Bioservices

What it does

When your agent uses it

• Tasks that involve Bioinformatics

Example prompts

• “Use the bioservices skill to provide a Python interface to bioinformatics services including UniProt, KEGG, ChEMBL, Reactome, QuickGO, and UniChem”
• “/bioservices”

Requirements

• Python 3
• Compatibility (from SKILL.md): Requires Python >=3.9,<4 with bioservices==1.16.0 and internet access. EMBL-EBI BLAST submission requires a real contact email; the bundled script reads NCBI_EMAIL or an explicit parameter.
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash

Workflow steps

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

1. 1Resolve the requested organism and entity to stable accessions. Review search
2. 2Inspect the service's actual response type, including pagination and errors.
3. 3Preserve one-to-many mappings, failed identifiers, taxonomy, database release,
4. 4Distinguish annotations and inferred associations from experimental evidence.
5. 5Run a small lookup before batching; honor provider limits and retain failures

What it can do on your machine

Read from SKILL.md and the folder at commit 92ace75. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 4 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • uv

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

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • ebi.ac.uk
  • rest.kegg.jp

  Also links to:

  • arxiv.org
  • bioservices.readthedocs.io
  • rest.uniprot.org
  • kegg.jp
  • string-db.org
  • doi.org
  • export.arxiv.org

  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.

• Compatibility

  Requires Python >=3.9,<4 with bioservices==1.16.0 and internet access. EMBL-EBI BLAST submission requires a real contact email; the bundled script reads NCBI_EMAIL or an explicit parameter.

  From compatibility in the SKILL.md frontmatter.

Context cost

Bioservices loads about 3k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 71 tokens; SKILL.md has 995 words of instructions outside code blocks.

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

~71

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

~3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~11k

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

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Bash

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); the scripts in this folder are not scanned.

SKILL.md

The full file from K-Dense-AI/scientific-agent-skills at commit 92ace75, republished under its MIT licence (© K-Dense-AI). 995 words, ~2,986 tokens.

name

bioservices

description

Provides a Python interface to bioinformatics services including UniProt, KEGG, ChEMBL, Reactome, QuickGO, and UniChem. Used for cross-database protein annotation, pathway retrieval, chemical identifier mapping, and integrated biological data workflows with BioServices.

allowed-tools

Read, Write, Edit, Bash

compatibility

Requires Python >=3.9,<4 with bioservices==1.16.0 and internet access. EMBL-EBI BLAST submission requires a real contact email; the bundled script reads NCBI_EMAIL or an explicit parameter.

license

GPLv3 license

metadata.version

1.7

metadata.last-reviewed

2026-09-30

metadata.skill-author

K-Dense Inc.

uv pip install "bioservices==1.16.0"

from bioservices import UniProt

u = UniProt(verbose=False)
u.services.TIMEOUT = 30
rows = u.search(
    "gene_exact:ZAP70 AND organism_id:9606 AND reviewed:true",
    frmt="tsv", columns="accession,gene_names,organism_name,length",
    limit=5, size=5,
)
if not isinstance(rows, str):
    raise RuntimeError("UniProt search failed")
print(rows)
fasta = u.retrieve("P43403", frmt="fasta")
record = u.retrieve("P43403", frmt="json")

mapping = u.mapping(fr="UniProtKB_AC-ID", to="KEGG", query="P43403")
if not isinstance(mapping, dict) or "results" not in mapping:
    raise RuntimeError("Mapping incomplete or failed")
kegg_ids = [row["to"] for row in mapping["results"] if row["from"] == "P43403"]
print(kegg_ids, mapping.get("failedIds", []))

from bioservices import KEGG

k = KEGG(verbose=False)
k.services.url = "https://rest.kegg.jp"
pathway_names = k.get_pathway_by_gene("7535", "hsa")  # dict: pathway ID -> name
print(pathway_names)
kgml = k.parse_kgml_pathway("hsa04660")
entries = {entry["id"]: entry for entry in kgml["entries"]}
for relation in kgml["relations"][:5]:
    print(entries[relation["entry1"]]["name"], relation["name"],
          entries[relation["entry2"]]["name"])

from bioservices import UniChem

uc = UniChem(verbose=False)
response = uc.get_compounds("CHEBI:15365", "chebi")  # aspirin
if not isinstance(response, dict) or "compounds" not in response:
    raise RuntimeError("UniChem request failed")
chembl_ids = sorted({source["compoundId"]
    for match in response["compounds"] for source in match.get("sources", [])
    if source.get("shortName") == "chembl"})
print(chembl_ids)

from bioservices import QuickGO

g = QuickGO(verbose=False)
terms = g.get_go_terms("GO:0003824")  # list of term dictionaries
page = g.Annotation(geneProductId="UniProtKB:P43403", includeFields="goName",
                    limit=100, page=1)
if not isinstance(page, dict) or "results" not in page:
    raise RuntimeError("QuickGO request failed")
for annotation in page["results"][:5]:
    print(annotation["goId"], annotation["goName"], annotation["goAspect"])
print(page["pageInfo"])  # current, total, resultsPerPage

import os
from bioservices import NCBIblast

blast = NCBIblast(verbose=False)
blast.services.url = "https://www.ebi.ac.uk/Tools/services/rest/ncbiblast"
# protein_sequence must contain the actual query sequence.
job_id = blast.run(program="blastp", sequence=protein_sequence, stype="protein",
                   database="uniprotkb", email=os.environ["NCBI_EMAIL"])
status = blast.get_status(job_id)
if status == "FINISHED":
    result_types = blast.get_result_types(job_id)
    report = blast.get_result(job_id, "out")

python scripts/protein_analysis_workflow.py P43403 --skip-blast
python scripts/pathway_analysis.py hsa output_directory/ --limit 2
python scripts/compound_cross_reference.py Geldanamycin
python scripts/batch_id_converter.py input_ids.txt --from UniProtKB_AC-ID --to KEGG
python scripts/batch_id_converter.py --list-databases

© K-Dense-AI, MIT. 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 7 other files (scripts, references) in skills/bioservices of K-Dense-AI/scientific-agent-skills.

• SKILL.md
• references/identifier_mapping.md
• references/services_reference.md
• references/workflow_patterns.md
• scripts/batch_id_converter.py
• scripts/compound_cross_reference.py
• scripts/pathway_analysis.py
• scripts/protein_analysis_workflow.py

Open the folder on GitHubat commit 92ace75

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in K-Dense-AI/scientific-agent-skills, which our catalogue first saw on October 7, 2026.

• lingxling/awesome-skills-cnclaude-scientific-skills/skills/bioservices