Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

matchms Mass Spectra Toolkit

A skill that guides loading, cleaning, comparing, and library-searching tandem mass spectra with matchms 0.33.1.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Handles MS/MS I/O across MGF, MSP, mzML, mzXML, JSON, mzSpecLib, and metabolomics-USI sources.
  • Builds preprocessing pipelines with SpectrumProcessor: metadata harmonization, adduct/precursor handling, intensity normalization, and peak filters applied identically to queries and references.
  • Helps pick the right similarity metric (CosineGreedy, ModifiedCosineGreedy/Hungarian, NeutralLossesCosine, BlinkCosine, FlashSimilarity, fingerprint similarity) for the scientific question.
  • Covers sparse score matrices, precursor-gated search, top-hit extraction, molecular similarity networks, and a bundled scripts/library_search.py CLI with CSV output.
  • Documents removed or renamed APIs (ModifiedCosine, add_losses(), spectrums) so older tutorial code stops breaking.

Who it's for

  • Metabolomics and natural-product researchers automating MS/MS library search.
  • Anyone whose matchms scripts broke after upgrading past 0.27/0.32.
  • Teams needing reproducible large-scale all-vs-all spectral comparisons or networks.

Examples

  1. "Search queries.mgf against library.msp with modified cosine and export the top 10 hits to CSV" → generates the CLI invocation or equivalent calculate_scores() code.
  2. "Build an all-vs-all similarity network from my 3,000 spectra" → script using is_symmetric=True, sparse arrays, and a pair-count estimate first.
  3. "Why does this example fail on add_losses?" → migrates the code to compute_losses() or NeutralLossesCosine.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/matchms folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/matchms/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/matchms ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Copy just this skill: cp -r scientific-agent-skills/skills/matchms ~/.claude/skills/
  4. Make sure you have Python 3.10–3.14 and uv, then install the pinned library: uv pip install "matchms==0.33.1"
  5. Verify with uv run python -c "import matchms; print(matchms.__version__)" — it should print 0.33.1.
  6. Restart Claude Code and try a prompt like "use matchms to search my MGF queries against this MSP library".
View source on GitHub ↗License: MIT