uniprot

uniprot is a skill for Claude Code, Codex from adaptyvbio/protein-design-skills. It costs 79 tokens per session (1,272 once invoked), scanned A, original, MIT.

A way to retrieve protein sequences and scientific annotations from UniProt, a public database of protein information.

In plain words
What is it for?
Use it to look up proteins by accession, fetch sequences, inspect functional annotations and domain boundaries, find related proteins or variants, and cross-reference PDB structures.
Why use it?
It avoids manually searching database pages and helps connect sequence data with known functions, regions, variants, and related structures.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to look up proteins by accession, fetch sequences, inspect functional annotations and domain boundaries, find related proteins or variants, and cross-reference PDB structures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adaptyvbio/protein-design-skills/uniprot
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add adaptyvbio/protein-design-skills --skill uniprot
Clone the repo
git clone --depth 1 https://github.com/adaptyvbio/protein-design-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for uniprot

README.md
[![agentmods](https://agentmods.dev/badge/skills/adaptyvbio/protein-design-skills/uniprot/github.svg)](https://agentmods.dev/skills/adaptyvbio/protein-design-skills/uniprot)
Your own site
<a href="https://agentmods.dev/skills/adaptyvbio/protein-design-skills/uniprot"><img src="https://agentmods.dev/badge/skills/adaptyvbio/protein-design-skills/uniprot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for uniprot

Your own site · 80×15
<a href="https://agentmods.dev/skills/adaptyvbio/protein-design-skills/uniprot"><img src="https://agentmods.dev/badge/skills/adaptyvbio/protein-design-skills/uniprot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,272 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.01272
Opus 5 $0.00039 $0.00636
Sonnet 5 $0.00016 $0.00254
Haiku 4.5 $0.00008 $0.00127

Measured 12d ago against content hash c6355471b04e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

uniprot scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl "https://rest.uniprot.org/uniprotkb/P00533.fasta"
skills/uniprot/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UniProt Database Access

Note: This skill uses the UniProt REST API directly. No Modal deployment needed - all operations run locally via HTTP requests.

Fetching Sequences

By Accession

# FASTA format
curl "https://rest.uniprot.org/uniprotkb/P00533.fasta"

# JSON format with annotations
curl "https://rest.uniprot.org/uniprotkb/P00533.json"

Using Python

import requests

def get_uniprot_sequence(accession):
    """Fetch sequence from UniProt."""
    url = f"https://rest.uniprot.org/uniprotkb/{accession}.fasta"
    response = requests.get(url)
    if response.ok:
        lines = response.text.strip().split('\n')
        header = lines[0]
        sequence = ''.join(lines[1:])
        return header, sequence
    return None, None

Getting Annotations

Full Entry

def get_uniprot_entry(accession):
    """Fetch full UniProt entry as JSON."""
    url = f"https://rest.uniprot.org/uniprotkb/{accession}.json"
    response = requests.get(url)
    return response.json() if response.ok else None

entry = get_uniprot_entry("P00533")
print(f"Protein: {entry['proteinDescription']['recommendedName']['fullName']['value']}")

Domain Boundaries

def get_domains(accession):
    """Extract domain annotations."""
    entry = get_uniprot_entry(accession)
    domains = []

    for feature in entry.get('features', []):
        if feature['type'] == 'Domain':
            domains.append({
                'name': feature.get('description', ''),
                'start': feature['location']['start']['value'],
                'end': feature['location']['end']['value']
            })

    return domains

# Example: EGFR domains
domains = get_domains("P00533")
# [{'name': 'Kinase', 'start': 712, 'end': 979}, ...]

Searching UniProt

By Gene Name

def search_uniprot(query, organism=None, limit=10):
    """Search UniProt by query."""
    url = "https://rest.uniprot.org/uniprotkb/search"
    params = {
        "query": query,
        "format": "json",
        "size": limit
    }
    if organism:
        params["query"] += f" AND organism_id:{organism}"

    response = requests.get(url, params=params)
    return response.json()['results']

# Search for human EGFR
results = search_uniprot("EGFR", organism=9606)

Read the full file on GitHub · 192 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 192 lines · 79 tokens per session scan A c6355471b04e

Subscribe to this mod's changes

uniprot is a skill published in the GitHub repository adaptyvbio/protein-design-skills (159 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 1,272 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

uniprot

Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence…

zongtingwei/Bioclaw_Skills_Hub · 79 tokens

uniprot

Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence…

BioTender-max/awesome-bio-agent-skills · 79 tokens

uniprot

Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence…

BioTender-max/ProteinClaw · 79 tokens

protein-function-prediction

Predict protein function and properties from amino acid sequence using BioT5. Use this skill when: (1) You have a protein sequence and want to understand its biological function, (2) You need to identify enzyme activity, pathway involvement, or molecular interactions, (3) You want a concise description of protein…

PharMolix/OpenBioMed · 73 tokens

protein-binder-design

Design and validate de novo protein binders with the current NVIDIA BioNeMo Agent Toolkit workflow, while adapting honestly when NVIDIA-hosted credentials are unavailable.

synthetic-sciences/openscience · 35 tokens

biomed-skill-creator

Create new biomedical skills or improve existing ones for the OpenBioMed toolkit. Use this skill when: (1) Creating a new skill from scratch, (2) Capturing a workflow as a reusable skill, (3) Automating a biomedical task, (4) Improving an existing skill. This skill guides through an interactive process: define intent…

PharMolix/OpenBioMed · 89 tokens