Agent skill

Uniprot

Protein sequence, function, and annotation lookup. An agent skill from lamm-mit/scienceclaw.

Apache-2.0Auto-check passedResearch & Science

Install Uniprot

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill uniprot -a claude-code

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

GitHub CLI

$ gh skill install lamm-mit/scienceclaw uniprot --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/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/uniprot .claude/skills/uniprot && 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/

Paste into Claude Code

Install the "uniprot" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/uniprot into .claude/skills/uniprot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uniprot", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/lamm-mit/scienceclaw/tree/main/skills/uniprot

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill uniprot -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw uniprot --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/uniprot .agents/skills/uniprot && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "uniprot" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/uniprot into .agents/skills/uniprot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uniprot", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill uniprot -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw uniprot --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/uniprot .cursor/skills/uniprot && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "uniprot" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/uniprot into .cursor/skills/uniprot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uniprot", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/lamm-mit/scienceclaw.git --path skills/uniprot

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill uniprot -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw uniprot --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/uniprot .gemini/skills/uniprot && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "uniprot" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/uniprot into .gemini/skills/uniprot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uniprot", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw uniprot

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill uniprot -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/uniprot .github/skills/uniprot && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "uniprot" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/uniprot into .github/skills/uniprot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uniprot", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add lamm-mit/scienceclaw --skill uniprot -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install lamm-mit/scienceclaw uniprot --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/uniprot .opencode/skills/uniprot && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "uniprot" agent skill from https://github.com/lamm-mit/scienceclaw/tree/main/skills/uniprot into .opencode/skills/uniprot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "uniprot", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: uniprot
GitHub stars: 244
Token cost: ~1.2k tokens
SKILL.md length: 406 words
Files: 3 (incl. scripts)
Skills in repo: 86
Repo updated: Aug 21, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Protein sequence, function, and annotation lookup. An agent skill from lamm-mit/scienceclaw.

Works in 2 steps: UniProt: --search "KRAS_HUMAN" or… → PubChem/ChEMBL: search "KRAS G12C…
Tasks that involve Protein structure and design
SKILL.md covers Overview, Usage, Parameters and Examples, plus 4 more sections
Runs Python scripts from its folder; calls python3

What it does

Uniprot is an agent skill from lamm-mit/scienceclaw. Protein sequence, function, and annotation lookup. Query MUST be a bare gene symbol or protein name — 1 to 3 words maximum. Valid examples: 'KRAS', 'EGFR', 'BTK', 'TP53', 'Bruton tyrosine kinase', 'P01116'. If the topic is 'sotorasib KRAS G12C', the correct query is 'KRAS'. If the topic is 'imatinib BCR-ABL resistance', the correct query is 'BCR-ABL'. Strip the drug name, mutation label, and all mechanism words — pass only the protein or gene name.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/uniprot_fetch.py`).

It sits in Research & Science, covering Protein structure and design. It works with UniProt. The licence is Apache-2.0.

When your agent uses it

Tasks that involve Protein structure and design

Example prompts

“Bruton tyrosine kinase”
“P01116”
“sotorasib KRAS G12C”
“/uniprot”

Requirements

Python 3

Workflow steps

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

UniProt: --search "KRAS_HUMAN" or --accession P01116 → get KRAS protein structure, active site residues (Cys12, Gly12), domains
PubChem/ChEMBL: search "KRAS G12C inhibitor" or "sotorasib" → get inhibitor SMILES, IC50, selectivity data

What it can do on your machine

Read from SKILL.md and the folder at commit ab9aba1. 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 2 files in scripts/ (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

Uniprot loads about 1.2k tokens when it runs. Until then it costs about 115 tokens; SKILL.md has 406 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~115
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k

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 lamm-mit/scienceclaw at commit ab9aba1, republished under its Apache-2.0 licence (© lamm-mit). 406 words, ~1,238 tokens.

Download SKILL.mdSave it as .claude/skills/uniprot/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: uniprot
description: Protein sequence, function, and annotation lookup. Query MUST be a bare gene symbol or protein name — 1 to 3 words maximum. Valid examples: 'KRAS', 'EGFR', 'BTK', 'TP53', 'Bruton tyrosine kinase', 'P01116'. If the topic is 'sotorasib KRAS G12C', the correct query is 'KRAS'. If the topic is 'imatinib BCR-ABL resistance', the correct query is 'BCR-ABL'. Strip the drug name, mutation label, and all mechanism words — pass only the protein or gene name.

