New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Bioservices

by aipoch in aipoch/medical-research-skills

Unified Python access to 40+ bioinformatics web services; use when you need to query multiple databases (e.g., UniProt/KEGG/ChEMBL/Reactome) with one consistent API in a single workflow, especially…

MITAuto-check passedResearch & Science

Install Bioservices

skills CLI
$ npx skills add aipoch/medical-research-skills --skill bioservices -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aipoch/medical-research-skills bioservices --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'scientific-skills/Data Analysis/bioservices' .claude/skills/bioservices && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bioservices
GitHub stars
2k
Token cost
~1.7k tokens
SKILL.md length
407 words
Files
9 (incl. scripts, references)
Skills in repo
567
Repo updated
First seen
Licence
MIT

At a glance

Unified Python access to 40+ bioinformatics web services; use when you need to query multiple databases (e.g., UniProt/KEGG/ChEMBL/Reactome) with one consistent API in a single workflow, especially…

  • Works in 6 steps: UniProt search + FASTA retrieval → UniProt → KEGG ID mapping → KEGG pathway lookup and KGML relation… → …
  • You need to query multiple databases (e.g.
  • SKILL.md covers When to Use, Key Features, Dependencies and Example Usage, plus 1 more section
  • Runs Python scripts from its folder; calls python

What it does

Bioservices is an agent skill from aipoch/medical-research-skills. Unified Python access to 40+ bioinformatics web services; use when you need to query multiple databases (e.g., UniProt/KEGG/ChEMBL/Reactome) with one consistent API in a single workflow, especially for cross-database analysis and identifier mapping.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and reference files (for example `bioservices_audit_result_v1.json`, `references/identifier_mapping.md` and `references/services_reference.md`).

It sits in Research & Science, covering Bioinformatics. It works with Python and UniProt. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.

When your agent uses it

  • You need to query multiple databases (e.g.
  • UniProt/KEGG/ChEMBL/Reactome) with one consistent API in a single workflow
  • Especially for cross-database analysis and identifier mapping

Example prompts

  • “/bioservices”

Requirements

  • Python 3

Workflow steps

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

  1. UniProt search + FASTA retrieval
  2. UniProt → KEGG ID mapping
  3. KEGG pathway lookup and KGML relation extraction
  4. QuickGO annotation query
  5. PSICQUIC interaction query
  6. KEGG compound lookup + UniChem mapping to ChEMBL

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. 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 4 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Bioservices loads about 1.7k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 407 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~15k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 407 words, ~1,734 tokens.

Download SKILL.mdSave it as .claude/skills/bioservices/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
bioservices
description
Unified Python access to 40+ bioinformatics web services; use when you need to query multiple databases (e.g., UniProt/KEGG/ChEMBL/Reactome) with one consistent API in a single workflow, especially for cross-database analysis and identifier mapping.
license
MIT
author
AIPOCH

Source: https://github.com/aipoch/medical-research-skills

When to Use

  • You need to retrieve and combine biological data from multiple databases (e.g., UniProt + KEGG + GO) in one Python workflow.
  • You need cross-database identifier mapping (e.g., UniProt ↔ KEGG, KEGG compound ↔ ChEMBL) as part of downstream analysis.
  • You want to programmatically explore pathways and networks (e.g., KEGG pathway parsing, exporting interactions to SIF).
  • You need service-agnostic access across many providers (REST and SOAP/WSDL) without writing custom clients per service.
  • You are building integrated bioinformatics pipelines (protein → sequence → BLAST → pathways → interactions) that span multiple resources.

Key Features

  • Unified API for ~40+ bioinformatics services (single Python package, consistent patterns).
  • Transparent protocol handling (REST and SOAP/WSDL).
  • Protein-centric workflows via UniProt (search, retrieve, ID mapping).
  • Pathway discovery and parsing via KEGG (KGML parsing, relations extraction, SIF export).
  • Compound lookup and cross-referencing (e.g., KEGG compounds + UniChem mapping to ChEMBL).
  • Sequence analysis integrations (e.g., NCBI BLAST asynchronous jobs).
  • Ontology and annotation queries (e.g., QuickGO).
  • Protein–protein interaction queries via PSICQUIC-compatible services.

