Claude Skills by HolobiomicsLab

Use when you are designing a new tool for FT-ICR MS analysis (or similar high-resolution mass spectrometry domain) and need to understand which analytical and visualization features are already implemented in competing or complementary tools (e.

Use when when cataloging a suite of related bioinformatics tools or web applications (particularly in domains like metabolomics, microbiology, or systems biology) and you need to establish the authoritative peer-reviewed or preprint publication for each tool, verify publication URLs are live, and.

Use when when a deep learning pipeline processes mass spectrometry spectra through multiple independent scripts (e.g., train_rescore.py, run_fiddle.py, test_caffeine.py) and a specific feature must be removed or masked to prevent the model from learning directly from a protected input (e.

Use when when uploading a new mass spectrometry data file to Punc'data in CSV or delimited-text format, before attempting to map columns to their semantic roles (m/z value, intensity, formula).

Use when you have a metabolomics dataset (CSV format) containing detected peaks with m/z values and optionally retention time windows, and you need to filter a Pickaxe-generated compound expansion to keep only compounds whose masses match these observed peaks within a specified mass tolerance.

Use when when you have validated mass spectrometry transition data (precursor m/z, product m/z, intensity, retention time, and compound identifiers) formatted in one tabular format (CSV or XLSX) and need to convert it to the other format for ingestion into EISA-EXPOSOME or long-term archival.

Use when when you have mass spectrometry data stored in a database or non-mzML file format and need to integrate it into the pymzML pipeline without converting to mzML. Use this skill when FileInterface does not natively recognize your file extension and you want to avoid data conversion overhead.

Use when your mzML file contains custom or non-standard spectrum index identifiers that do not follow the default mzML indexing convention, and you need random-access retrieval of spectra by these identifiers.

Use when after computing pairwise mass-difference transformations between FT-ICR MS peaks and matching them to a reference biochemical transformation key, you have putative edge data (source peak, target peak, transformation type, mass error) and node data (peaks with m/z, molecular formula.

Use when after generating a dashboard_data.json file from the msFeaST Jupyter pipeline, use this skill to verify that the JSON file is correctly formatted and completely loaded into the interactive dashboard before conducting visual exploration or sharing the dashboard with collaborators.

Use when when uploading a delimited CSV or similar tabular file to Punc'data containing high-resolution mass spectrometry results, and the column headers are present but their semantic roles (e.

Use when mSMetaEnhancer fetches metadata from external services (CIR, CTS, PubChem, IDSM, BridgeDb) and must write enriched annotations (SMILES, InChI, CAS numbers, formulas, inchikeys, IUPAC names) into .msp files.

Use when you have m/z peak lists (positive and negative mode) and sample metadata from peak-picking software (e.g., XCMS with MetaboAnalyst export, MSnbase, or MetaboLights format) and need to load them into MetaboShiny for compound identification, statistical analysis, or machine learning.

Use when you have raw MS files (with associated metadata: filename, upload path, file format) staged in an uploader repository and need to route them to a proteomics processor for analysis while preserving audit trails and ensuring format compatibility before processing begins.

Use when when building a platform that must accept raw MS data files (e.g., .raw, .mzML, .mzXML) from instrument runs or external sources as the first stage of an automated omics workflow.

Use when after applying matchms metadata cleaning tools to normalize field values and standardize naming conventions on imported spectra (mzML, mzXML, msp, MGF, or JSON formats).

Use when you have Spectra::Spectra objects in R and need to apply Python MS algorithms from matchms or spectrum_utils (e.g., CosineGreedy similarity scoring, normalization, or filtering), or conversely need to convert Python spectral objects back to R for downstream Spectra workflows.

Use when processing spectral datasets from open mass spectra libraries (OMSLs) where structural identifiers and ionization metadata are incomplete or inconsistent.

Use when after loading and parsing raw MRM export files (TSV, CSV, or vendor-specific formats) into a pandas DataFrame and decomposing lipid nomenclature, before performing lipid matching, statistical analysis, or visualization.

Use when you have a new or draft file format specification (e.g., mzPeak) with multiple independent language implementations, and you need to verify that all readers agree on the structured data they extract before recommending the format for production use.

Use when after converting or filtering objects (e.g., transformation products to suspect lists, feature groups through componentization) and before passing them to downstream functions like screenSuspects or generateComponents.

Use when when ingesting or updating MassBank records in plain-text or structured format, and you need to verify that metadata fields (accession, name, formula, mass, spectrum peaks) comply with type definitions, presence requirements, and allowed value ranges.

Use when when processing mass spectrometry spectral records from a database where critical fields (e.g., adduct annotation) are absent or null, and you have a secondary field (e.g., ionmode: ''pos''/''neg'') that can deterministically populate the missing field.

Use when when you have an mzML file that you want to store persistently in a queryable format for repeated access, or when memory constraints prevent loading entire mzML files into memory;

Use when when implementing a new MsBackend subclass and need to return complete spectra data as a single DataFrame object that combines required core variables with backend-specific metadata columns, while avoiding cyclic function calls between spectraData() and spectraVariables().

Use when when implementing a new MsBackend subclass that stores only a subset of core spectra variables (e.

Use when when designing or optimizing an MsBackend implementation (or similar columnar data structure) you must decide whether to pre-allocate all known columns in the backing DataFrame at initialization or defer column creation until first access.

Use when when building a scientific visualization library that must support multiple plotting backends and needs to avoid backend-specific code duplication. Specifically: (1) your domain (e.

Use when when implementing a custom MsBackend subclass and need to verify that spectra variables (e.g., precursor m/z, retention time, MS level) conform to expected data types before exposing them to Spectra objects.

Use when performing large-scale untargeted metabolomics annotation where you need to estimate the false discovery rate of metabolite identifications.

Use when you have preprocessed mass spectrometry spectra (tokenized m/z and intensity pairs or feature matrices) and a trained deep learning model checkpoint, and you need to classify unknown compounds or generate prediction confidence scores for structural novelty analysis.

Use when you have paired mass-spectrometry spectral data (m/z and intensity arrays) with known molecular fingerprints or InChIKeys, and need to train a supervised deep learning model to predict fingerprints for novel spectra.

Use when when processing OMSLs (Open Mass Spectra Libraries) with heterogeneous data quality, inconsistent annotations, or mixed ionmode/chromatographic modes (LC/GC), and you need to track which spectra were discarded, why, and potentially recover or reprocess them in future iterations.

Use when a bioinformatics package claims to install a large number of tools (e.g., ~89 for untargeted metabolomics pipelines) but the article or main documentation does not enumerate them explicitly.

Use when after spectral database dereplication (using Spectra) and compound database dereplication (using SIRIUS or MetFrag) have produced candidate annotations in CSV or JSON format.

Use when after raw mass spectrometry data has been converted to a peak feature table (CSV or tabular format) containing mass-to-charge ratios, retention times, and intensity values across samples, and you need to reduce noise and identify which peaks show meaningful differential patterns between.

Use when after data preprocessing and standardization of a metabolomics feature matrix, when you need to detect and visually characterize batch effects arising from known experimental conditions, unknown latent groups, or hidden substructures before formal statistical testing.

Use when after batch effect removal and data integration, when you have a feature-by-sample matrix (finalData) and wish to separate and visualize sample groups by their metabolomic profiles using clustering methods such as hierarchical clustering analysis (HCA).

Use when you have normalized peak intensity data (or absence/presence matrices) from metabolomics experiments with multiple samples and need to quantify compositional differences between them prior to multivariate analysis. This step is essential when testing whether categorical factors (e.

Use when when preparing a software release, testing contribution workflows, or auditing package availability: verify that matchms can be installed and imported successfully from all advertised distribution channels (PyPI and Bioconda) to confirm the package metadata, dependencies, and entry points.

Use when when you have a collection of DNA adduct compound structures in SDF format that requires validation for structural integrity and completeness, and you need to generate predicted fragment spectra at defined ionization levels and mass ranges for comparison against experimental mass.

Use when your analysis requires msconvert or another ProteoWizard tool on macOS, but native installation is infeasible or licensing-restricted. You need to convert vendor raw mass spectrometry files (.raw) to the open mzML format without installing ProteoWizard directly on your system.

Use when you have a vendor mass spectrometry raw file (e.g., .raw format) that requires conversion to Aird format using AirdPro CLI, and you are running on macOS or Linux.

Use when when you have vendor raw mass spectrometry files on the host machine that need to be processed by a containerized tool (e.g., AirdPro), and the container must read input from and write output to specific host paths. Typical trigger: you have a .

Use when you have raw mass spectrometry data converted to MS1 format and need to predict peptide features (charge, isotope count, retention time) without installing complex dependencies or configuring GPU/Python environments locally.

Use when when you have a containerized scientific tool available on Docker Hub (e.

Use when you need to containerize a C#-based Windows application (like AirdPro CLI) for Linux deployment, require Wine and .NET Framework 4.

Use when deploying the ipbhalle/metfragweb container and you need to supply custom MetFrag settings (ChemSpider tokens, proxy servers, local database connections) without modifying the container image.

Use when when you need to containerize a Windows-only .NET Framework GUI application (such as AirdPro V5/V6 written in C# for .NET Framework 4.8) for execution on macOS or Linux hosts, and you want to avoid shipping compile-time tooling (SDK) in the production image.

Use when when you need to enable non-programmers or domain experts to formulate complex, unambiguous queries over specialized data (e.