UniProt Protein Lookup

Query the UniProt protein database to retrieve protein sequences, annotations, functional information, and cross-references.

Overview

UniProt is the world's most comprehensive protein sequence and functional annotation database. This skill provides access to:

Protein sequences (FASTA format)
Functional annotations
Gene ontology (GO) terms
Protein domains and families
Cross-references to PDB, Pfam, InterPro, etc.

Usage

Fetch protein by accession:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --accession P53_HUMAN

Fetch by UniProt ID:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --accession P04637

Search for proteins:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --search "insulin human"

Get sequence only:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --accession P53_HUMAN --format fasta

Get full entry with all annotations:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --accession P53_HUMAN --format detailed

Parameters

Parameter	Description	Default
`--accession`	UniProt accession or entry name	-
`--search`	Search query	-
`--organism`	Filter by organism (e.g., "human", "9606")	-
`--reviewed`	Only Swiss-Prot (reviewed) entries	False
`--max-results`	Maximum results for search	10
`--format`	Output format: summary, detailed, fasta, json	summary
`--include-features`	Include sequence features	False
`--include-xrefs`	Include cross-references	False

Examples

Look up human p53 tumor suppressor:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --accession P53_HUMAN --format detailed

Search for kinases in human:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --search "kinase" --organism human --reviewed --max-results 20

Get FASTA sequence for multiple proteins:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --accession "P53_HUMAN,BRCA1_HUMAN,EGFR_HUMAN" --format fasta

Search with advanced query:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --search "gene:TP53 AND organism_id:9606"

Get protein with PDB cross-references:

bash

python3 {baseDir}/scripts/uniprot_fetch.py --accession P53_HUMAN --include-xrefs

Output Fields

Summary

Accession, entry name, protein name
Gene name, organism
Sequence length
Reviewed status

Detailed

Full protein name and alternative names
Function description
Subcellular location
Gene ontology terms
Protein domains
Post-translational modifications
Disease associations
Literature references

FASTA

Standard FASTA format sequence output.

JSON

Full UniProt entry in JSON format.

Cross-References

UniProt entries contain cross-references to:

PDB: 3D protein structures
Pfam: Protein families
InterPro: Protein signatures
GO: Gene Ontology terms
KEGG: Pathway information
Reactome: Reaction pathways
DrugBank: Drug interactions
OMIM: Disease associations

Show full SKILL.md (172 more words)Show less

Query Limitations — Read Before Using

UniProt is a protein database, not a drug/chemistry database. Queries must target proteins by name, gene, or accession. Drug or chemistry concepts will return zero results.

❌ Fails (not a protein query)	✅ Works
"KRAS covalent inhibitors"	"KRAS_HUMAN" or "P01116"
"BTK warhead optimization"	"BTK" or "BTK_HUMAN" or "Q06187"
"covalent inhibitor design"	"Bruton tyrosine kinase"
"BBB penetration ADMET"	"ABCB1 human" or "MDR1"
"kinase inhibitor selectivity"	"EGFR kinase" or "EGFR_HUMAN"

Rule: If your query describes a drug, chemical process, mechanism, or assay — use PubChem or TDC instead. UniProt answers: "What is this protein and what does it do?"

For KRAS covalent inhibitor research, the correct two-step workflow is:

UniProt: --search "KRAS_HUMAN" or --accession P01116 → get KRAS protein structure, active site residues (Cys12, Gly12), domains
PubChem/ChEMBL: search "KRAS G12C inhibitor" or "sotorasib" → get inhibitor SMILES, IC50, selectivity data

Notes

UniProt accession numbers (e.g., P04637) are stable identifiers
Entry names (e.g., P53_HUMAN) may change
Reviewed (Swiss-Prot) entries are manually curated
Unreviewed (TrEMBL) entries are computationally annotated
API has no authentication requirement

Files

SKILL.md and 2 other files (scripts) in skills/uniprot of lamm-mit/scienceclaw.

SKILL.md
scripts/__pycache__/uniprot_fetch.cpython-313.pyc
scripts/uniprot_fetch.py

Open the folder on GitHubat commit ab9aba1

Compare with similar skills

Uniprot 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.