Dependencies

  • python >= 3.9
  • bioservices (install via pip/uv; version depends on your environment)

Optional (commonly used alongside returned formats):

  • pandas >= 1.5 (TSV/tabular outputs)
  • beautifulsoup4 >= 4.11 (XML parsing)
  • lxml >= 4.9 (faster XML parsing)
  • networkx >= 2.8 (network analysis of interactions)
  • biopython >= 1.81 (sequence handling for FASTA outputs)

Example Usage

A single runnable script that demonstrates a cross-service workflow:

  1. UniProt search + FASTA retrieval
  2. UniProt → KEGG ID mapping
  3. KEGG pathway lookup and KGML relation extraction
  4. QuickGO annotation query
  5. PSICQUIC interaction query
  6. KEGG compound lookup + UniChem mapping to ChEMBL
python
"""
Run:
  uv pip install bioservices pandas
  python bioservices_example.py

Notes:
- Some services may rate-limit or be temporarily unavailable.
- NCBI BLAST requires an email; this example does not run BLAST to stay lightweight.
"""

from bioservices import UniProt, KEGG, QuickGO, PSICQUIC, UniChem


def main():
    # --- UniProt: search + retrieve ---
    u = UniProt(verbose=False)

    # Search by entry name (example: ZAP70 human)
    tab = u.search("ZAP70_HUMAN", frmt="tab", columns="id,entry name,genes,organism")
    print("UniProt search (tab):")
    print(tab.splitlines()[0:3], "\n")  # show header + first rows

    uniprot_ac = "P43403"  # ZAP70_HUMAN accession
    fasta = u.retrieve(uniprot_ac, "fasta")
    print("UniProt FASTA header:")
    print(fasta.splitlines()[0], "\n")

    # --- UniProt: identifier mapping (UniProt -> KEGG) ---
    mapping = u.mapping(fr="UniProtKB_AC-ID", to="KEGG", query=uniprot_ac)
    print("UniProt -> KEGG mapping:")
    print(mapping, "\n")

    # --- KEGG: pathway discovery + parsing ---
    k = KEGG(verbose=False)
    k.organism = "hsa"

    # Example gene: ZAP70 is KEGG gene hsa:7535
    pathways = k.get_pathway_by_gene("7535", "hsa")
    print("KEGG pathways containing hsa:7535:")
    print(pathways, "\n")

    pathway_id = "hsa04660"  # T cell receptor signaling pathway (example)
    kgml_relations = k.parse_kgml_pathway(pathway_id).get("relations", [])
    print(f"KEGG KGML relations count for {pathway_id}: {len(kgml_relations)}\n")

    # Export to SIF (useful for network tools)
    sif = k.pathway2sif(pathway_id)
    print(f"KEGG SIF preview for {pathway_id}:")
    print("\n".join(sif.splitlines()[:5]), "\n")

    # --- QuickGO: GO annotations for a UniProt protein ---
    g = QuickGO(verbose=False)
    ann = g.Annotation(protein=uniprot_ac, format="tsv")
    print("QuickGO annotation TSV header:")
    print(ann.splitlines()[0], "\n")

    # --- PSICQUIC: interaction query (database name may vary by availability) ---
    p = PSICQUIC(verbose=False)
    # Example query: ZAP70 interactions in human
    # Choose a database that is active in your environment; "intact" is commonly available.
    interactions = p.query("intact", "ZAP70 AND species:9606")
    print("PSICQUIC query result preview:")
    print("\n".join(interactions.splitlines()[:3]), "\n")

    # --- Compound workflow: KEGG compound -> UniChem -> ChEMBL ---
    # Example: Geldanamycin
    cpd_hits = k.find("compound", "Geldanamycin")
    print("KEGG compound find('Geldanamycin'):")
    print(cpd_hits, "\n")

