string-database

97 / 100 · Low risk

Fine to try.

By lamm-mit/scienceclaw (GitHub) · coding · 251 stars · scanned at commit 894598c

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.

Works with any agent that supports SKILL.md skills.

What this skill can do

Connects to the internet

This is disclosed by the author in the skill's SKILL.md or README.

Found in 12 places.

skills/string-database/references/string_reference.md, line 389response = requests.get(url, params=params)
skills/string-database/references/string_reference.md, line 394import urllib.request
skills/string-database/references/string_reference.md, line 396response = urllib.request.urlopen(url)

Show 9 more

skills/string-database/scripts/string_api.py, line 14import urllib.request
skills/string-database/scripts/string_api.py, line 66with urllib.request.urlopen(url, data=data) as response:
skills/string-database/scripts/string_api.py, line 119with urllib.request.urlopen(url) as response:
skills/string-database/scripts/string_api.py, line 168with urllib.request.urlopen(url) as response:
skills/string-database/scripts/string_api.py, line 212with urllib.request.urlopen(url) as response:
skills/string-database/scripts/string_api.py, line 251with urllib.request.urlopen(url) as response:
skills/string-database/scripts/string_api.py, line 293with urllib.request.urlopen(url) as response:
skills/string-database/scripts/string_api.py, line 331with urllib.request.urlopen(url) as response:
skills/string-database/scripts/string_api.py, line 350with urllib.request.urlopen(url) as response:

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'string-database' ] || [ -L ~/.agents/skills/'string-database' ]; then echo 'A skill folder named string-database already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/lamm-mit/scienceclaw' "$d" && git -C "$d" checkout --quiet '894598cd3a90891a077c254566276bd379038bad' -- 'skills/string-database' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/string-database' ~/.agents/skills/'string-database' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'string-database' ~/.claude/skills/'string-database' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for lamm-mit/scienceclaw shows the score of its lowest-scoring skill.

SkillTrust badge for lamm-mit/scienceclaw

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/lamm-mit/scienceclaw.svg)](https://zalavijaysinh.github.io/skilltrust/repos/lamm-mit/scienceclaw/)

Score history

Date	Version	Score
2026-11-13	`894598c`	97