Uniprot compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Uniprot this skilllamm-mit/scienceclaw	244	—	~1.2k	Automated safety check: Pass	Apache-2.0	1 mo ago
Alphafold Database Fetch And Analyzegoogle-deepmind/science-skills	3.2k	2 repos	~1.2k	Automated safety check: Pass	Apache-2.0	24 days ago
Bio DB ToolsDrugClaw/DrugClaw	125	—	~1.4k	Automated safety check: Pass	Apache-2.0	6 mo ago
Ggetdavila7/claude-code-templates	32k	10 repos	~6.3k	Automated safety check: Pass	MIT	today
Alphafold Databasedavila7/claude-code-templates	32k	10 repos	~4k	Automated safety check: Pass	MIT	today
Uniprot Databasegoogle-deepmind/science-skills	3.2k	1 repos	~3.1k	Automated safety check: Pass	Apache-2.0	24 days ago

Similar skills

Alphafold Database Fetch And Analyze
google-deepmind/science-skills
Retrieve and analyze AlphaFold predicted structures for a protein.
3.2k GitHub starsUsed in 2 repos~1.2k tokens
Research & ScienceAuto-check passed
Bio DB Tools
DrugClaw/DrugClaw
Query public biology databases and APIs including UniProt, RCSB PDB, AlphaFold DB, ClinVar, dbSNP, gnomAD, Ensembl, GEO, InterPro, KEGG, OpenTargets, Reactome, and STRING.
125 GitHub stars~1.4k tokensUpdated 6 mo ago
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 10 repos~6.3k tokens
Research & ScienceAuto-check passed
Alphafold Database
davila7/claude-code-templates
Access AlphaFold's 200M+ AI-predicted protein structures. An agent skill from davila7/claude-code-templates.
32k GitHub starsUsed in 10 repos~4k tokens
Research & ScienceAuto-check passed
Uniprot Database
google-deepmind/science-skills
Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef.
3.2k GitHub starsUsed in 1 repo~3.1k tokens
Research & ScienceAuto-check passed
Tooluniverse
ynulihao/AgentSkillOS
A skill your agent uses when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery.
617 GitHub starsUsed in 2 repos~2.5k tokens
Research & ScienceAuto-check passed

Questions about Uniprot

What does Uniprot do?

Protein sequence, function, and annotation lookup. An agent skill from lamm-mit/scienceclaw. Uniprot is an agent skill from lamm-mit/scienceclaw. Protein sequence, function, and annotation lookup.

When should I use Uniprot?

Uniprot fits situations like: tasks that involve Protein structure and design.

How do I install Uniprot in Claude Code?

Run `npx skills add lamm-mit/scienceclaw --skill uniprot -a claude-code`. Or copy the skill folder (skills/uniprot in lamm-mit/scienceclaw) into .claude/skills/uniprot in your project. Claude Code loads it when a task matches its description.

How do I install Uniprot in Codex?

Run `npx skills add lamm-mit/scienceclaw --skill uniprot -a codex`. Or copy the skill folder (skills/uniprot in lamm-mit/scienceclaw) into .agents/skills/uniprot in your project. Codex loads it when a task matches its description.

Can I use Uniprot 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 lamm-mit/scienceclaw --skill uniprot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/uniprot, .gemini/skills/uniprot, .github/skills/uniprot and .opencode/skills/uniprot in your project.

What does Uniprot need to run?

Going by SKILL.md and its folder, Uniprot needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Uniprot 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 Uniprot 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 Uniprot use?

Uniprot is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Uniprot use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Uniprot?

Skills that share tags, products or a category with Uniprot: Alphafold Database Fetch And Analyze (google-deepmind/science-skills, 3.2k stars), Bio DB Tools (DrugClaw/DrugClaw, 125 stars), Gget (davila7/claude-code-templates, 32k stars) and Alphafold Database (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Uniprot?

lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 86 skills in this directory. The repository was last updated on August 21, 2026.

Source: lamm-mit/scienceclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Uniprot

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

UniProt Protein Lookup

Overview

Usage

Fetch protein by accession:

Fetch by UniProt ID:

Search for proteins:

Get sequence only:

Get full entry with all annotations:

Parameters

Examples

Look up human p53 tumor suppressor:

Search for kinases in human:

Get FASTA sequence for multiple proteins:

Search with advanced query:

Get protein with PDB cross-references:

Output Fields

Summary

Detailed

FASTA

JSON

Cross-References

Query Limitations — Read Before Using

Notes

Files

Compare with similar skills

Similar skills

More from lamm-mit/scienceclaw

Related

Questions about Uniprot