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.
npx -y skills add google-deepmind/science-skills --skill ucsc-conservation-and-tfbs --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills