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.
85
82%
Does it follow best practices?
Impact
88%
4.63xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines its domain (spectral similarity in metabolomics), lists specific concrete actions (comparing spectra, computing cosine/modified cosine scores, compound identification), and provides explicit trigger guidance. The inclusion of a boundary condition distinguishing it from pyopenms for proteomics pipelines is a strong differentiator that reduces conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: comparing mass spectra, computing similarity scores (cosine, modified cosine), identifying unknown compounds from spectral libraries. These are well-defined, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both what (comparing mass spectra, computing similarity scores, identifying compounds) and when ('Use for comparing mass spectra...', 'Best for metabolite identification, spectral matching, library searching'). Also includes a helpful negative boundary ('For full LC-MS/MS proteomics pipelines use pyopenms'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'mass spectra', 'similarity scores', 'cosine', 'modified cosine', 'spectral libraries', 'metabolite identification', 'spectral matching', 'library searching', 'metabolomics'. Good coverage of domain-specific terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in spectral similarity for metabolomics. The explicit boundary distinguishing it from pyopenms (proteomics pipelines) further reduces conflict risk. The domain-specific terminology makes accidental triggering very unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent executable code examples covering the core matchms API surface. Its main weaknesses are moderate verbosity (some explanatory text and exhaustive lists that could be trimmed or moved to references) and the lack of validation/error-handling guidance in workflows. The progressive disclosure structure is well-designed in principle but cannot be verified without bundle files.
Suggestions
Add validation checkpoints to workflows — e.g., check that spectra loaded successfully (non-empty list), verify score results are non-empty before accessing best matches, and handle None returns from filters.
Trim the overview sentence and reduce inline lists (supported formats, filter categories, similarity functions) by moving exhaustive details to the referenced files, keeping only the 2-3 most common items inline.
Add a brief error-handling note for common failure modes (e.g., empty spectra list from loading, missing precursor_mz for ModifiedCosine).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good code examples, but includes some unnecessary explanations (e.g., 'Matchms is an open-source Python library for mass spectrometry data processing and analysis' is redundant given the skill description). The supported formats list and filter categories are somewhat verbose but provide useful reference value. Some sections like Metadata Management explain things Claude could infer. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples throughout — importing/exporting, filtering, similarity calculation, pipeline building, and spectrum creation. Each section includes concrete function calls with realistic parameters and clear usage patterns. | 3 / 3 |
Workflow Clarity | The processing pipeline section shows a clear sequence, and the individual sections demonstrate step-by-step usage. However, there are no validation checkpoints or error handling guidance — e.g., no mention of checking if spectra loaded correctly, handling empty results from similarity searches, or verifying filter outputs. The common workflows section just defers to a reference file. | 2 / 3 |
Progressive Disclosure | References to `references/filtering.md`, `references/similarity.md`, `references/workflows.md`, and `references/importing_exporting.md` are well-signaled and one level deep. However, no bundle files were provided, so these references cannot be verified. The main file itself is fairly long (~150 lines of content) and some sections (like the full supported formats list and filter categories) could be moved to reference files to keep the overview leaner. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
cbcae7b
- Reviewed
Table of Contents
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.