Design & frontend
15,938 rows, by stacks then stars
1,697 of these skill files have been read, by 1,179 distinct authors, and what they tell an agent counted. What Design & frontend authors agree on, and what they forbid
Gnn architecture design for molecular graphs
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/gnn-architecture-design-for-molecular-graphs Skill
16★ repoUse when when you have preprocessed molecular graph data (node and edge tensors representing atoms and bonds) and need to train a regression model to predict a continuous molecular property (e.g., LC retention time).
Graph neural network architecture design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/graph-neural-network-architecture-design Skill
16★ repoUse when you have molecular structures that need to be represented as both fingerprint vectors (fixed-length chemical descriptors) and graph-structured data, and you need a model that can learn from both representations simultaneously to predict a continuous molecular property (e.
Graph neural network design for chemistry
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/graph-neural-network-design-for-chemistry Skill
16★ repoUse when you have 1D or 2D NMR spectra (1H and/or 13C) and need to predict unknown molecular structure (formula and connectivity) up to ~19 heavy atoms; or you have a set of molecular fragment-structure pairs and need to model how fragments assemble into complete structures.
Graph neural network encoder design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/graph-neural-network-encoder-design Skill
16★ repoUse when when you need to compare spectrum prediction models fairly across different encoder architectures (GNN vs. FFN vs. Transformer), and you require equivalent settings (same covariates, identical hyperparameter sweeps) to isolate the effect of the encoder design.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/heatmap-visualization-design Skill
16★ repoUse when after training a DeepMSProfiler model and generating per-sample predictions: when you need to display Pearson or Spearman correlation coefficients between individual metabolite signals and disease class labels in a matrix form suitable for publication or exploratory review of.
Heterogeneous graph embedding design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/heterogeneous-graph-embedding-design Skill
16★ repoUse when when building a Graph Transformer model for continuous property prediction on molecules with associated experimental or instrumental metadata (e.g., retention time prediction across different chromatographic columns, methods, or conditions).
Hierarchical library data structure design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/hierarchical-library-data-structure-design Skill
16★ repoUse when when building a reference library for high-throughput spectral matching against experimental MS/MS data, and you need to support millions to billions of queries per second on a standardized dataset.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/http-api-endpoint-design Skill
16★ repoUse when when you need to expose a multi-step spectral processing workflow (parse → extract → render → annotate → compress) as a web service endpoint that accepts jcamp/RAW/mzML spectral files and must return coordinated output artifacts (modified JCAMP files, peak tables, and PNG images) in a.
Infrared spectral prediction task design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/infrared-spectral-prediction-task-design Skill
16★ repoUse when when you have a dataset of molecules with experimentally measured or simulated infrared spectra and want to train a graph neural network to predict spectral features (e.g., absorption peaks, intensities) from molecular structure.
Interactive application accessibility testing
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/interactive-application-accessibility-testing Skill
16★ repoUse when after instantiating a specXplore dashboard session layer with a loaded session data object from disk, before conducting visual exploration of LC-MS/MS spectral data.
Interactive data exploration design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/interactive-data-exploration-design Skill
16★ repoUse when you have NMR metabolomics measurements paired with pre-analytical metadata (processing delay times, centrifugation timing, sample type such as plasma vs. serum, cohort identifiers) and need to interactively explore how variation in processing conditions drives changes in metabolic.
Interactive filter control design web
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/interactive-filter-control-design-web Skill
16★ repoUse when when you have a web-based visualization of aligned mass spectrometry peaks (m/z, intensity, retention time, alignment quality metrics) and need users to interactively explore subsets of those peaks by applying constraints on intensity thresholds, alignment score cutoffs, or peak.
Interactive plot axis selection ui
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/interactive-plot-axis-selection-ui Skill
16★ repoUse when when you have a high-resolution mass spectrometry dataset with m/z values and need to generate Kendrick mass plots where users should choose between plotting raw m/z or computed Normalized Kendrick Mass (NKM) on the x-axis.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/ion-image-augmentation-design Skill
16★ repoUse when when preparing ion image data from mass spectrometry imaging for contrastive self-supervised representation learning, and you need to generate augmented image pairs that reflect either co-localization relationships between different molecular ions (COL mode) or isotopic relationships.
