Data & backend
10,137 rows, by stacks then stars
233 of these skill files have been read, by 258 distinct authors, and what they tell an agent counted. What Data & backend authors agree on, and what they forbid
Metabolomics database search and formula matching
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/metabolomics-database-search-and-formula-matching Skill
16★ repoUse when after you have detected LC-MS features, grouped them into empirical compounds via isotope and adduct clustering (using khipu), and have accurate m/z and retention time values.
Metabolomics workbench api integration
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/metabolomics-workbench-api-integration Skill
16★ repoUse when when you need to analyze a publicly archived lipidomics study (identified by study_id like ST001111) and want to bypass manual data download and format conversion.
Metacyc database query and retrieval
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/metacyc-database-query-and-retrieval Skill
16★ repoUse when you need to (1) quantify how many MetaCyc reactions can be represented by different numbers of generalized rules, (2) select a subset of rules for reaction network expansion based on coverage targets (e.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/metfrag-settings-injection Skill
16★ repoUse when when deploying the ipbhalle/metfragweb container and you need to configure MetFrag parameters such as ChemSpider tokens, proxy settings for web services (MoNA, KEGG, MetaCyc), or local database connections (PubChem via MySQL/PostgreSQL) without modifying the container image itself.
Model metadata endpoint validation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/model-metadata-endpoint-validation Skill
16★ repoUse when after starting a TensorFlow Serving instance (e.g., via docker-compose) and before attempting classification tasks, to confirm that input layers are named 'input_2048' and 'input_4096' and the output layer is named 'output'.
Molecular database loading and parsing
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/molecular-database-loading-and-parsing Skill
16★ repoUse when when setting up a ViMMS chemical sampling environment and you need to restrict the chemical search space to a specific m/z range (e.g., 100–1000) and MS level (e.g., MS1 only) before generating virtual LC-MS/MS data.
Molecular formula database filtering
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/molecular-formula-database-filtering Skill
16★ repoUse when when you need to constrain a large metabolite database to a specific instrumental range (e.g., m/z 100–1000) before generating virtual chemical mixtures for LC-MS/MS simulation, or when you need to verify that a reported filtered database count can be reproduced from raw database files.
Motif database lookup and retrieval
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/motif-database-lookup-and-retrieval Skill
16★ repoUse when after completing the MS2LDA LDA modeling step when you have a JSON-serialized inferred motifset (Mass2Motifs with fragment and neutral-loss patterns) and need to annotate those motifs by comparing them against a curated MotifDB reference database to identify known structural subpatterns.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/ms-backend-api-implementation Skill
16★ repoUse when you have MS data in a new format or storage system (e.g., a custom database, HDF5 file, or proprietary raw file) and need to make it accessible to Spectra-based analysis workflows without forking the Spectra package itself.
Msexperiment backend configuration
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/msexperiment-backend-configuration Skill
16★ repoUse when you have multiple centroided .mzML LC-MS files that need to be loaded into a unified object for targeted peak integration, and you need to distinguish QC runs from sample runs to compute per-group quality metrics (e.g., average SNR, peak correlation, area under curve per QC cohort).
Msms spectral database retrieval
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/msms-spectral-database-retrieval Skill
16★ repoUse when when you have a target compound (modified or unmodified) and need to obtain its experimental MS/MS spectrum and metadata to serve as a known reference for ModiFinder analysis, or when benchmarking evaluation methods like average_distance scoring.
Multi backend plot generation and benchmarking
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/multi-backend-plot-generation-and-benchmarking Skill
16★ repoUse when when you have a suite of Sphinx gallery example scripts targeting multiple plotting library backends and need to verify that all examples execute successfully within expected time constraints and produce output across matplotlib (static), bokeh (interactive), and plotly (interactive).
Multi backend visualization abstraction
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/multi-backend-visualization-abstraction Skill
16★ repoUse when when building a mass spectrometry visualization library that must support multiple plotting backends (matplotlib for static output, bokeh and plotly for interactive exploration) with a uniform DataFrame-based API, and where different plot kinds (spectrum, chromatogram, mobilogram, peakmap).
Multi database structure querying
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/multi-database-structure-querying Skill
16★ repoUse when after cleaning and clustering LC-MS features in MS-CleanR, when you need to assign putative compound identities to a feature set with MS/MS spectra, and when candidate compounds may exist across multiple specialized databases (e.g., natural products, pharmaceuticals, contaminants).
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/multi-format-data-ingestion Skill
16★ repoUse when you have raw metabolomics data files in one or more of the supported formats (.raw from Thermo instruments, .d directories from Agilent, or mzXML open-format exports) and need to ingest them into SMART for preprocessing, visualization, or statistical analysis.
Natural product database preparation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/natural-product-database-preparation Skill
16★ repoUse when you need to update your local LOTUS natural-product database file before running metadata enrichment or structure-query workflows, or when a pre-existing provided LOTUS file is unavailable or suspected to be stale. Trigger on project initialization or on a scheduled basis (e.
Natural product database querying norine coconut npatsas
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/natural-product-database-querying-norine-coconut-npatsas Skill
16★ repoUse when you have a chemical structure (as SMILES string or identifier) and need to discover matching records across specialized natural product databases.
Natural product database schema parsing
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/natural-product-database-schema-parsing Skill
16★ repoUse when when ingesting raw data from multiple external natural-product databases with different formats, field naming conventions, and data structures.
Natural product database validation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/natural-product-database-validation Skill
16★ repoUse when after curating and integrating structure-organism pairs from multiple source databases, and before publishing or using the dataset for computational research. Apply this skill when you have aggregated organism counts binned by structural diversity (e.
Ncbi database cross referencing
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/ncbi-database-cross-referencing Skill
16★ repoUse when you have a collection of sequence files (e.g., GenBank format files in a repository directory) and need to determine which ones lack corresponding entries in NCBI's GenBank or RefSeq databases.
Nmr peak prediction via database lookup
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/nmr-peak-prediction-via-database-lookup Skill
16★ repoUse when you have extracted peak data (chemical shift values in ppm, multiplicities, integration) from a processed NMR spectrum (JCAMP, RAW, or mzML format) and need to match these peaks against known NMR signals to propose or confirm structural assignments.
Pathway annotation database matching
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/pathway-annotation-database-matching Skill
16★ repoUse when after marker identification or metabolite annotation has produced a curated list of compound IDs (e.g., KEGG IDs or CAS numbers) and you need to determine which metabolic pathways are statistically overrepresented in your dataset.
Pathway database filtering by detection
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/pathway-database-filtering-by-detection Skill
16★ repoUse when you have run a metabolomics experiment with incomplete coverage of a reference pathway database (e.g., 10–100% of database metabolites detected), and you plan to use ORA for pathway enrichment. The skill is essential if your detection method has known sensitivity limits (e.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/pathway-database-integration Skill
16★ repoUse when you have intensity measurements (peak features, protein intensities, or gene expression values) with compound or gene annotations (KEGG IDs, ChEBI IDs, UniProt IDs, or ENSEMBL IDs), and you need to aggregate them into biologically meaningful pathway groups for differential analysis.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/pathway-database-querying Skill
16★ repoUse when when preparing to run ORA on a metabolomics study: you have a list of detected metabolites from your experiment and need to determine which metabolites from the full pathway database should serve as the statistical background, and which pathways contain how many metabolites overall.
Peak data extraction and formatting
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/peak-data-extraction-and-formatting Skill
16★ repoUse when when you have initialized an MsBackend subclass (e.
Plant species authentication via mass spectrometry
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/plant-species-authentication-via-mass-spectrometry Skill
16★ repoUse when when you have mass spectrometry raw data (DI-MS or ASAP-MS format) from plant samples that are easily confused due to morphological similarity, or when you need to verify or authenticate the species identity of a plant material against a reference database.
Polymorphic class dispatch in python
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/polymorphic-class-dispatch-in-python Skill
16★ repoUse when when you have multiple file format variants (compressed indexed gzip, standard gzip, SQLite database, uncompressed mzML) that all need to be read via a unified interface, and you want to avoid a long chain of conditional logic in client code.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/postgresql-record-insertion Skill
16★ repoUse when after successful gensim LDA inference has produced a JSON result file (e.g., myexp.ldaresult.json) and you need to make those topic assignments and model parameters queryable and accessible to a Django web application.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/pubchem-api-integration Skill
16★ repoUse when when you have raw chemical structures in diverse input formats (SMILES, SDF, or other molecular representations) from multiple sources and need to produce a uniform, canonicalized representation before molecular descriptor calculation, fingerprinting, or retention time modeling.
