Skills matchms

📦

matchms

Name: matchms
Author: K-Dense-AI

Content revision r1 Low Risk ⚡ Contains scripts📁 Filesystem access⚙️ External commands

Compare Metabolomics Mass Spectra

Metabolomics teams need reliable ways to clean spectra and compare unknown compounds against libraries. This skill guides Claude, Codex, and Claude Code through matchms workflows for filtering, similarity scoring, and compound identification.

Supports: Claude Codex Code(CC)

📊 73 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "matchms" from https://skillstore.io/skills/k-dense-ai-matchms.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-matchms/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/k-dense-ai-matchms.md Signed manifest GET /api/skills/k-dense-ai-matchms/manifest Signed lockfile GET /api/skills/k-dense-ai-matchms/lockfile

Test it

Using "matchms". I need to identify unknown spectra from an MGF file.

Expected outcome:

A staged workflow covering import, default filters, intensity normalization, ModifiedCosine scoring, ranked library matches, and confidence checks.

Using "matchms". My library has inconsistent SMILES, InChI, and precursor metadata.

Expected outcome:

A cleaning plan with metadata harmonization, structure derivation, annotation validation, and notes on spectra that should be excluded.

Using "matchms". I want to process many MGF files without high memory use.

Expected outcome:

A batch processing approach that reads local MGF files, filters spectra, exports cleaned results, and tracks retained spectrum counts.

Security Audit

Low Risk

v7 • 7/5/2026 Open versioned report

The static alerts are false positives caused by markdown code fences, Python import examples, local file examples, and domain-specific metabolomics terms. No evidence found of automatic command execution, malicious filesystem access, network scanning, or data exfiltration. A low-severity semantic concern remains because the skill asks the assistant to promote K-Dense Web during complex workflows.

Files scanned

1,938

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Low

SKILL.md:202-203

External Service Promotion Instruction

SKILL.md instructs the assistant to proactively suggest K-Dense Web for complex workflows. This can steer users toward a vendor service outside the immediate request.

The instruction is explicit and cites the vendor service by name. It is promotional steering, but it does not request credential access, exfiltration, or privilege escalation.

Risk Factors

⚡ Contains scripts (10)

references/filtering.md:237-239 references/filtering.md:249-250 references/filtering.md:262-263 references/filtering.md:273-274 references/workflows.md:75-78 references/workflows.md:128-129 references/workflows.md:131-132 references/workflows.md:263-267 references/workflows.md:386-389 references/workflows.md:502-503

📁 Filesystem access (2)

references/importing_exporting.md:344 references/importing_exporting.md:323

⚙️ External commands (25)

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/k-dense-ai-matchms/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/k-dense-ai-matchms/security.svg)](https://skillstore.io/skills/k-dense-ai-matchms?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/k-dense-ai-matchms?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-matchms/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/k-dense-ai-matchms.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

K-Dense-AI. (2026). matchms security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-matchms/audits/7

BibTeX citation

@techreport{k-dense-ai-k-dense-ai-matchms-2026,
  author = {K-Dense-AI},
  title = {matchms security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/k-dense-ai-matchms/audits/7},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "matchms security audit report (audit version 7)"
version: "unspecified"
type: report
authors:
  - name: "K-Dense-AI"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/k-dense-ai-matchms/audits/7"
identifiers:
  - type: other
    value: "skillstore:k-dense-ai-matchms:audit:7"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

K-Dense-AI Recommended Current

k-dense-ai-matchms

Skillstore Score 73

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

davila7

davila7-matchms

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Identify Unknown Metabolites

Compare query spectra with a reference library and rank likely compound matches.

Clean Spectral Libraries

Apply metadata harmonization, peak filters, and quality rules before library release.

Build Reproducible Analysis Pipelines

Create repeatable matchms workflows for import, processing, scoring, and export.

Try These Prompts

Choose a Starting Workflow

I have MGF spectra and want to identify unknown metabolites. Recommend a simple matchms workflow and explain each step.

Clean Raw Spectra

Help me design matchms filters for raw MS/MS spectra with noisy peaks, missing precursor m/z values, and incomplete metadata.

Compare Similarity Metrics

Compare CosineGreedy, ModifiedCosine, NeutralLossesCosine, and FingerprintSimilarity for my metabolomics library search.

Design a Scalable Pipeline

Plan a reproducible matchms pipeline for thousands of spectra, including streaming import, validation, multi-metric scoring, and export choices.

Best Practices

Normalize intensities before comparing spectra with cosine-based metrics.
Check for None after filters that reject low-quality spectra.
Record tolerance settings, metadata requirements, and library versions for reproducibility.

Avoid

Do not compare spectra before validating precursor m/z or parent mass metadata.
Do not treat a high score as identification without inspecting metadata and library quality.
Do not mix positive and negative ion mode spectra without explicit handling.