    # If you already know the KEGG compound ID:
    kegg_compound_id = "C11222"
    uc = UniChem(verbose=False)
    chembl_id = uc.get_compound_id_from_kegg(kegg_compound_id)
    print(f"UniChem KEGG {kegg_compound_id} -> ChEMBL:")
    print(chembl_id, "\n")


if __name__ == "__main__":
    main()
Show full SKILL.md (161 more words)Show less

Implementation Details

  • Service objects: Each remote resource is exposed as a Python class (e.g., UniProt, KEGG, QuickGO, PSICQUIC, NCBIblast). You instantiate a client and call methods that wrap the underlying endpoints.
  • Protocols: BioServices abstracts REST and SOAP/WSDL services behind similar method calls; returned payloads may be text (TSV), XML, JSON-like dicts, or FASTA.
  • Common parameters
    • verbose: toggles HTTP/request logging (verbose=False is recommended for scripts).
    • TIMEOUT: per-service timeout control (useful for slow networks or large responses).
    • Service-specific parameters (examples):
      • UniProt: search(query, frmt=..., columns=...), retrieve(accession, format), mapping(fr=..., to=..., query=...)
      • KEGG: find(db, query), get(entry_id), parse(raw), parse_kgml_pathway(pathway_id), pathway2sif(pathway_id)
      • NCBI BLAST: asynchronous job model (run(...) → getStatus(jobid) → getResult(jobid, ...))
  • Data handling guidance
    • TSV/tabular outputs: load into pandas.read_csv(io.StringIO(text), sep="\t")
    • XML outputs: parse with BeautifulSoup or lxml
    • Network exports (SIF): import into NetworkX/Cytoscape-compatible tooling
  • Operational considerations
    • Many endpoints are rate-limited; implement retries/backoff for production pipelines.
    • Some services require contact information (e.g., NCBI BLAST email) and may enforce usage policies.
    • Availability varies by provider; design workflows to degrade gracefully (try/except, fallbacks).

© aipoch, 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 8 other files (scripts, references) in scientific-skills/Data Analysis/bioservices of aipoch/medical-research-skills.

  • SKILL.md
  • bioservices_audit_result_v1.json
  • 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 686e09d

Compare with similar skills

Bioservices next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bioservices compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bioservices this skillaipoch/medical-research-skills2k—~1.7kAutomated safety check: PassMIT
UniProt Database Accessdavila7/claude-code-templates32k15 repos~1.7kAutomated safety check: PassMIT
Bioservicesdavila7/claude-code-templates32k11 repos~2.5kAutomated safety check: PassMIT
Ggetdavila7/claude-code-templates32k11 repos~6.3kAutomated safety check: PassMIT
BioservicesK-Dense-AI/scientific-agent-skills48k1 repos~3kAutomated safety check: NotesMIT
Research Biomedical Databasesaws-samples/amazon-bedrock-agents-healthcare-lifesciences274—~3.1kAutomated safety check: PassMIT-0

Similar skills

  • UniProt Database Access

    davila7/claude-code-templates

    Queries the UniProt REST API directly to search proteins, fetch FASTA sequences, map IDs between databases and read Swiss-Prot and TrEMBL entries.

    32k GitHub starsUsed in 15 repos~1.7k tokens
    Research & ScienceAuto-check passed

  • Bioservices

    davila7/claude-code-templates

    Primary Python tool for 40+ bioinformatics services. An agent skill from davila7/claude-code-templates.

    32k GitHub starsUsed in 11 repos~2.5k tokens
    Research & ScienceAuto-check passed

  • Gget

    davila7/claude-code-templates

    CLI/Python toolkit for rapid bioinformatics queries. An agent skill from davila7/claude-code-templates.

    32k GitHub starsUsed in 11 repos~6.3k tokens
    Research & ScienceAuto-check passed

  • Bioservices

    K-Dense-AI/scientific-agent-skills

    Provides a Python interface to bioinformatics services including UniProt, KEGG, ChEMBL, Reactome, QuickGO, and UniChem.

