MS spectral matching and metabolite ID with matchms. Import spectra (mzML, MGF, MSP, JSON), filter/normalize peaks, score similarity (cosine, modified cosine, fingerprint), build reproducible pipelines, identify unknowns vs spectral libraries. Use pyopenms for full LC-MS/MS proteomics.
SkillScore95Maintained
Automatic
◆Research pack
Last verified 8/23/2026
What it changes
Passed 21 of 22 test cases with the skill, and 13 of 22 without it.
Without skill59%
With skill95%
Checks it passed that the model alone missed
The script uses reduce_to_number_of_peaks with n_max=50.
The script uses load_from_pickle to read the spectra back.
The script uses save_as_pickle to write the spectra to disk.
and 7 more in the full report
8 fixed13 passed either way1 still failing0 broke
Pass-rate lift
+36 pp
Tokens
+218%
Agent turns
0%
Response time
-31%
Model gemini-3.6-flashMeasured 8/23/2026v1 · latest is v221 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
I need to clean raw spectral peaks using matchms before library matching. Specifically, peak intensities should be scaled relative to the maximum peak (max = 1.0), and low-intensity noise peaks below 1% (0.01) of the base peak should be removed. Write the exact matchms code for these two steps.
What was checked, without and with the skill
Checked
Without skill
With skill
The code uses normalize_intensities to scale peak intensities.
Passed
Passed
The code uses select_by_relative_intensity with intensity_from=0.01.
Missed
Passed
case-14 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
Matchms is a Python library for mass spectrometry data processing focused on spectral similarity calculation and compound identification. It provides multi-format I/O, 50+ spectrum filters for metadata harmonization and peak processing, 8 similarity scoring functions, and a pipeline framework for reproducible analytical workflows.
When to Use
Identifying unknown metabolites by matching MS/MS spectra against reference libraries