Back to resources

SKILL

matchms

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/matchms
Use with an agent

SUMMARY

What it does

This skill provides procedural guidance for using the matchms Python package (version 0.33.1) to process, clean, compare, and search tandem mass spectra. It covers file I/O for formats like MGF, MSP, mzML, mzXML, JSON, mzSpecLib, and metabolomics-USI; metadata harmonization; peak filtering; spectral similarity scoring (cosine, modified cosine, neutral loss, etc.); library matching; score matrices; and molecular-similarity networks. The skill includes code examples, API guardrails for matchms 0.33.1, and references to detailed documentation. It explicitly states that matchms is not for LC-MS feature detection or proteomics pipelines, recommending pyopenms for those tasks. The skill is part of the Scientific Agent Skills library by K-Dense and is licensed under Apache-2.0.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

data.analyzeweight 90 · confidence 90data.transformweight 80 · confidence 90data.searchweight 70 · confidence 90

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.