RepoAI
Browse MCPs

Unibind Database

88TrustedShips scripts

Access experimentally validated transcription factor binding site datasets

What it does

Unibind Database integrates your environment with a collection of direct transcription factor and DNA interaction data. By using this skill, your assistant gains the ability to programmatically retrieve curated binding site information across multiple species, effectively turning your workspace into a bridge for molecular interaction research.

The skill provides a direct interface for exploring datasets, cell lines, and specific transcription factors. It ensures that data retrieval remains stable by managing rate limits through a specialized script, allowing you to fetch structured information in JSON format or download raw coordinate files like BED and FASTA for downstream tasks.

When it earns its place

Reach for it when…

Apply this when your work requires precise, experimentally validated transcription factor binding coordinates or when you need to audit available datasets by species, cell line, or specific experimental identifiers.

Look elsewhere when…

Do not use this to analyze expression levels, predict de novo motifs, or retrieve general genomic interval data that lacks a transcription factor binding context, as this skill is strictly for known TF-DNA interaction archives.

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.

  • find all CTCF binding datasets for Homo sapiens
  • download the BED file for this specific binding experiment
  • what cell lines are available for this transcription factor in the database
  • list the datasets associated with the GSE60130 identifier

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/unibind_database ~/.claude/skills/unibind-database

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/unibind_database .claude/skills/unibind-database

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

Unibind Database changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →