Pymol logo

Pymol

OrganizationPopular
google-deepmind
pymol

Visualize, analyze, and render protein and molecular structures using PyMOL. Use when the user wants to create images of protein structures, perform structural alignments or superposition, measure distances or contacts, highlight binding sites or active site residues, color by B-factor/pLDDT, or analyze protein-ligand interactions. Do not use for docking, molecular dynamics, or sequence-only analysis.

Overview

Publishergoogle-deepmind
Repositoryscience-skills
Skill namepymol
Stars
3.1K
Forks
349
Bundled files
3
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by google-deepmind on GitHub. Read the source before you install it.

Installation

Install the Pymol AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 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
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pymol in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pymol on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pymol is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PyMOL

Prerequisites

  1. uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
  2. User Notification: If .licenses/pymol_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the license at https://www.pymol.org/, then (2) create the file recording the notification text and timestamp.

Overview

All PyMOL commands run on the host via uv with OSMesa software rendering — no GPU, display, or X server is needed. Structure files must be downloaded to the host before running PyMOL.

Do NOT use when:

  • The user wants to run AlphaFold predictions.
  • The user wants docking or molecular dynamics simulations.
  • The user only has a sequence and no structure file — fetch the structure first. Check if any other installed skills can retrieve structures from the PDB or AlphaFold Database before proceeding.

Setup (Agent Instructions)

Ensure that uv is installed on the host system. The PyMOL scripts use PEP 0723 headers to declare their dependencies, and uv run will automatically handle installing them (including pymol-open-source-whl) when the script is executed.

Core Rules

  • Output paths must be absolute or relative to the user's project root. Always run PyMOL scripts from the user's project directory.
  • Software rendering only. Use cmd.png() for output. Never use cmd.draw() or cmd.ray() with hardware acceleration — OSMesa does not support it. Set environment variable PYOPENGL_PLATFORM=osmesa for headless rendering.
  • Always save a .pse session file alongside any PNG output. This lets the user open the session in their local PyMOL for further inspection.
  • Always call cmd.quit() at the end of every PyMOL script. Omitting it causes the process to stop responding.
  • Init boilerplate is mandatory. Every PyMOL script must begin with the initialization sequence. from pymol import cmd must come after finish_launching(), not before.
  • See references/PYMOL_REFERENCE.md for selection syntax, common commands, and gotchas.
  • Pre-Flight File Check: Before writing the PyMOL script or running it, you MUST verify that the requested structure file actually exists on the host machine.
  • Verify Structure Load: After loading a structure with cmd.load(), always verify it succeeded by checking cmd.count_atoms("all"). If the result is 0, print an error to stdout and call cmd.quit() immediately.
  • Auto-detect Alpha-Carbon Trace: For a cartoon representation your PyMOL scripts should automatically detect if the structure is an alpha-carbon trace (cmd.count_atoms("name CA") == cmd.count_atoms("all")), then you MUST follow the Alpha carbon trace cartoon recipe.
  • Notification: If this skill is used, ensure this is mentioned in the output.

Quick Start

  • Ensure structure files are downloaded to a directory in the user's project.
  • Write a PyMOL Python script (e.g., render.py) with the required init boilerplate and PEP 0723 header.
  • Run it via uv run: bash uv run render.py

Minimal example script (render.py)

python
# /// script
# requires-python = ">=3.10, <3.13"
# dependencies = [
#     "pymol-open-source-whl",
# ]
# ///

import os
import sys

# Set environment variable for headless rendering
os.environ["PYOPENGL_PLATFORM"] = "osmesa"

import pymol # pytype: disable=import-error
pymol.pymol_argv = ["pymol", "-cq"]
pymol.finish_launching()

from pymol import cmd # pytype: disable=import-error

cmd.load("AF-P00520-F1-model_v4.cif", "structure")
cmd.show("cartoon")
cmd.color("green", "ss h")
cmd.color("yellow", "ss s")
cmd.color("gray", "ss l+''")
cmd.orient()
cmd.set("ray_opaque_background", 1)
cmd.png("output/render.png", width=1200, height=900, dpi=150)
cmd.save("output/session.pse")
cmd.quit()

Common Recipes

See references/RECIPES.md for complete, copy-paste ready recipes. Available recipes:

  • Cartoon with secondary structure coloring — basic helix/sheet/loop coloring
  • Alpha carbon trace cartoon — force cartoon representation for CA-only structures
  • B-factor (pLDDT) coloring — continuous spectrum coloring by B-factor
  • AlphaFold pLDDT coloring — canonical threshold-based confidence colors
  • Highlight specific residues — show active site or key residues as sticks
  • Surface rendering — transparent surface over cartoon
  • Electrostatic surface rendering — vacuum electrostatics (qualitative)
  • Multi-chain complex colors — automatic per-chain coloring
  • B-factor putty analysis — tube width proportional to flexibility
  • Cavity and pocket visualization — surface cavity detection with ligand focus
  • Multi-structure batch rendering — render a directory of structures
  • Measure distance between residues — CA–CA distance with labels
  • Zoom into binding pocket — simple pocket focus
  • Protein-ligand interaction — ligand isolation, styled rendering, polar contacts
  • Two-structure superposition with RMSD — align/cealign with auto-fallback
  • In silico mutagenesis — mutate residues with the mutagenesis wizard
  • Load and modify an existing session — re-open a .pse file

Interpreting Output

  • The output/ directory contains PNG images and a .pse session file.
  • Any measurements or metrics (distances, RMSD, atom counts) are printed to stdout by the PyMOL script. Report these values to the user.
  • Present PNG images to the user and describe the visualization.
  • Tell the user they can open the .pse file in their local PyMOL to further explore, rotate, or modify the visualization.
  • If the user wants modifications, load the saved .pse in a new script and re-run.
  • Large sessions with surfaces can exceed the --max_output_mb limit (default 500 MB). Increase it with --max_output_mb=1000 if needed.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Pymol AI skill do?

Visualize, analyze, and render protein and molecular structures using PyMOL. Use when the user wants to create images of protein structures, perform structural alignments or superposition, measure distances or contacts, highlight binding sites or active site residues, color by B-factor/pLDDT, or analyze protein-ligand interactions. Do not use for docking, molecular dynamics, or sequence-only analysis.

Why use Pymol on TypingMind?

Because you install it once and use it with any model. Pymol is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pymol in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/google-deepmind/science-skills/tree/main/skills/pymol. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Pymol?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pymol?

As many as you like. As long as a model supports skills, you can use Pymol with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pymol AI skill free?

Yes. It is published on GitHub by google-deepmind under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