RepoAI
Browse MCPs

PyMOL

100TrustedInstructions only

Structural visualization and image rendering for protein molecular files.

What it does

Adding this skill allows the assistant to generate high-quality images and session files directly from protein structure data. It uses headless software rendering to create visual outputs without needing a graphical interface, making it suitable for automated documentation and scientific reporting pipelines.

The assistant handles the technical requirements of script initialization and environment configuration, saving you the effort of managing dependencies. It produces PNG images for immediate viewing and PSE files that allow you to resume your work within the full PyMOL environment on your own workstation.

When it earns its place

Reach for it when…

Apply this when you have existing PDB or CIF coordinate files and require visual aids, such as highlighting specific residues, color-coding by pLDDT confidence scores, or rendering secondary structure diagrams.

Look elsewhere when…

Do not attempt to use this for computational heavy lifting like molecular dynamics, ligand docking simulations, or predicting protein structures from raw sequence data, as this skill is strictly for processing and rendering existing structural coordinates.

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.

  • Render an image of this protein structure with helixes colored red
  • Create a session file for the ligand binding site in this PDB file
  • Show the structural difference between these two protein models
  • Color this structure based on the pLDDT confidence score

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/pymol ~/.claude/skills/pymol

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/pymol .claude/skills/pymol

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.