RepoAI
Browse MCPs

AlphaFold Database Fetch and Analyze

88TrustedShips scripts

Structural insights from AlphaFold Database using specific UniProt Accession IDs.

What it does

Alphafold Database Fetch and Analyze adds the ability to retrieve and interpret computational protein models directly from the AlphaFold Database. It bridges the gap between raw database files and actionable biological insights by automating the extraction of structural confidence scores and domain architecture. By processing metadata and error matrices, the assistant produces summaries regarding folding stability and expected flexibility. This skill handles the underlying script execution required to pull structure files and error data safely. It translates technical metrics like pLDDT and PAE into human-readable assessments of rigid domains and disordered regions, allowing for rapid evaluation of a protein's potential conformation.

When it earns its place

Reach for it when…

Apply this when you have a specific UniProt Accession ID and require a breakdown of domain boundaries, confidence metrics, or identified disordered regions for a predicted protein structure.

Look elsewhere when…

Avoid this if you lack a UniProt ID, as it cannot perform lookups for protein names, gene symbols, or raw amino acid sequences. It is also unsuitable for searching structural homologs or retrieving experimentally derived structures from the PDB archive.

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.

  • pull the AlphaFold data for UniProt P00520
  • analyze the structural domains of this protein ID
  • how confident is the AlphaFold prediction for this protein
  • check the disorder regions of protein P04637

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/alphafold_database_fetch_and_analyze ~/.claude/skills/alphafold-database-fetch-and-analyze

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/alphafold_database_fetch_and_analyze .claude/skills/alphafold-database-fetch-and-analyze

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

AlphaFold Database Fetch and Analyze changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →