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.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable reference that split detail into four real bundle files and gives executable code for every capability. Its main weakness is the absence of validation/verification checkpoints in the batch processing and similarity workflows.

Suggestions

Add a validation step to the pipeline and similarity workflows (e.g. assert non-empty scores, check spectra count, or sanity-check match counts before proceeding) to satisfy the batch-operation feedback-loop expectation.

Trim the 'Overview' paragraph since it overlaps the frontmatter description, letting the body start closer to the actionable capability sections.

Show a short end-to-end 'load → filter → score → inspect best matches' sequence with a checkpoint so the multi-step workflow is explicit rather than implied across sections.

Dimension	Reasoning	Score
Conciseness	Largely lean with clean code examples and brief inline comments that earn their place; the 'Overview' paragraph slightly restates the description and a few section intros could be trimmed, keeping it just short of fully efficient.	4 / 5
Actionability	Provides copy-paste-ready, executable Python across all six capability areas with full import statements and concrete arguments, covering the common cases (import/export, filtering, similarity, pipelines, Spectrum objects, metadata).	5 / 5
Workflow Clarity	Capabilities are well sequenced by section and the pipeline example shows a clear processing order, but there are no validation or verification checkpoints for batch operations like large-scale similarity comparisons, which the rubric flags as a workflow-clarity cap.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references to four real files (filtering.md, importing_exporting.md, similarity.md, workflows.md), each announced inline and summarized in a Reference Documentation section for easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states what the skill does and when to use it, with concrete actions and an explicit boundary to a sibling library. Its only gap is the absence of common file-extension triggers that metabolomics users often mention.

Suggestions

Add file-extension triggers users naturally mention, e.g. '.mgf, .mzML, .msp, .mzXML files', to raise trigger-term coverage.

Consider including 'MS/MS' or 'tandem mass spectra' as a synonym since users often phrase requests that way.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'comparing mass spectra', 'computing similarity scores (cosine, modified cosine)', 'identifying unknown compounds from spectral libraries' — giving comprehensive coverage of the library's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (spectral similarity and compound identification for metabolomics) and 'when' via a concrete 'Use for...' clause with trigger phrases, plus an explicit boundary routing to pyopenms.	5 / 5
Trigger Term Quality	Good natural-term coverage including 'spectral matching', 'library searching', 'metabolite identification', 'similarity scores', but lacks common file extensions (.mgf, .mzML, .msp) and synonyms like 'MS/MS' that users would naturally say.	4 / 5
Distinctiveness Conflict Risk	Clear metabolomics/mass-spectra niche with distinct triggers and an explicit de-scoping boundary ('For full LC-MS/MS proteomics pipelines use pyopenms'), minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/matchms/SKILL.md
Commit: d5ae560

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.