Agent skill

Coot Rdkit

RDKit molecular manipulation and visualization within Coot's Python environment.

GPL-3.0Auto-check passedResearch & Science

Install Coot Rdkit

skills CLI

$ npx skills add pemsley/coot --skill coot-rdkit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install pemsley/coot coot-rdkit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/pemsley/coot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/mcp/docs/skills/rdkit .claude/skills/coot-rdkit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "coot-rdkit" agent skill from https://github.com/pemsley/coot/tree/main/mcp/docs/skills/rdkit into .claude/skills/coot-rdkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "coot-rdkit", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/pemsley/coot/tree/main/mcp/docs/skills/rdkit

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add pemsley/coot --skill coot-rdkit -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install pemsley/coot coot-rdkit --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pemsley/coot.git skills-src && mkdir -p .agents/skills && cp -r skills-src/mcp/docs/skills/rdkit .agents/skills/coot-rdkit && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "coot-rdkit" agent skill from https://github.com/pemsley/coot/tree/main/mcp/docs/skills/rdkit into .agents/skills/coot-rdkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "coot-rdkit", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add pemsley/coot --skill coot-rdkit -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install pemsley/coot coot-rdkit --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pemsley/coot.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/mcp/docs/skills/rdkit .cursor/skills/coot-rdkit && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "coot-rdkit" agent skill from https://github.com/pemsley/coot/tree/main/mcp/docs/skills/rdkit into .cursor/skills/coot-rdkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "coot-rdkit", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/pemsley/coot.git --path mcp/docs/skills/rdkit

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add pemsley/coot --skill coot-rdkit -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install pemsley/coot coot-rdkit --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pemsley/coot.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/mcp/docs/skills/rdkit .gemini/skills/coot-rdkit && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "coot-rdkit" agent skill from https://github.com/pemsley/coot/tree/main/mcp/docs/skills/rdkit into .gemini/skills/coot-rdkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "coot-rdkit", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install pemsley/coot coot-rdkit

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add pemsley/coot --skill coot-rdkit -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/pemsley/coot.git skills-src && mkdir -p .github/skills && cp -r skills-src/mcp/docs/skills/rdkit .github/skills/coot-rdkit && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "coot-rdkit" agent skill from https://github.com/pemsley/coot/tree/main/mcp/docs/skills/rdkit into .github/skills/coot-rdkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "coot-rdkit", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add pemsley/coot --skill coot-rdkit -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install pemsley/coot coot-rdkit --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/pemsley/coot.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/mcp/docs/skills/rdkit .opencode/skills/coot-rdkit && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "coot-rdkit" agent skill from https://github.com/pemsley/coot/tree/main/mcp/docs/skills/rdkit into .opencode/skills/coot-rdkit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "coot-rdkit", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: coot-rdkit
GitHub stars: 168
Token cost: ~981 tokens
SKILL.md length: 178 words
Files: 1
Skills in repo: 11
Repo updated: Oct 7, 2026
First seen: Oct 8, 2026
Licence: GPL-3.0

At a glance

RDKit molecular manipulation and visualization within Coot's Python environment.

Works in 7 steps: Load monomer from Coot library → Convert to RDKit molecule → Make modifications (atom substitution,… → …
Working with Coot and need to
SKILL.md covers Key Integration Points, Molecular Manipulation, 2D Structure Visualization and Data Handling Best Practices, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Coot Rdkit is an agent skill from pemsley/coot. RDKit molecular manipulation and visualization within Coot's Python environment. Use when working with Coot and need to (1) Create RDKit molecules from Coot monomers, (2) Modify molecular structures (e.g., atom substitution), (3) Generate 2D chemical structure diagrams, (4) Perform cheminformatics operations on ligands or small molecules loaded in Coot.

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Drug discovery and cheminformatics. It works with RDKit and Python. The repository describes itself as: Software for macromolecular model-building. The licence is GPL-3.0.

When your agent uses it

Working with Coot and need to
Create RDKit molecules from Coot monomers
Modify molecular structures (e.g.
Atom substitution)

Example prompts

“/coot-rdkit”

Requirements

Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

Load monomer from Coot library
Convert to RDKit molecule
Make modifications (atom substitution, etc.)
Remove hydrogens if desired for cleaner diagram
Regenerate 2D coordinates (critical!)
Generate SVG diagram
Save to file without displaying

What it can do on your machine

Read from SKILL.md and the folder at commit 6e3c026. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python and bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Coot Rdkit loads about 981 tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 178 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~92
When it runs · the whole SKILL.md, loaded when a task matches: ~981

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pemsley/coot at commit 6e3c026, republished under its GPL-3.0 licence (© pemsley). 178 words, ~981 tokens.

