Ucsc Conservation And Tfbs

If you're analyzing non-coding variants and need to know whether they land on evolutionarily conserved regions, this pulls conservation data directly from UCSC Genome Browser. It uses phastCons scores to identify functional blocks and phyloP scores to measure constraint at individual sites, both calculated from multiple alignments. The real value is quick pathogenicity signals: if a variant hits a site that hasn't changed since a common ancestor, that's worth paying attention to. Also useful for scanning regulatory elements to find conservation peaks. From Google DeepMind's science-skills collection, which explains the focus on genomics workflows. Already has 935 installs and passed multiple security audits.

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 ucsc-conservation-and-tfbs --agent claude-code

Installs into .claude/skills of the current project.

Files

Conservation Scores & TFBS Lookup (UCSC)

This skill provides access to evolutionary constraint scores and conserved elements from the UCSC Genome Browser. It retrieves scores from the PHAST package — specifically phastCons (identifying functional blocks) and phyloP (measuring individual site constraint) — calculated from multiple alignments.

Use this skill to determine if a non-coding variant hits a site that hasn't changed since a common ancestor (which is a strong signal for pathogenicity) or to find conservation peaks across a regulatory element.

Prerequisites

uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
User Notification: If .licenses/ucsc_conservation_and_tfbs_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://genome.ucsc.edu/conditions.html and https://genome.ucsc.edu/goldenPath/help/api.html, then (2) create the file recording the notification text and timestamp.