matchms

Process, clean, compare, and search tandem mass spectra with matchms. Use for MS/MS file I/O, metadata harmonization, peak filtering, spectral similarity, library matching, score matrices, and molecular-similarity networks. Use pyopenms instead for LC-MS feature detection or proteomics pipelines.

Quality

89%

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

86%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, highly actionable body with executable code throughout, real one-level-deep references, and a sequenced workflow with validation. The main slack is a small amount of inline catalog/date detail that could move to references and the absence of an explicit error-recovery loop.

Suggestions

Move the full similarity-method catalog ("Choose a Similarity Method") to references/similarity.md and keep only a 2-3 line pointer in the body to tighten conciseness.

Drop or relocate the hard release date "released 2026-06-08" — time-sensitive detail belongs in the migration/sources reference, not the overview.

Add an explicit validate-then-fix feedback loop to the Operating Workflow (e.g., 'If a require_* filter yields None, correct the offending metadata and re-run') to lift workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	Largely lean and free of basic-concept padding, but the full "Choose a Similarity Method" catalog and the dated "released 2026-06-08" detail could be trimmed or pushed to references; it is efficient with minor over-content, fitting the 4 anchor rather than the every-token-earns-its-place 5.	4 / 5
Actionability	Multiple copy-paste-ready, executable blocks (install/verify commands, the full load-and-score Quick Start, pair scoring, all-vs-all, the bundled CLI invocation) cover the common cases, matching the fully-executable 5 anchor.	5 / 5
Workflow Clarity	An 8-step Operating Workflow with explicit validation steps (drop invalid spectra, estimate pair count, validate top hits) and a Non-Negotiable Checks checklist avoids the batch-cap-at-3 rule, but lacks an explicit validate-fix-retry feedback loop, landing at the 4 anchor rather than 5.	4 / 5
Progressive Disclosure	The body is a clear overview that signals one-level-deep references (importing_exporting, filtering, similarity, workflows, migration, sources) plus scripts/library_search.py, all verified to exist, with each link annotated — matching the well-signaled-easy-navigation 5 anchor.	5 / 5
	Total	18 / 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 tight, domain-specific description that states concrete capabilities, explicit use-for triggers, and a clear hand-off boundary to pyopenms. Its only gap is omitting the file-format extensions that would round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain plus many concrete actions — "Process, clean, compare, and search tandem mass spectra" and "MS/MS file I/O, metadata harmonization, peak filtering, spectral similarity, library matching, score matrices, and molecular-similarity networks" — giving comprehensive, not just minor-gap, coverage, which fits the 5 anchor over the 4.	5 / 5
Completeness	Explicitly answers what (the concrete action list) and when ("Use for MS/MS file I/O, metadata harmonization, peak filtering...") with concrete trigger phrases, and adds a negative boundary ("Use pyopenms instead for LC-MS feature detection..."), matching the 5 anchor rather than the 4 where 'when' is only loosely specified.	5 / 5
Trigger Term Quality	Strong domain keywords users would say ("tandem mass spectra", "MS/MS", "spectral similarity", "library matching", "molecular-similarity networks") but no file extensions/formats (.mgf, .msp, .mzml), so it stops short of the comprehensive-synonyms-plus-extensions 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche (tandem mass spectrometry with matchms) with distinct triggers and an explicit don't-use-this-for pyopenms boundary, giving minimal conflict risk per the 5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/matchms/SKILL.md
Commit: 36d8f13

Reviewed: about 7 hours 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.