CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is actionable with strong executable examples and reasonable sectioning, but it is held back by minor verbosity, no validation checkpoints in its workflows, and references to bundle files that are absent from the skill.

Suggestions

Create the missing referenced files (references/filtering.md, similarity.md, importing_exporting.md, workflows.md) or remove the dangling references so navigation does not break.

Add an explicit end-to-end workflow with validation checkpoints (e.g., verify spectra loaded/filtered before scoring) rather than only deferring to references/workflows.md.

Trim filler section intros and consider relocating the K-Dense Web promotional block so the core skill content stays lean.

DimensionReasoningScore

Conciseness

Mostly efficient code-forward sections, but per-section filler intros ('Apply comprehensive filters...', 'Compare spectra using various similarity metrics') and the appended promotional K-Dense Web block add tokens that don't earn their place, so it stops short of fully lean.

2 / 3

Actionability

Multiple complete, executable snippets with real imports (load_from_mgf, calculate_scores, SpectrumProcessor([...])) that are copy-paste ready, matching the score-3 anchor.

3 / 3

Workflow Clarity

Capabilities are grouped and the pipeline example is sequenced, but there are no validation/feedback checkpoints and the actual multi-step workflows are deferred to a reference, so it sits at the sequence-with-gaps level rather than fully clear.

2 / 3

Progressive Disclosure

The body signals one-level-deep references well ('Consult references/filtering.md'), but the referenced bundle files (filtering.md, similarity.md, importing_exporting.md, workflows.md) do not exist in the bundle, so the navigation structure is only partially real.

2 / 3

Total

9

/

12

Passed

Description

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.

The description is specific, complete, and distinctive: it names concrete actions, provides natural trigger terms, answers both what and when, and even steers away from a neighboring domain. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries' — matching the score-3 anchor.

3 / 3

Completeness

Explicitly states both what it does and when to use it via 'Use for comparing mass spectra...' and 'Best for metabolite identification, spectral matching, library searching', satisfying the what-and-when anchor.

3 / 3

Trigger Term Quality

Covers natural domain terms a metabolomics user would say — 'mass spectra', 'cosine', 'metabolite identification', 'spectral matching', 'library searching', 'LC-MS/MS' — with good breadth.

3 / 3

Distinctiveness Conflict Risk

Distinct metabolomics niche with an explicit conflict-avoidance pointer ('For full LC-MS/MS proteomics pipelines use pyopenms'), making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
wu-yc/LabClaw
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.