Skills uniprot-database

📦

uniprot-database

Name: uniprot-database
Author: davila7

Content revision r2 Low Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Query UniProt Protein Data

Protein searches and identifier mapping often require careful UniProt REST syntax. This skill provides focused guidance and a Python client for reliable retrieval.

Supports: Claude Codex Code(CC)

🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "uniprot-database" from https://skillstore.io/skills/davila7-uniprot-database.md and its manifest at https://skillstore.io/api/skills/davila7-uniprot-database/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/davila7-uniprot-database.md Signed manifest GET /api/skills/davila7-uniprot-database/manifest Signed lockfile GET /api/skills/davila7-uniprot-database/lockfile

Test it

Using "uniprot-database". Find the reviewed human insulin precursor entry.

Expected outcome:

P01308, INS_HUMAN. Reviewed Swiss-Prot entry for insulin in Homo sapiens; gene INS; sequence length 110 amino acids.

Using "uniprot-database". Map a supplied list of UniProt accessions to PDB.

Expected outcome:

A mapping summary lists each accession, matching PDB identifiers, unmapped inputs, and cases where one protein maps to multiple structures.

Using "uniprot-database". Find five reviewed human kinases with known structures.

Expected outcome:

A compact table lists five accessions with gene names, protein names, sequence lengths, and PDB cross-references.

Security Audit

Low Risk

v9 • 7/23/2026 Open versioned report

All 129 static alerts are false positives after contextual review. Backtick alerts are Markdown or JavaScript literals; network calls target documented UniProt endpoints, while file writes are explicit download examples. The Python ID-mapping helper has unbounded polling and lacks request timeouts, creating a low-severity availability risk.

Files scanned

1,765

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Low

scripts/uniprot_client.py:180-188

Unbounded ID-mapping polling

The ID-mapping loop has no maximum attempts, and requests omit timeouts. A stalled API can keep an agent process occupied indefinitely.

The loop condition is unconditional and has no deadline or attempt limit. The surrounding requests also omit timeout arguments.

Risk Factors

⚙️ External commands (46)

references/api_examples.md:251-262 references/api_examples.md:267-281 references/api_examples.md:301-314 references/api_examples.md:314-322 SKILL.md:31-49 SKILL.md:49-51 SKILL.md:51-63 SKILL.md:63-65 SKILL.md:65-72 SKILL.md:72-73 SKILL.md:73-74 SKILL.md:74-82 SKILL.md:82-92 SKILL.md:92-101 SKILL.md:101-102 SKILL.md:102-103 SKILL.md:103-104 SKILL.md:104-105 SKILL.md:105-106 SKILL.md:106-107 SKILL.md:107-108 SKILL.md:108-109 SKILL.md:109-110 SKILL.md:110-112 SKILL.md:112-114 SKILL.md:114-118 SKILL.md:118-120 SKILL.md:120-121 SKILL.md:121-122 SKILL.md:122-123 SKILL.md:123-124 SKILL.md:124-133 SKILL.md:133-137 SKILL.md:137-140 SKILL.md:140-146 SKILL.md:146-149 SKILL.md:149-152 SKILL.md:152-155 SKILL.md:155-158 SKILL.md:158-160 SKILL.md:160-164 SKILL.md:164-175 SKILL.md:175-178 SKILL.md:178-179 SKILL.md:179-180 SKILL.md:180-181

🌐 Network access (50)

📁 Filesystem access (2)

references/api_examples.md:105 references/api_examples.md:395

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/davila7-uniprot-database/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/davila7-uniprot-database/security.svg)](https://skillstore.io/skills/davila7-uniprot-database?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/davila7-uniprot-database?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-uniprot-database/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/davila7-uniprot-database.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

davila7. (2026). uniprot-database security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-uniprot-database/audits/9

BibTeX citation

@techreport{davila7-davila7-uniprot-database-2026,
  author = {davila7},
  title = {uniprot-database security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/davila7-uniprot-database/audits/9},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "uniprot-database security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "davila7"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/davila7-uniprot-database/audits/9"
identifiers:
  - type: other
    value: "skillstore:davila7-uniprot-database:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

davila7 Recommended Current

davila7-uniprot-database

Skillstore Score 78

Evidence Confidence High

Skillstore usage 10

Updated

2026-08-21

K-Dense-AI

k-dense-ai-uniprot-database

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 12

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Retrieve proteins for experiments

Find reviewed entries and FASTA sequences for genes or proteins selected during experimental planning.

Normalize identifiers for analysis

Convert mixed protein identifiers into UniProt accessions before merging datasets or running pipelines.

Teach reproducible database queries

Demonstrate field selection, review-status filters, pagination, and output formats with clear UniProt examples.

Try These Prompts

Find a protein entry

Find UniProt entry {accession}. Return its reviewed status, protein name, organism, gene names, sequence length, and available functional summary.

Search reviewed proteins

Search UniProt for reviewed {protein_family} proteins in {organism}. Return up to {limit} accessions with gene names, lengths, and functions.

Map database identifiers

Map these {source_database} identifiers to {target_database}: {identifiers}. Report successful mappings, failed identifiers, duplicate mappings, and relevant UniProt accessions.

Design a reproducible dataset

Build a UniProt query for {research_question}. Apply {filters}, select only {fields}, explain review status, paginate safely, and summarize data-quality caveats.

Best Practices

Prefer reviewed Swiss-Prot entries when curated evidence is required.
Request only needed fields and use bounded result sizes before streaming complete datasets.
Record the query, selected fields, output format, and retrieval date for reproducibility.

Avoid

Do not request every annotation field when only sequences or identifiers are needed.
Do not treat unreviewed TrEMBL predictions as manually curated evidence.
Do not submit confidential sequences or identifiers to public UniProt endpoints.