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.
88
86%
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 a specific scientific niche—spectral similarity analysis for metabolomics. It lists concrete actions, includes rich domain-specific trigger terms, explicitly states when to use it, and even disambiguates from a related skill (pyopenms for proteomics). The description is concise yet comprehensive.
| 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 precise, actionable 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 disambiguation clause directing LC-MS/MS proteomics pipelines to pyopenms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user in this domain would use: 'mass spectra', 'similarity scores', 'cosine', 'modified cosine', 'spectral libraries', 'metabolite identification', 'spectral matching', 'library searching', 'metabolomics', 'LC-MS/MS'. These are the exact terms domain users would naturally employ. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in spectral similarity and metabolomics compound identification. The explicit boundary with pyopenms for proteomics pipelines further reduces conflict risk. Unlikely to be confused with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that provides actionable, executable code examples across all major matchms capabilities with good progressive disclosure to reference files. The main weaknesses are some verbosity in descriptive sections that Claude doesn't need, and the lack of validation/error-handling guidance (e.g., handling None returns from filters, checking for empty spectra lists). Overall it serves as an effective quick-start guide with clear pointers to deeper documentation.
Suggestions
Add a validation note about filters returning None (e.g., `processed = [s for s in processed_spectra if s is not None]`) since this is a common pitfall that could silently break downstream similarity calculations.
Trim descriptive text like the overview sentence and filter category descriptions—Claude already understands these concepts; focus on the code and parameter specifics that are unique to matchms.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly 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' and listing out filter categories descriptively). Some sections like Metadata Management and Spectrum Objects could be tightened. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples for all core operations: importing/exporting, filtering, similarity calculation, pipeline building, and spectrum creation. Each code block is complete with proper imports and realistic parameters. | 3 / 3 |
Workflow Clarity | The processing pipeline section shows a clear sequence, and the overall structure follows a logical progression from import to processing to similarity calculation. However, there are no explicit validation checkpoints or error recovery steps—important when processing mass spec data where spectra can be None after filtering or files can be malformed. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to filtering.md, similarity.md, importing_exporting.md, and workflows.md. The main content provides enough to get started while pointing to detailed references for deeper exploration. | 3 / 3 |
Total | 10 / 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
25e1c0f
- 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.