AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Raman Spectra Simulation

skill-internscience-chemclaw-raman-spectra-simulation · by InternScience

Compute and visualize Raman Spectra from input SMILES or XYZ file with MLatom.

No reviews yet
0 installs
35 views
0.0% view→install

Install

$ agentstack add skill-internscience-chemclaw-raman-spectra-simulation

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-internscience-chemclaw-raman-spectra-simulation)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
5mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Raman Spectra Simulation? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Raman Spectra Simulation Skill

When to use this

Use this skill when the user provides a SMILES or XYZ file (coordinates) and wants:

  • Optimized geometry
  • Theoretically calculated Raman spectrum in a summarized table
  • Quick overview of simulated Raman spectrum
  • Publication-ready image file

Inputs

  • SMILES string (e.g. CCO for ethanol) or XYZ file path (necessary)
  • A corresponding experimental Raman spectrum (optional, .txt format)

Outputs

  • /tmp/chemclaw/optimized_geometry.md
  • /tmp/chemclaw/theoretical_raman.md
  • /tmp/chemclaw/theoretical_raman.png
  • /tmp/chemclaw/exp_raman.png (optional, if experimental data provided)
  • /tmp/chemclaw/comparison_raman.png (optional, if experimental data provided)

Agent response

When returning results to the user, include the generated spectrum image(s) in the response so the user sees them directly. Use markdown image syntax with the correct path to the PNG file(s), e.g. `. Include comparison_raman.png` if experimental data was provided.

New environment (from zero)

conda create -n spec python=3.12 -y
conda activate spec
conda install -c conda-forge xtb -y   # macOS 必装(MLatom 内建 xTB 为 Linux 版)
pip install mlatom numpy matplotlib pyscf geometric rdkit

cd raman-spectra-simulation
python raman_spectra_simulation.py CCO
# optional: python raman_spectra_simulation.py /path/to/structure.xyz
# optional: python raman_spectra_simulation.py CCO experimental_raman.txt
  • 请在 skill 目录内执行脚本。
  • macOS 若仍误用 MLatom 内建 Linux 版 xTB,可 export PATH="$CONDA_PREFIX/bin:$PATH" 让系统先找到 conda 的 xtb

How to use(已装好环境时)

SMILES:

cd raman-spectra-simulation
python raman_spectra_simulation.py CCO

XYZ(用户提供坐标文件):

cd raman-spectra-simulation
python raman_spectra_simulation.py /path/to/structure.xyz

含实验谱对照:

cd raman-spectra-simulation
python raman_spectra_simulation.py CCO experimental_raman.txt

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.