Pubchem compound database retrieval
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/pubchem-compound-database-retrieval Skill
16★ repoUse when you need to supply candidate metabolite structures for mass spectrometry annotation when working within an integrative metabolomics data analysis workflow (such as MAGMa).
Public database query integration
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/public-database-query-integration Skill
16★ repoUse when you have an experimental MS/MS spectrum (m/z and intensity pairs with known precursor m/z) and need to identify the compound by searching against public repositories or a local reference library.
Python class implementation with dunder methods
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/python-class-implementation-with-dunder-methods Skill
16★ repoUse when you have mzML spectral data stored in a non-standard format (SQLite database, custom binary store, or indexed archive) and need pymzML's Reader to parse and iterate over spectra as if they were in native mzML files. Specifically, when FileInterface.
Python sqlite migration and etl
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/python-sqlite-migration-and-etl Skill
16★ repoUse when you have MS/MS spectral library data currently stored in multiple file formats (JSON, CSV, or binary) and need to enable fast, filtered queries by metadata (e.g., precursor m/z, retention time, molecular class) without loading entire libraries into memory.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/qc-summary-data-extraction Skill
16★ repoUse when after applying one or more mpactr filters (filter_mispicked_ions, filter_group, filter_cv, filter_insource_ions) to a feature table, use qc_summary() to extract the pass/fail status of each ion across all applied filters.
R parallel backend configuration
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/r-parallel-backend-configuration Skill
16★ repoUse when you have multiple MSP (mass spectrum) library files to read and merge in R, and your computational task is time-consuming (e.g., structure extraction, SMILES assignment, or RI assignment) and you have a multi-core system available.
Raw file data extraction via api
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/raw-file-data-extraction-via-api Skill
16★ repoUse when you have a Thermo Fisher Scientific .raw file (e.g., Q Exactive HF, Orbitrap) and need to extract specific spectral scans, chromatographic traces, scan-level metadata, or file-level headers programmatically—e.
Raw mass spectrometry data ingestion
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/raw-mass-spectrometry-data-ingestion Skill
16★ repoUse when you have raw mass spectrometry data in mzML, abf (Reifycs), or cdf (NetCDF) format and need to load it into MS-DIAL or a similar open-source metabolomics platform.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/redis-queue-job-submission Skill
16★ repoUse when you have an OpenMS workflow ready to execute in online_deployment:true mode with Redis available, and you need to submit it as a queued job artifact rather than blocking the Streamlit thread. Trigger conditions: (1) online_deployment flag is true in settings;
Reference database maintenance
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/reference-database-maintenance Skill
16★ repoUse when when preparing to run compound metadata enrichment or structure queries, check whether your reference databases (LOTUS, DrugBank, DrugCentral) are stale or missing.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/reference-database-screening Skill
16★ repoUse when after a CNN model has generated predicted molecular embeddings from mass spectrometry data, use this skill to match those predictions against a curated reference database of known molecular embeddings.
Reference database tolerance mapping
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/reference-database-tolerance-mapping Skill
16★ repoUse when you have calculated pairwise mass differences from MS peaks (via massdiff()) and binned them into a histogram, and now need to identify which observed mass differences correspond to known molecular adducts (e.g., [M+Na]+, [M+H]+, matrix-related species) rather than random noise.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/repository-backend-dispatch Skill
16★ repoUse when when you have a USI string (e.g., 'mzspec:GNPS:TASK-abc123:scan:1943') and need to retrieve the underlying spectrum data from its native repository without knowing a priori which backend stores it.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/rest-api-client-integration Skill
16★ repoUse when you have a batch of chemical compounds (identifiers and structures in SMILES, InChI, or IUPAC format) that need to be submitted to a remote REST API for classification or analysis, and you require the server's response (query ID and status) to track or retrieve results asynchronously.
