.py opentargets \
  --mode disease-targets \
  --id EFO_0000305 \
  --limit 10 \
  --output bio/opentargets_breast_cancer.csv \
  --summary bio/opentargets_breast_cancer.json

python3 templates/bio_db_lookup.py stringdb \
  --mode network \
  --gene BRCA1 --gene BRCA2 --gene TP53 \
  --species 9606 \
  --output bio/string_brca_network.csv \
  --summary bio/string_brca_network.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 1 other file in skills/science/bio-db-tools of DrugClaw/DrugClaw.

• SKILL.md
• templates/bio_db_lookup.py

Open the folder on GitHubat commit 960a6e0