# Chem Db Spectra

> Search and download experimental InfraRed (IR), Mass spectra, and UV-Vis spectra data (JCAMP-DX format) for molecules.

- **Type:** Skill
- **Install:** `agentstack add skill-learningmatter-mit-atomisticskills-chem-db-spectra`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [learningmatter-mit](https://agentstack.voostack.com/s/learningmatter-mit)
- **Installs:** 0
- **Category:** [Search](https://agentstack.voostack.com/c/search)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [learningmatter-mit](https://github.com/learningmatter-mit)
- **Source:** https://github.com/learningmatter-mit/AtomisticSkills/tree/main/.agents/skills/chem-db-spectra
- **Website:** https://arxiv.org/abs/2605.24002

## Install

```sh
agentstack add skill-learningmatter-mit-atomisticskills-chem-db-spectra
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# chem-db-spectra

## Goal
To query experimental molecular spectra—such as Infrared (IR), Mass Spectrometry, and UV-Vis—from standard experimental databases like the NIST Chemistry WebBook for baseline comparison against properties computed via MLIPs or DFT.

## Instructions

### Step 1. Query Spectra Data

Use the `query_spectra.py` script to fetch available spectrographic data for a given chemical formula. The script automatically searches the NIST Chemistry WebBook, resolves the compound, and downloads all available JCAMP-DX (`.jdx`) formatted spectra into the specified directory.

```bash
# Env: base-agent
python .agents/skills/chem-db-spectra/scripts/query_spectra.py   [--type {IR,Mass,UVVis,All}]
```

Parameters:
- `formula`: The chemical formula to query (e.g., `CH4`, `C2H6O`).
- `output_dir`: The directory path to save the downloaded JCAMP-DX (`.jdx`) spectrum files.
- `--type`: Filter the spectrum type to download (options: `IR`, `Mass`, `UVVis`, `All`). Default is `All`.

## Constraints
- **Environments**: The scripts require the `base-agent` Conda environment.
- **Spectrum Format**: Output data is universally saved in JCAMP-DX (`.jdx`) standard format. You must use appropriate spectroscopic python package (e.g., `jcamp`) if you need to parse it back into numpy arrays.
- **Scraping Dependability**: This script utilizes HTML scraping (`beautifulsoup4`). If the NIST WebBook layout changes in the future, the selectors may need to be updated.

## References
- Linstrom, P.J. and Mallard, W.G., Eds., *NIST Chemistry WebBook, NIST Standard Reference Database Number 69*, National Institute of Standards and Technology, Gaithersburg MD. [URL](https://webbook.nist.gov)
- JCAMP-DX for Infrared, Raman, and Related Data. [URL](https://jcamp-dx.org)

---

**Author:** Bowen Deng
**Contact:** [GitHub @learningmatter-mit](https://github.com/learningmatter-mit)

## Source & license

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

- **Author:** [learningmatter-mit](https://github.com/learningmatter-mit)
- **Source:** [learningmatter-mit/AtomisticSkills](https://github.com/learningmatter-mit/AtomisticSkills)
- **License:** MIT
- **Homepage:** https://arxiv.org/abs/2605.24002

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

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-learningmatter-mit-atomisticskills-chem-db-spectra
- Seller: https://agentstack.voostack.com/s/learningmatter-mit
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.