matchms

Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries. Best for metabolite identification, spectral matching, library searching. For full LC-MS/MS proteomics pipelines use pyopenms.

4.63x

Quality

86%

Does it follow best practices?

Impact

88%

4.63x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Evaluation results

94%

79%

Metabolite Identification from Unknown MS/MS Spectra

Spectral library matching workflow

Criteria

Without context

With context

ModifiedCosine for analogs

83%

PrecursorMzMatch pre-filter

16%

100%

default_filters on library

100%

default_filters on queries

100%

normalize_intensities applied

12%

100%

None check after require filters

60%

scores_by_query for retrieval

100%

calculate_scores used

100%

uv for installation

100%

Results output file

100%

92%

79%

Standardized Spectral Data Cleaning Pipeline

Reusable spectrum preprocessing pipeline

Criteria

Without context

With context

SpectrumProcessor used

100%

default_filters as first step

100%

normalize before relative intensity

100%

mz_tolerance=17 for precursor removal

100%

intensity_from=0.01 threshold

100%

None guard after require filters

30%

100%

uv installation

load_from_mgf import path

100%

Spectra list conversion

100%

Processed output saved

100%

80%

50%

Multi-Metric Compound Similarity Analysis for Drug Discovery

Chemical annotation and fingerprint-based similarity

Criteria

Without context

With context

matchms[chemistry] installed

25%

33%

derive_inchi_from_smiles used

100%

derive_inchikey_from_inchi used

100%

morgan2 fingerprint type

25%

100%

nbits=2048 for fingerprint

40%

100%

FingerprintSimilarity used

100%

add_losses before NeutralLossesCosine

NeutralLossesCosine used

100%

default_filters applied

100%

Results written to file

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: b58ad7e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Metabolite Identification from Unknown MS/MS Spectra Standardized Spectral Data Cleaning Pipeline Multi-Metric Compound Similarity Analysis for Drug Discovery

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.