RepoAI
Browse MCPs

Ucsc Conservation and Tfbs

88TrustedShips scripts

Retrieve evolutionary constraint data and transcription factor sites from UCSC archives.

What it does

Ucsc Conservation and Tfbs integrates specialized scripts to query genomic datasets for evolutionary conservation scores and transcription factor binding evidence. By installing this, your assistant gains the ability to retrieve site-specific constraint metrics like phyloP and phastCons, alongside regulatory binding site data directly from Genome Browser resources.

This is a data-retrieval skill intended for bioinformatics workflows. It automates the extraction of comparative genomics information, ensuring that query operations adhere to rate limits while handling large datasets through file-based outputs.

When it earns its place

Reach for it when…

Apply this skill when assessing the biological impact of non-coding variants or characterizing the regulatory potential of genomic regions. It is highly effective for identifying evolutionarily conserved segments that may indicate functional importance or for cross-referencing specific DNA sequences against known transcription factor binding sites.

Look elsewhere when…

Do not use this for general gene annotation tasks, such as retrieving protein coding sequences, exon boundaries, or population-level allele frequencies. This skill focuses strictly on comparative genomics and binding site data, so it lacks the scope for variant calling pipelines or high-level clinical interpretation of gene expression.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • check the evolutionary conservation score for this genome coordinate
  • find transcription factor binding sites in this enhancer region
  • compare vertebrate and primate conservation at this position
  • extract conserved functional elements for this genomic window

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/ucsc_conservation_and_tfbs ~/.claude/skills/ucsc-conservation-and-tfbs

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/ucsc_conservation_and_tfbs .claude/skills/ucsc-conservation-and-tfbs

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server

Ucsc Conservation and Tfbs changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →