Agent skill

Molecular Descriptors Calculation

by InternScience in InternScience/scp

Calculate advanced molecular descriptors including shape indices, connectivity indices, and structural features for QSAR and drug discovery.

MITAuto-check passedResearch & Science

Install Molecular Descriptors Calculation

skills CLI
$ npx skills add InternScience/scp --skill molecular-descriptors-calculation -a claude-code

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

GitHub CLI
$ gh skill install InternScience/scp molecular-descriptors-calculation --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/InternScience/scp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/molecular-descriptors-calculation .claude/skills/molecular-descriptors-calculation && 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/

Facts

Skill name
molecular-descriptors-calculation
GitHub stars
169
Used in
1 other repo
Token cost
~1.7k tokens
SKILL.md length
374 words
Files
1
Skills in repo
73
Repo updated
First seen
Licence
MIT

At a glance

Calculate advanced molecular descriptors including shape indices, connectivity indices, and structural features for QSAR and drug discovery.

  • Works in 2 steps: MCP Server Definition → Molecular Descriptors Calculation Workflow
  • Tasks that involve Drug discovery and cheminformatics
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Molecular Descriptors Calculation is an agent skill from InternScience/scp. Calculate advanced molecular descriptors including shape indices, connectivity indices, and structural features for QSAR and drug discovery.

Its SKILL.md is about 1.7k 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. The licence is MIT.

When your agent uses it

  • Tasks that involve Drug discovery and cheminformatics

Example prompts

  • “/molecular-descriptors-calculation”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. MCP Server Definition
  2. Molecular Descriptors Calculation Workflow

What it can do on your machine

Read from SKILL.md and the folder at commit cea5398. 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).

    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

Molecular Descriptors Calculation loads about 1.7k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 374 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~44
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 InternScience/scp at commit cea5398, republished under its MIT licence (© InternScience). 374 words, ~1,665 tokens.

Download SKILL.mdSave it as .claude/skills/molecular-descriptors-calculation/SKILL.md (or your agent's skills folder).
name
molecular-descriptors-calculation
description
Calculate advanced molecular descriptors including shape indices, connectivity indices, and structural features for QSAR and drug discovery.
license
MIT license
metadata.skill-author
PJLab

Molecular Descriptors Calculation

Usage

1. MCP Server Definition

Use the same ChemicalToolsClient class as defined in the molecular-properties-calculation skill.

2. Molecular Descriptors Calculation Workflow

This workflow calculates advanced molecular descriptors used in QSAR modeling, drug discovery, and computational chemistry.

Workflow Steps:

  1. Calculate Kappa Shape Indices - Molecular shape descriptors
  2. Calculate Connectivity Indices - Topological descriptors
  3. Calculate Structural Features - Rings, bonds, and functional groups

Implementation:

python
## Initialize client
HEADERS = {"SCP-HUB-API-KEY": "<your-api-key>"}

client = ChemicalToolsClient(
    "https://scp.intern-ai.org.cn/api/v1/mcp/31/SciToolAgent-Chem",
    HEADERS
)

if not await client.connect():
    print("connection failed")
    exit()

## Input: SMILES string to analyze
smiles = "CCO"  # Ethanol
print(f"=== Molecular Descriptors for {smiles} ===\n")

## Step 1: Calculate Kappa shape indices
print("Step 1: Kappa Shape Indices")
for tool in ["GetKappa1", "GetKappa2", "GetKappa3"]:
    result = await client.client.call_tool(
        tool,
        arguments={"smiles": smiles}
    )
    result_data = client.parse_result(result)
    print(f"{tool}: {result_data}")
print()

## Step 2: Calculate Chi connectivity indices
print("Step 2: Chi Connectivity Indices")
for tool in ["GetChi0n", "GetChi0v", "GetChi1n", "GetChi1v"]:
    result = await client.client.call_tool(
        tool,
        arguments={"smiles": smiles}
    )
    result_data = client.parse_result(result)
    print(f"{tool}: {result_data}")
print()

## Step 3: Calculate structural features
print("Step 3: Structural Features")

# Rotatable bonds
result = await client.client.call_tool(
    "GetRotatableBondsNum",
    arguments={"smiles": smiles}
)
print(f"Rotatable bonds: {client.parse_result(result)}")

# Hydrogen bond donors and acceptors
result = await client.client.call_tool(
    "GetHBDNum",
    arguments={"smiles": smiles}
)
print(f"H-bond donors: {client.parse_result(result)}")

result = await client.client.call_tool(
    "GetHBANum",
    arguments={"smiles": smiles}
)
print(f"H-bond acceptors: {client.parse_result(result)}")

# Ring counts
result = await client.client.call_tool(
    "GetRingsNum",
    arguments={"smiles": smiles}
)
print(f"Number of rings: {client.parse_result(result)}")

result = await client.client.call_tool(
    "GetAromaticRingsNum",
    arguments={"smiles": smiles}
)
print(f"Aromatic rings: {client.parse_result(result)}")
print()

## Step 4: Calculate physicochemical descriptors
print("Step 4: Physicochemical Descriptors")

# LogP and molar refractivity (Crippen descriptors)
result = await client.client.call_tool(
    "GetCrippenDescriptors",
    arguments={"smiles": smiles}
)
print(f"Crippen descriptors (LogP, MR): {client.parse_result(result)}")

# Topological polar surface area
result = await client.client.call_tool(
    "CalculateTPSA",
    arguments={"smiles": smiles}
)
print(f"TPSA: {client.parse_result(result)}")

# Fraction of sp3 carbons
result = await client.client.call_tool(
    "GetFractionCSP3",
    arguments={"smiles": smiles}
)
print(f"Fraction sp3 carbons: {client.parse_result(result)}")
print()

await client.disconnect()
Tool Descriptions

SciToolAgent-Chem Server:

Shape Descriptors:

  • GetKappa1, GetKappa2, GetKappa3: Kappa shape indices (molecular shape)

Connectivity Indices:

  • GetChi0n, GetChi0v: Zero-order chi indices
  • GetChi1n, GetChi1v: First-order chi indices
  • GetChi2n, GetChi2v: Second-order chi indices
  • GetChi3n, GetChi3v, GetChi4n, GetChi4v: Higher-order chi indices

Structural Features:

  • GetRotatableBondsNum: Count rotatable bonds (flexibility)
  • GetHBDNum/GetHBANum: Hydrogen bond donors/acceptors
  • GetRingsNum: Total ring count
  • GetAromaticRingsNum: Aromatic ring count
  • GetAliphaticRingsNum: Aliphatic ring count

Physicochemical Descriptors:

  • GetCrippenDescriptors: LogP (lipophilicity) and molar refractivity
  • CalculateTPSA: Topological polar surface area
  • GetFractionCSP3: Fraction of sp³ hybridized carbons
  • GetLabuteASA: Labute accessible surface area
Input/Output

Input:

  • smiles: Molecule in SMILES format

Output:

  • Kappa Indices: Molecular shape descriptors (1, 2, 3)
  • Chi Indices: Topological connectivity indices
  • Structural Counts: Rings, bonds, functional groups
  • LogP: Lipophilicity (partition coefficient)
  • TPSA: Topological polar surface area (Ų)
  • Fraction sp³: Proportion of sp³ carbons (0-1)
Show full SKILL.md (180 more words)Show less
Descriptor Applications

Kappa Shape Indices

  • κ₁, κ₂, κ₃: Describe molecular shape from linear to spherical
  • Used in: QSAR models, molecular shape comparison

Chi Connectivity Indices

  • Encode information about branching and cyclicity
  • Used in: Property prediction, similarity searching

Structural Features

  • Rotatable bonds: Molecular flexibility, bioavailability
  • H-bond donors/acceptors: Solubility, permeability
  • Rings: Rigidity, drug-likeness

Physicochemical Descriptors

  • LogP: Lipophilicity, membrane permeability
  • TPSA: Oral bioavailability, BBB penetration
  • Fraction sp³: Molecular complexity, drug-likeness
Drug-Likeness Rules

Lipinski's Rule of Five:

  • MW ≤ 500 Da
  • LogP ≤ 5
  • HBD ≤ 5
  • HBA ≤ 10

Veber's Rules (Oral Bioavailability):

  • Rotatable bonds ≤ 10
  • TPSA ≤ 140 Ų

CNS Drug-Likeness:

  • TPSA < 90 Ų (for blood-brain barrier penetration)
Use Cases
  • QSAR model development
  • Virtual screening and compound prioritization
  • Drug-likeness assessment
  • Molecular similarity calculations
  • Pharmacokinetic property prediction
  • Lead optimization
  • Chemical space exploration
Additional Descriptor Tools

The SciToolAgent-Chem server provides 160+ tools including:

  • GetBCUT: BCUT descriptors
  • GetAutocorrelation2D/GetAutocorrelation3D: Autocorrelation descriptors
  • GetWHIM: WHIM descriptors
  • GetGETAWAY: GETAWAY descriptors
  • GetMORSE: MORSE descriptors
  • GetRDF: Radial distribution function
  • GetUSR/GetUSRCAT: Ultrafast shape recognition descriptors
Performance Notes
  • Most descriptor calculations are very fast (<1 second)
  • Can batch process multiple molecules
  • Descriptors are deterministic (same molecule → same descriptors)

© InternScience, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/molecular-descriptors-calculation of InternScience/scp.

Open the folder on GitHubat commit cea5398

Used in 2 other repositories

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in InternScience/scp, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Molecular Descriptors Calculation 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.

Molecular Descriptors Calculation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Molecular Descriptors Calculation this skillInternScience/scp1691 repos~1.7kAutomated safety check: PassMIT
MolecodeAtomFlow-AI/MoleCode306—~1.9kAutomated safety check: PassMIT
Drug DiscoveryTommy-yw/RunbookHermes5461 repos~2.3kAutomated safety check: PassMIT
DiffDock Molecular DockingK-Dense-AI/scientific-agent-skills48k1 repos~3kAutomated safety check: NotesMIT
Biomedical Analysis Dispatchxjtulyc/MedgeClaw6171 repos~2kAutomated safety check: PassNone
Edu Chem Reactionwy51ai/edulab1.4k—~1.2kAutomated safety check: PassApache-2.0

Similar skills

  • Molecode

    AtomFlow-AI/MoleCode

    A skill your agent uses for deterministic molecule understanding, graph-level editing, generation, and validation with MoleCode — an explicit Mermaid graph in which every atom and bond is a typed…

    306 GitHub stars~1.9k tokensUpdated 4 mo ago
    Research & ScienceAuto-check passed
  • Drug Discovery

    Tommy-yw/RunbookHermes

    Pharmaceutical research assistant for drug discovery workflows.

    546 GitHub starsUsed in 1 repo~2.3k tokens
    Research & ScienceAuto-check passed
  • 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
  • Routes bioinformatics, drug discovery, clinical and multi-omics tasks from a chat interface to Claude Code sessions running K-Dense scientific skills, with a live dashboard per task.

    617 GitHub starsUsed in 1 repo~2k tokens
    Research & ScienceAuto-check passed
  • 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
  • Biopipelines

    locbp-uzh/biopipelines

    Design and run computational protein and ligand workflows on a GPU: binder and enzyme design, de novo backbone generation, inverse folding and sequence redesign, structure prediction, protein-ligand…

    109 GitHub stars~2.4k tokensUpdated 8 days ago
    Research & ScienceAuto-check passed

More from InternScience/scp

All 73 skills in this repo
  • Given an rsID, query multiple databases (dbSNP, FAVOR, GWAS Catalog, ClinVar, gnomAD, PharmGKB, ClinGen) for comprehensive annotation.

    169 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed
  • Calculate atmospheric parameters including Coriolis parameter, geostrophic wind, heat index, potential temperature, and dewpoint for meteorology and climate science.

    169 GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed
  • Biomedical Web Search

    InternScience/scp

    Search biomedical literature and web content using Tavily search engine for research and clinical information.

    169 GitHub starsUsed in 1 repo~598 tokens
    Auto-check passed
  • Calculate buoyancy forces and acceleration for fluid mechanics and hydrodynamics analysis.

    169 GitHub starsUsed in 1 repo~540 tokens
    Auto-check passed
  • Capacitance Calculation

    InternScience/scp

    Calculate electrical capacitance from geometric parameters and dielectric properties for circuit design.

    169 GitHub starsUsed in 1 repo~537 tokens
    Auto-check passed
  • Chembl Molecule Search

    InternScience/scp

    Search ChEMBL database for molecule information by name to retrieve bioactivity data and chemical structures.

    169 GitHub starsUsed in 1 repo~757 tokens
    Auto-check passed

Questions about Molecular Descriptors Calculation

What does Molecular Descriptors Calculation do?

Calculate advanced molecular descriptors including shape indices, connectivity indices, and structural features for QSAR and drug discovery. Molecular Descriptors Calculation is an agent skill from InternScience/scp. Calculate advanced molecular descriptors including shape indices, connectivity indices, and structural features for QSAR and drug discovery.

When should I use Molecular Descriptors Calculation?

Molecular Descriptors Calculation fits situations like: tasks that involve Drug discovery and cheminformatics.

How do I install Molecular Descriptors Calculation in Claude Code?

Run `npx skills add InternScience/scp --skill molecular-descriptors-calculation -a claude-code`. Or copy the skill folder (skills/molecular-descriptors-calculation in InternScience/scp) into .claude/skills/molecular-descriptors-calculation in your project. Claude Code loads it when a task matches its description.

How do I install Molecular Descriptors Calculation in Codex?

Run `npx skills add InternScience/scp --skill molecular-descriptors-calculation -a codex`. Or copy the skill folder (skills/molecular-descriptors-calculation in InternScience/scp) into .agents/skills/molecular-descriptors-calculation in your project. Codex loads it when a task matches its description.

Can I use Molecular Descriptors Calculation 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 InternScience/scp --skill molecular-descriptors-calculation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/molecular-descriptors-calculation, .gemini/skills/molecular-descriptors-calculation, .github/skills/molecular-descriptors-calculation and .opencode/skills/molecular-descriptors-calculation in your project.

What does Molecular Descriptors Calculation need to run?

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

Does Molecular Descriptors Calculation 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 Molecular Descriptors Calculation 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 Molecular Descriptors Calculation use?

Molecular Descriptors Calculation is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Molecular Descriptors Calculation use?

About 1.7k tokens (SKILL.md is roughly 6.7k 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 Molecular Descriptors Calculation?

Skills that share tags, products or a category with Molecular Descriptors Calculation: Molecode (AtomFlow-AI/MoleCode, 306 stars), Drug Discovery (Tommy-yw/RunbookHermes, 546 stars), DiffDock Molecular Docking (K-Dense-AI/scientific-agent-skills, 48k stars) and Biomedical Analysis Dispatch (xjtulyc/MedgeClaw, 617 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Molecular Descriptors Calculation?

InternScience (a GitHub organization) maintains it in InternScience/scp, which has 169 GitHub stars. The repository holds 73 skills in this directory. The repository was last updated on June 3, 2026.

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