Rest api contract documentation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/rest-api-contract-documentation Skill
16★ repoUse when a webservice component (like MAGMa's joblauncher) lacks formal API documentation but the source code is accessible, and downstream consumers (web applications, external services) need to understand available HTTP endpoints, parameter schemas, and response formats without manual.
Rest api endpoint construction
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/rest-api-endpoint-construction Skill
16★ repoUse when you have pre-trained neural network models (e.g., Keras/TensorFlow) for chemical classification and need to expose them as a queryable HTTP service.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/rest-api-endpoint-querying Skill
16★ repoUse when when you need to verify that a deployed model service (such as TensorFlow Serving) is running and exposing the correct input and output layer names before sending classification requests.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/rest-api-endpoint-routing Skill
16★ repoUse when your input is a raw query string containing a chemical compound identifier and structural representation (e.g. tab-delimited compound ID + structure), and you need to submit it to the ClassyFire API for automatic structure-based classification.
Rest api query and response parsing
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/rest-api-query-and-response-parsing Skill
16★ repoUse when you have deployed a TensorFlow Serving instance (via docker-compose or equivalent) and need to verify that the model's input layer names ('input_2048' and 'input_4096') and output layer name ('output') match the expected schema before integrating the model into a classification pipeline or.
Restful api endpoint invocation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/restful-api-endpoint-invocation Skill
16★ repoUse when you have NMR peak data (1H and 13C chemical shift values) and need to obtain SMART 3 classification predictions from the DeepSAT service.
Retention index extraction from nist database
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/retention-index-extraction-from-nist-database Skill
16★ repoUse when you have a compiled EI or MS2 library object (from read_lib or c() combination of multiple sources) and a local NIST library installation with accessible ri.dat and USER.DBU files in the mssearch/nist_ri directory.
Retention time intensity data extraction
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/retention-time-intensity-data-extraction Skill
16★ repoUse when you have xcms-processed LC-MS data with detected misaligned feature groups and need to recover the underlying raw retention time–intensity profiles for each feature and sample combination prior to realignment.
Ripp peptide sequence database construction
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/ripp-peptide-sequence-database-construction Skill
16★ repoUse when when you have genomic sequences (assembled contigs or antiSMASH/BOA mining results) and want to match experimental tandem mass spectra against predicted RiPP structures.
Rippp structure database matching
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/rippp-structure-database-matching Skill
16★ repoUse when you have: (1) tandem MS/MS spectra in MGF, mzXML, mzML, or mzData format from LC-MS/MS analysis; (2) a set of predicted RiPP precursor peptides derived from genomic biosynthetic gene cluster mining (via antiSMASH, BOA, or raw FASTA);
S4 class extension for backend implementation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/s4-class-extension-for-backend-implementation Skill
16★ repoUse when you are building a new data representation or storage strategy for MS spectra (e.g., on-disk HDF5, SQL database, remote file access) and need to integrate it seamlessly into workflows that use the Spectra package.
Singularity container backend setup
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/singularity-container-backend-setup Skill
16★ repoUse when your LC-HRMS metabolomics analysis must run on a high-performance computing cluster (e.g., HiPerGator, SLURM-managed systems) that lacks Docker support or prefers Singularity for security and portability. You have .mzML or .
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/slack-api-integration Skill
16★ repoUse when rapid QC-MS detects a QC failure (e.g., internal standard retention time drift, m/z deviation, or intensity anomaly) during an active LC-MS instrument run and users have configured Slack as a notification target.
Species authentication classification evaluation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/species-authentication-classification-evaluation Skill
16★ repoUse when when you have high-throughput mass spectrometry data (DI-MS, ASAP-MS, LDI-MS, or other ambient ionization formats) from unknown biological samples and need to determine their species identity against a curated reference database.
Spectra data extraction and subsetting
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/spectra-data-extraction-and-subsetting Skill
16★ repoUse when when you need to extract m/z and intensity peak values from a Spectra object backed by MsBackendMzR or similar on-disk backends; when analyzing subsets of spectra without loading all peaks into memory;
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/spectral-database-compilation Skill
16★ repoUse when you have generated predicted fragment spectra for a set of compounds using CFM-ID or similar in-silico prediction tools and need to organize these results into a persistent, queryable database that mirrors the schema of an existing online spectral reference (such as the predicted-fragments.