    48k GitHub starsUsed in 1 repo~3k tokens
    Research & ScienceAuto-check: notes

  • Research Biomedical Databases

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    A skill your agent uses when querying biomedical databases (UniProt, ClinVar, gnomAD, PDB, Reactome, Open Targets, etc.) via the Biomni AgentCore Gateway MCP server.

    274 GitHub stars~3.1k tokensUpdated 7 days ago
    Research & ScienceAuto-check passed

  • Biopython

    lamm-mit/scienceclaw

    Computational molecular biology library (sequence I/O, alignment, phylogenetics).

    244 GitHub stars~3.9k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from aipoch/medical-research-skills

All 567 skills in this repo

  • Academic Poster Generator

    aipoch/medical-research-skills

    Complete workflow for generating academic research posters from PDF literature; use when you need to extract paper content from PDFs and produce a LaTeX-based poster…

    2k GitHub stars~2.2k tokensUpdated 21 days ago
    Auto-check passed

  • Diagnostic Study Quality Assessment Quadas

    aipoch/medical-research-skills

    Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool.

    2k GitHub stars~1.4k tokensUpdated 21 days ago
    Auto-check passed

  • Exploratory Data Analysis

    aipoch/medical-research-skills

    Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.

    2k GitHub stars~3.7k tokensUpdated 21 days ago
    Auto-check passed

  • Iso Certification

    aipoch/medical-research-skills

    A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS.

    2k GitHub stars~1.8k tokensUpdated 21 days ago
    Auto-check passed

  • Journal Skills

    aipoch/medical-research-skills

    Recommends target journals for manuscript submission by analyzing the paper topic/abstract and the journal distribution of similar PubMed literature; use when users ask for journal…

    2k GitHub stars~1.7k tokensUpdated 21 days ago
    Auto-check passed

  • Latex Posters

    aipoch/medical-research-skills

    Creates academic-poster writing packages for LaTeX using beamerposter, tikzposter, or baposter.

    2k GitHub stars~1.3k tokensUpdated 21 days ago
    Auto-check passed

Works with

Categories

Questions about Bioservices

What does Bioservices do?

Unified Python access to 40+ bioinformatics web services; use when you need to query multiple databases (e.g., UniProt/KEGG/ChEMBL/Reactome) with one consistent API in a single workflow, especially…. Bioservices is an agent skill from aipoch/medical-research-skills., UniProt/KEGG/ChEMBL/Reactome) with one consistent API in a single workflow, especially for cross-database analysis and identifier mapping.

When should I use Bioservices?

Bioservices fits situations like: you need to query multiple databases (e.g; uniProt/KEGG/ChEMBL/Reactome) with one consistent API in a single workflow; especially for cross-database analysis and identifier mapping.

How do I install Bioservices in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill bioservices -a claude-code`. Or copy the skill folder (scientific-skills/Data Analysis/bioservices in aipoch/medical-research-skills) into .claude/skills/bioservices in your project. Claude Code loads it when a task matches its description.

How do I install Bioservices in Codex?

Run `npx skills add aipoch/medical-research-skills --skill bioservices -a codex`. Or copy the skill folder (scientific-skills/Data Analysis/bioservices in aipoch/medical-research-skills) into .agents/skills/bioservices in your project. Codex loads it when a task matches its description.

Can I use Bioservices in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aipoch/medical-research-skills --skill bioservices -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bioservices, .gemini/skills/bioservices, .github/skills/bioservices and .opencode/skills/bioservices in your project.

What does Bioservices need to run?

Going by SKILL.md and its folder, Bioservices needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Bioservices access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bioservices safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Bioservices use?

Bioservices is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bioservices use?

About 1.7k tokens (SKILL.md is roughly 6.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Bioservices?

Skills that share tags, products or a category with Bioservices: UniProt Database Access (davila7/claude-code-templates, 32k stars), Bioservices (davila7/claude-code-templates, 32k stars), Gget (davila7/claude-code-templates, 32k stars) and Bioservices (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bioservices?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,974 GitHub stars. The repository holds 567 skills in this directory. The repository was last updated on September 17, 2026.

Source: aipoch/medical-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.