Skip to content
Get packs

PyOpenMS Mass Spectrometry Toolkit

Lets the agent process mass spec data: feature detection, peptide ID, quantification and adduct annotation via pyOpenMS.

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
15 files

What it does

Mass spectrometry produces large raw data files from lab instruments, and turning them into usable results takes specialized software. With this skill installed, the agent knows how to use the pyOpenMS library and a set of ready-made command-line scripts to inspect and convert these files, find and align signal peaks across samples, build quantification tables, annotate metabolites by accurate mass, and post-process peptide identifications. The skill tells the agent to prefer the bundled scripts and fall back to writing Python only when no script fits.

Great for

  • Metabolomics or proteomics researchers who want quick, repeatable LC-MS analysis pipelines
  • Data analysts turning mzML files into feature tables and quantification matrices
  • Students learning how a computational mass spectrometry workflow is structured

Skip it if

  • Simple spectral similarity or small-molecule library matching, which the skill itself says to handle with matchms instead; using it here adds needless complexity
  • Clinical or regulatory decisions based on its outputs, because the files state that instrument-specific detection and search performance is not validated and FDR figures need careful reporting
  • Users without Python 3.11+ and the ability to install pyOpenMS 3.6.0, since the scripts will not run otherwise

Try asking

  • “Detect features in sample.mzML and export a features CSV for untargeted metabolomics”
  • “Align and link these five mzML files and produce a normalized quantification matrix”
  • “Annotate my features.featureXML against HMDB by accurate mass at 5 ppm in negative mode”
  • “Digest this FASTA file with trypsin allowing 2 missed cleavages and export the peptides as CSV”
Step-by-step guide: how to use PyOpenMS Mass Spectrometry ToolkitInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    pyopenms.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip pyopenms.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip pyopenms.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run python scripts/<name>.py --help first, since input formats differ between scripts
  • Use centroided MS1 data for feature detection; the scripts reject profile data and unknown spectrum types unless you explicitly override with --assume-centroided
  • Report the exact FDR unit (PSM, peptide or protein) and decoy strategy when using the identification filter, as the skill itself warns the peptide-level filter does not establish protein-level FDR

What's inside

  • references/data_structures.md
  • references/feature_detection.md
  • references/file_io.md
  • references/identification.md
  • references/metabolomics.md
  • references/signal_processing.md
  • scripts/_common.py
  • scripts/accurate_mass_search.py
  • scripts/align_link_quantify.py
  • scripts/consensus_to_matrix.py
  • scripts/convert_format.py
  • scripts/detect_adducts.py
  • scripts/detect_features_centroided.py
  • scripts/detect_features_metabo.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.