Download SKILL.mdSave it as .claude/skills/coot-rdkit/SKILL.md (or your agent's skills folder).

name: coot-rdkit
description: RDKit molecular manipulation and visualization within Coot's Python environment. Use when working with Coot and need to (1) Create RDKit molecules from Coot monomers, (2) Modify molecular structures (e.g., atom substitution), (3) Generate 2D chemical structure diagrams, (4) Perform cheminformatics operations on ligands or small molecules loaded in Coot.

Coot-RDKit Integration

This skill provides guidance for using RDKit within Coot's Python environment for molecular manipulation and visualization.

Key Integration Points

Module Import

Use coot_headless_api (NOT chapi):

python

import coot_headless_api
from rdkit import Chem
from rdkit.Chem import AllChem

Creating RDKit Molecules from Coot Monomers

python

import coot_headless_api
import base64
from rdkit import Chem

# Initialize molecules container
molecules = coot_headless_api.molecules_container_t(False)  # False = not verbose

# Get monomer from Coot's library
imol = molecules.get_monomer("AMP")  # or any other monomer code

# Get RDKit molecule as pickled base64
pickle_base64_str = molecules.get_rdkit_mol_pickle_base64("AMP", imol)

# Decode and create RDKit molecule
pickle_bytes = base64.b64decode(pickle_base64_str)
rdkit_mol = Chem.Mol(pickle_bytes)  # Use Chem.Mol(), NOT pickle.loads()

Molecular Manipulation

Atom Substitution

python

from rdkit import Chem

# Make editable copy
mol_edit = Chem.RWMol(rdkit_mol)

# Replace atom (e.g., phosphorus to sulfur)
for atom in mol_edit.GetAtoms():
    if atom.GetSymbol() == 'P':
        atom.SetAtomicNum(16)  # 16 = sulfur
        break

# Convert back to read-only molecule
modified_mol = mol_edit.GetMol()
Chem.SanitizeMol(modified_mol)

2D Structure Visualization

CRITICAL: Always Regenerate 2D Coordinates

When removing hydrogens or modifying structure, ALWAYS regenerate 2D coordinates:

python

from rdkit.Chem import AllChem

# Remove hydrogens
mol_no_h = Chem.RemoveHs(mol)

# IMPORTANT: Regenerate 2D coords AFTER removing hydrogens
AllChem.Compute2DCoords(mol_no_h)

# Now generate visualization

Generating SVG Diagrams

python

from rdkit.Chem.Draw import rdMolDraw2D

drawer = rdMolDraw2D.MolDraw2DSVG(400, 400)
drawer.DrawMolecule(mol_no_h)
drawer.FinishDrawing()
svg_string = drawer.GetDrawingText()

# Save without displaying (see Data Handling below)

Data Handling Best Practices

NEVER Display Large String Data

Do NOT return or print large strings (SVG, base64, etc.) as this causes slow response times:

BAD:

python

svg_data  # This displays all the text - SLOW!

GOOD:

python

# Just save directly without displaying
# (use len() to verify if needed, though even this may not return properly)

Efficient File Writing

Write files directly without displaying content:

From Coot Python:

python

svg_content = drawer.GetDrawingText()
# Don't display svg_content - just reference it

Then in bash or file creation:

bash

# Use the variable directly without echoing/catting the content

Coot Python Limitations

Single-Line Return Values Only

Coot's Python environment only returns values from single-line expressions:

Works:

python

Chem.MolToSmiles(mol)  # Returns SMILES string

Doesn't return properly:

python

x = 5
y = 10
x + y  # Won't return the value

Workaround - Define function in one call, execute in next:

python

# Call 1: Define
def my_function():
    x = 5
    y = 10
    return x + y

# Call 2: Execute
my_function()  # Now returns 15

Common Workflows

Modify and Visualize Ligand

Load monomer from Coot library
Convert to RDKit molecule
Make modifications (atom substitution, etc.)
Remove hydrogens if desired for cleaner diagram
Regenerate 2D coordinates (critical!)
Generate SVG diagram
Save to file without displaying

Files

Just SKILL.md in mcp/docs/skills/rdkit of pemsley/coot.

Open the folder on GitHubat commit 6e3c026

Compare with similar skills

Coot Rdkit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Coot Rdkit compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Coot Rdkit this skillpemsley/coot	168	—	~981	Automated safety check: Pass	GPL-3.0	yesterday
DiffDock Molecular DockingK-Dense-AI/scientific-agent-skills	48k	1 repos	~3k	Automated safety check: Notes	MIT	3 days ago
Edu Chem Reactionwy51ai/edulab	1.4k	—	~1.2k	Automated safety check: Pass	Apache-2.0	10 days ago
RDKit Conformer Generatorjinzhezenggroup/computational-chemistry-agent-skills	148	1 repos	~2.4k	Automated safety check: Pass	LGPL-3.0	3 days ago
RDKit Descriptors and Fingerprintsjinzhezenggroup/computational-chemistry-agent-skills	148	1 repos	~2.3k	Automated safety check: Pass	LGPL-3.0	3 days ago
Rowanlamm-mit/scienceclaw	244	4 repos	~3.1k	Automated safety check: Warn	Proprietary	1 mo ago

