Unibind Database

This gives Claude direct access to UniBind, a cross-species database of transcription factor DNA binding data that merges ChIP-seq peaks with JASPAR binding profiles. You'd reach for it when analyzing gene regulation, working with TF binding sites, or doing comparative genomics across any of the 9 supported species. It handles license notification automatically and requires uv as a dependency, which is a reasonable trade for programmatic access to what's otherwise a web-only resource. From DeepMind's science-skills collection, so the integration is solid, but check the Snyk warning before using it in production.

skills.sh installs: 2.2K
GitHub stars: 3.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add google-deepmind/science-skills --skill unibind-database --agent claude-code

Installs into .claude/skills of the current project.

Files

UniBind Database Skill

UniBind is a database of direct TF–DNA interactions across 9 species, integrating ChIP-seq peaks with JASPAR TF binding profiles via the DAMO framework.

Prerequisites

uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
User Notification: If .licenses/unibind_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://unibind.uio.no/ and https://unibind.uio.no/api/overview, then (2) create the file recording the notification text and timestamp.

Quick Start

Query commands print JSON to stdout by default. Most outputs are small enough to read directly. For large outputs (list_cell_lines, list_tfs), pipe through jq to extract only the fields you need.

uv run <SKILL DIR>/scripts/unibind_api.py list_species

The download_tfbs command writes BED/FASTA files to --output-dir instead. You may optionally use --output <path> on any query command to save results to a file if needed.