RepoAI
Browse MCPs

Encode Ccres Database

88TrustedShips scripts

Access regulatory genomics data from the ENCODE registry using GraphQL and REST queries.

What it does

Adding this skill integrates specialized command-line tools into your environment, allowing the assistant to retrieve information about cis-regulatory elements directly from the ENCODE project. It bridges the gap between raw genomic coordinates and functional biological insights by automating interactions with the SCREEN and ENCODE APIs.

When invoked, the assistant uses these scripts to extract structured metadata, such as promoters or enhancers, while managing data volume through selective filtering. It ensures that large query results remain manageable by enforcing efficient processing techniques rather than overwhelming the conversational context with raw JSON dumps.

When it earns its place

Reach for it when…

Use this to programmatically identify functional non-coding regions within human genomic sequences or to filter high-confidence biosamples based on core epigenetic markers like DNase and CTCF signatures.

Look elsewhere when…

This is not intended for high-throughput genomic alignment tasks or processing proprietary private datasets. If your work involves general sequence analysis, sequence alignment, or visualization of genomic tracks, use established bioinformatics packages instead of this API-focused tool.

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 enhancers near these coordinates on chromosome 11
  • List high-confidence biosamples from the ENCODE registry
  • Which genes are linked to this specific cCRE accession
  • Get orthologous regulatory elements in a different assembly

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/encode_ccres_database ~/.claude/skills/encode-ccres-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/encode_ccres_database .claude/skills/encode-ccres-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

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

How skills and MCP servers differ →