Similar skills

DiffDock Molecular Docking
K-Dense-AI/scientific-agent-skills
Predicts how small molecules bind to a protein with DiffDock, covering batch docking, pose ranking by confidence and checks on the results; not for binding affinity.
48k GitHub starsUsed in 1 repo~3k tokens
Research & ScienceAuto-check: notes
Edu Chem Reaction
wy51ai/edulab
把一个化学反应做成自包含的微观 3D 交互演示网页：左/上为 Three.js 可交互分子动画（拖滑块看断键·成键·原子重组，分步高亮），右为 KaTeX 反应方程 + 分步讲解 + 原子守恒计数 + 可选能量-反应进程曲线。支持三入口——给定文字反应/方程、随机出题、上传图片识别后演示。
1.4k GitHub stars~1.2k tokensUpdated 10 days ago
Research & ScienceAuto-check passed
RDKit Conformer Generator
jinzhezenggroup/computational-chemistry-agent-skills
Generates 3D molecular conformers from SMILES strings or files with RDKit, keeps the lowest-energy one per molecule, and falls back to 2D coordinates when embedding fails.
148 GitHub starsUsed in 1 repo~2.4k tokens
Research & ScienceAuto-check passed
RDKit Descriptors and Fingerprints
jinzhezenggroup/computational-chemistry-agent-skills
Computes RDKit physicochemical descriptors and molecular fingerprints from SMILES through a uv-run CLI script that skips and logs invalid molecules.
148 GitHub starsUsed in 1 repo~2.3k tokens
Research & ScienceAuto-check passed
Rowan
lamm-mit/scienceclaw
Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.
244 GitHub starsUsed in 4 repos~3.1k tokens
Research & ScienceAuto-check: warnings
RDKit Cheminformatics
davila7/claude-code-templates
Guides molecular work with RDKit in Python: reading SMILES and SDF, sanitization, descriptors, fingerprints, substructure and similarity search, reactions and coordinates.
32k GitHub starsUsed in 15 repos~5k tokens
Research & ScienceAuto-check passed

Questions about Coot Rdkit

What does Coot Rdkit do?

RDKit molecular manipulation and visualization within Coot's Python environment. Coot Rdkit is an agent skill from pemsley/coot. RDKit molecular manipulation and visualization within Coot's Python environment.

When should I use Coot Rdkit?

Coot Rdkit fits situations like: working with Coot and need to; create RDKit molecules from Coot monomers; modify molecular structures (e.g; atom substitution).

How do I install Coot Rdkit in Claude Code?

Run `npx skills add pemsley/coot --skill coot-rdkit -a claude-code`. Or copy the skill folder (mcp/docs/skills/rdkit in pemsley/coot) into .claude/skills/coot-rdkit in your project. Claude Code loads it when a task matches its description.

How do I install Coot Rdkit in Codex?

Run `npx skills add pemsley/coot --skill coot-rdkit -a codex`. Or copy the skill folder (mcp/docs/skills/rdkit in pemsley/coot) into .agents/skills/coot-rdkit in your project. Codex loads it when a task matches its description.

Can I use Coot Rdkit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add pemsley/coot --skill coot-rdkit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/coot-rdkit, .gemini/skills/coot-rdkit, .github/skills/coot-rdkit and .opencode/skills/coot-rdkit in your project.

What does Coot Rdkit need to run?

SKILL.md names no scripts, command-line tools or credentials: Coot Rdkit is instructions for the agent only. Our summary lists: Python 3.

Does Coot Rdkit access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Coot Rdkit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Coot Rdkit use?

Coot Rdkit is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Coot Rdkit use?

About 981 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Coot Rdkit?

Skills that share tags, products or a category with Coot Rdkit: DiffDock Molecular Docking (K-Dense-AI/scientific-agent-skills, 48k stars), Edu Chem Reaction (wy51ai/edulab, 1.4k stars), RDKit Conformer Generator (jinzhezenggroup/computational-chemistry-agent-skills, 148 stars) and RDKit Descriptors and Fingerprints (jinzhezenggroup/computational-chemistry-agent-skills, 148 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Coot Rdkit?

pemsley (a GitHub user) maintains it in pemsley/coot, which has 168 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.

Source: pemsley/coot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Coot Rdkit

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Coot-RDKit Integration

Key Integration Points

Module Import

Creating RDKit Molecules from Coot Monomers

Molecular Manipulation

Atom Substitution

2D Structure Visualization

CRITICAL: Always Regenerate 2D Coordinates

Generating SVG Diagrams

Data Handling Best Practices

NEVER Display Large String Data

Efficient File Writing

Coot Python Limitations

Single-Line Return Values Only

Common Workflows

Modify and Visualize Ligand

Files

Compare with similar skills

Similar skills

More from pemsley/coot

Related

Questions about Coot Rdkit