Claude Skills by HolobiomicsLab

Use when when you have processed LC-MS/MS spectral data in .mgf format with precomputed ms2deepscore similarity matrices and need a 2-D overview representation that preserves local spectral relationships for interactive exploration and visualization.

Use when you have native Thermo Fisher RAW mass spectrometry files and need to extract scan-level metadata (retention time, total ion current, scan mode), MS1/MS2 peak lists with m/z and intensity arrays, or instrument/LC/MS method details for downstream computational analysis, QC, or cross-sample.

Use when you receive raw MS data files from LC-MS, LC-IMS-MS, direct infusion, or DDA/DIA experiments and need to extract ion chromatograms, mobility heatmaps, quality metrics, or perform spectral matching.

Use when you have mass spectral libraries from multiple sources (e.g., NIST EI, RIKEN MS2, MoNA GC-MS or LC-MS/MS, GNPS mgf) that need to be consolidated for use in MS-DIAL, or you have a single library with incomplete or malformed metadata (e.

Use when you have raw MRM sample files from an LC-MS/MS instrument and need to programmatically identify and tabulate all precursor m/z and product m/z pairs for each MRM transition.

Use when you have raw mass spectrometry data in one of the supported spectral formats (mzML, mzXML, msp, MGF, JSON, or metabolomics-USI) and need to load it into a Python environment for cleaning, processing, or similarity comparison.

Use when you have raw MS/MS spectra in one of the supported exchange formats (.mgf, .mzML, or .msp) and need to ingest them into an MS2LDA pipeline for unsupervised motif discovery. This skill is required before any preprocessing, filtering, or ionization-mode-specific handling can occur.

Use when use this skill at the start of any mass spectrometry analysis pipeline when you have raw spectral data in mzML, mzXML, msp, MGF, JSON, or metabolomics-USI format and need to load it into a Python environment for preprocessing, cleaning, filtering, or similarity comparison.

Use when you have a set of ions already matched to a khipu instance (i.e., ions whose isotope and adduct assignments are known and positioned on the theoretical khipu grid), and you need to estimate the neutral mass of the parent compound.

Use when you have mass spectrometry data available in multiple identifier formats (GNPS Task ID, Universal Spectrum Identifier, or Feature-Based Molecular Networking task reference) and need to route each format to its specific loader without manual preprocessing.

Use when you have raw or curated mass spectrometry data (MS1, MS2, or MSMS) in mzML, mzXML, CDF, MGF, MSP formats, or from a MassBank/MetaboLights repository, and need to convert it into an in-memory or on-disk spectral object that supports filtering, comparison, and annotation workflows.

Use when you have raw MS data files from supported instruments (Agilent, Thermo, Bruker, or mzML format) and need to ingest them into IonToolPack for visualization, quality control, targeted extraction, or spectral library matching.

Use when when raw MS/MS spectra from GNPS or similar databases contain variable-scale peak intensities, missing metadata, or inconsistent m/z calibration, and you intend to feed peak information into a transformer-based spectral embedding model that expects normalized, fixed-length tensor inputs.

Use when you have received raw or vendor-converted centroid mzML files from LC-MS, GC-MS, or DI-MS platforms and need to extract MS1 spectra before building mass tracks, performing peak detection, or constructing composite feature maps.

Use when you have raw LCMS data in mzML or mzXML format from DDA, DIA, or fullscan analyses and need to extract metabolite features with unified m/z, retention time, and intensity values across multiple samples before performing MS2 annotation or in-source fragment analysis.

Use when you have generated a complete feature table from mzML files (e.g., Asari 'full' feature table) and need to curate it for downstream analysis.

Use when you have a directory of mzML mass spectrometry files and need to systematically identify and extract scans or peaks matching specific m/z values, retention time windows, intensity thresholds, or spectral fingerprints (e.g., product ion patterns, neutral loss signatures).

Use when you need to store or retrieve mass spectrometry spectra (m/z and intensity pairs) from a novel data source or storage medium (e.

Use when you have a normalized abundance matrix from LC-MS/MS profiling with sample class assignments (e.g., phenotypic groups, disease states, treatment conditions) and need to filter metabolic features for downstream pathway analysis or biological validation.

Use when after feature extraction and peak recognition have produced detected MS/MS spectra (precursor m/z, charge, retention time, and fragment ion peaks), and you need to export these spectra for external spectral database searching, cross-platform comparison, or archival in a format compatible.

Use when when you have raw or processed TWIM-MS data (arrival time and m/z values) from a mass spectrometry instrument and need to organize it into a feature table before biomolecular class assignment or CCS calculations.

Use when when reproducing or validating a tandem mass spectrometry denoising pipeline on mzML files with known feature precursor m/z and RT coordinates, compare pre- and post-filter counts of spectra and fragments at each major step (TIC cutoff, intra-spectrum grouping, frequency-based labeling).

Use when your input is a Pandas DataFrame containing mass spectrometry measurements (m/z and intensity columns for spectra, retention time and intensity for chromatograms, or x, y, z for 2D/3D peak maps) and you need to generate static plots (matplotlib) or interactive web-based visualizations.

Use when after applying retention time, abundance correlation, or EIC similarity-based feature grouping (e.g., via SimilarRtimeParam, AbundanceSimilarityParam, or EicSimilarityParam). Use when you need to visually confirm that grouped features belong to the same compound—i.

Use when you have an unknown mass spectrum (or a representative metabolite spectrum from public data) and need to identify it by comparing it against a large reference library—particularly when the database contains billions of spectra and earlier tools like MASST are too slow or resource-intensive.

Use when you have raw or semi-processed MS/MS spectra in MSP format (e.g., from GNPS, Orbitrap instruments) and need to feed them into MSBERT or similar transformer-based embedding models for library matching, clustering, or similarity scoring.

Use when you have raw DDA, DIA (MS^E, AIF, SWATH-MS), or MS1-only mass spectrometry data in mzML, mzXML, or netCDF format and need to deconvolute fragmentation spectra by linking precursor ions to their fragment ions based on retention time and m/z relationships.

Use when you need to translate user-facing mass spectrometry query intent (e.g., 'find all MS2 spectra with a precursor ion at m/z 572.

Use when when you have preprocessed MS/MS spectral data (normalized peak intensities and m/z values) and need to convert individual spectra into fixed-dimensional vector representations for similarity-based metabolite matching or comparative analysis.

Use when when you have peak-detected LC-MS/MS data (MGF files with MS1 and MS2 spectra, plus a feature abundance table from MZmine2) and need to assign chemical structures and molecular properties to individual MS1 features rather than relying on mass-to-charge alone.

Use when after XCMS feature detection and alignment when you have a CSV-formatted feature table with m/z and retention time annotations and want to deduplicate isotopic peaks, adducts, and in-source fragments into compound-level clusters before molecular weight inference or spectral matching.

Use when you have a peak table from LC-MS peak picking software (e.

Use when immediately after MZmine feature detection when you have both MGF (MS/MS spectra) and CSV (metadata) output files for one or both ionization modes and wish to construct a deduplicated molecular network.

Use when you have a Cardinal MSImagingExperiment object (e.g., from imzML or Analyze 7.5 files) and need to retrieve the complete set of m/z values and their intensities for annotation against metabolite databases (HMDB, Lipidmaps) or for statistical analysis.

Use when when you have raw mzML files from LC-MS/MS metabolomics experiments and need to convert them into a structured feature table with accurate mass, retention time, and MS2 spectral data linked to a reference compound list.

Use when after raw data processing and feature extraction (e.g., via XCMS, OpenMS, or enviPick) when you have detected features across multiple LC-MS or GC-MS analyses and need to identify which features represent the same chemical across samples.

Use when you have (1) aligned LC-MS/MS feature quantification matrix (features × fractions with m/z and RT for each feature), (2) bioassay activity measurements across the same fractions, and (3) need to assign bioactivity values to individual molecular network nodes to identify bioactive compounds.

Use when after LC-MS feature clustering based on MS-DIAL peak character estimation, when you have grouped features that share similar chromatographic or spectral properties and need to select a single representative feature per cluster to reduce false positives and redundant annotations before.

Use when you have vendor-independent centroided mzML files from LC- or GC-HRMS data acquired in data-dependent acquisition (ddMS2) mode and need to extract detected features with m/z, retention time, and intensity attributes as input for non-target screening or PFAS prioritization workflows.

Use when after running qiime qemistree make-hierarchy and obtaining a tree artifact (qemistree.

Use when you have raw MS data files in vendor-native format (.raw, .d, .ms) from CE-MS or LC-MS instruments and need to process them through AriumMS or other open-source metabolomics pipelines that require standardized XML-based interchange formats.

Use when when you have Thermo Fisher Scientific Orbitrap .raw files (e.g., from Q Exactive HF instruments) and need to extract spectral, chromatographic, or metadata directly into R for downstream statistical analysis, benchmarking, or integration with Bioconductor workflows.

Use when you have raw MS/MS spectral data in one or more standard mass spectrometry file formats (.mgf, .msp, or .mzML) and need to convert them into a standardized bag-of-fragments representation for unsupervised topic modeling or substructure discovery workflows.

Use when you have raw or semi-processed mass-spectrometry peak data from XCMS, MSnbase, or other peak-picking tools in non-standard formats (MetaboAnalyst-like, Metabolights, vendor-specific), and you need to load them into MetaboShiny for compound identification, normalization, and statistical.

Use when after MSConvert has converted vendor-specific raw mass spectrometry data (ThermoFisher, Agilent, or equivalent formats) on a Linux system and before initiating analysis in MSThunder.

Use when you have experimental fragment m/z peaklists from Q-Exactive orbitrap, Agilent Q-TOF, Bruker Q-TOF, or SCIEX Q-TOF UHPLC-HRMS/MS instruments (in CSV or mzML-derived table formats) and need to assign lipid identities using untargeted or targeted tandem MS data.

Use when you are generating synthetic LC-MS/MS data for method validation, algorithm benchmarking, or co-fragmentation analysis, and need to model how specific biomolecules (peptides, nucleosides, or other chemical formulas) fragment under collision-induced dissociation.

Use when you have preprocessed MS/MS spectral data (in positive or negative ion mode) and seek to discover recurring fragmentation and neutral-loss patterns that characterize molecular substructures across a dataset.

Use when when building a re-usable spectral reference library for lipidomics workflows where you need to match experimental MS/MS spectra against a comprehensive theoretical fragmentation model.

Use when you have raw or preprocessed MS imaging data archived as an RDS file or from a Zenodo deposit that includes the full m/z feature set (e.g., 10,200 m/z values spanning 150–1000 m/z range) and spectrum count (e.