Json serialization and data structure design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/json-serialization-and-data-structure-design Skill
16★ repoUse when you have inferred or discovered structured results (e.g., LDA-derived motif sets with mass compositions, neutral-loss patterns, and ranked database matches) that must be shared between tools, stored durably, or consumed by visualization or annotation pipelines.
Knowledge graph integration design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/knowledge-graph-integration-design Skill
16★ repoUse when designing a metabolite annotation workflow that must simultaneously leverage established biochemical knowledge (pathway databases, reaction networks) and experimental evidence (mass spectrometry feature similarity, co-occurrence patterns).
Lexical tokenization and grammar design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/lexical-tokenization-and-grammar-design Skill
16★ repoUse when you need to enable users to express complex domain-specific queries in a natural, succinct syntax—particularly when SQL patterns are familiar but must be augmented with domain assumptions (e.
Linear model design matrix specification
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/linear-model-design-matrix-specification Skill
16★ repoUse when when preparing to perform differential abundance analysis on batch-corrected lipid abundance matrices in designs with multiple factors (e.g., treatment × time, multi-group comparisons), repeated measures, or blocking structures.
Linear regression design matrix construction
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/linear-regression-design-matrix-construction Skill
16★ repoUse when after log-transformation and missing-value imputation of featuredata (via LogTransform and MissingValues functions), when you have normalized metabolomics intensity data and need to identify metabolites associated with specific biological or experimental factors encoded as covariates in a.
Mass spectrometry benchmark design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/mass-spectrometry-benchmark-design Skill
16★ repoUse when when claiming that one mass spectrometry processing library achieves higher throughput than competitors, or when evaluating whether a new or optimized implementation delivers the expected computational efficiency gains.
Mass spectrometry transition data formatting
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/mass-spectrometry-transition-data-formatting Skill
16★ repoUse when when you have raw mass spectrometry transition data from a triple-quadrupole or other tandem MS instrument and need to prepare it for suspect chemical screening using EISA-EXPOSOME, or when merging custom compound libraries into the T3DB format.
Mass spectrometry wrapper function design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/mass-spectrometry-wrapper-function-design Skill
16★ repoUse when when you have a Spectra-based MS analysis workflow in R but need access to specialized spectral similarity, filtering, or normalization algorithms available only in Python libraries.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/matlab-data-structure-design Skill
16★ repoUse when you have multiple CDF files containing mass spectrometry imaging data (spectra, m/z arrays, and spatial coordinates) that need to be ingested into MATLAB for the DIMPLE pipeline or similar linear-axis mass spectrometry imaging analysis.
Message passing neural network architecture design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/message-passing-neural-network-architecture-design Skill
16★ repoUse when when you have a working base MPNN implementation (e.g., chemprop) and need to adapt it for a new molecular property target (e.g., spectral data) that requires custom input processing, intermediate feature representations, or output layer modifications beyond the original model's scope.
Metabolomic meta analysis workflow design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/metabolomic-meta-analysis-workflow-design Skill
16★ repoUse when you have multiple metabolomic studies with aggregate summary statistics (p-values, fold-change estimates) and need to perform meta-analysis while harmonizing compound nomenclature across datasets. Use this skill when the underlying R package (e.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/mrm-transition-extraction Skill
16★ repoUse when you have raw LC-MS/MS data in MRM acquisition mode and need to systematically identify and catalog all precursor m/z and corresponding product m/z values for each transition monitored during data collection.
Mrm transition lipid identity mapping
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/mrm-transition-lipid-identity-mapping Skill
16★ repoUse when after parsing raw MRM data into a transition table containing m/z values, retention times, and transition parameters.
Multi head attention mechanism design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/multi-head-attention-mechanism-design Skill
16★ repoUse when when building a transformer-based model to process mass spectrometry data (MS/MS spectra or fingerprints) where you need the model to learn multiple independent attention patterns across spectrum features simultaneously.
Network layout algorithm selection
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/network-layout-algorithm-selection Skill
16★ repoUse when you have a network object (nodes and edges) loaded in MetaNet and need to compute 2D or 3D spatial coordinates for visualization. This skill is necessary before any network plotting step. Choose this when your network structure (e.
Neural network architecture design spectra
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/neural-network-architecture-design-spectra Skill
16★ repoUse when you have preprocessed MS/MS spectra pairs (unknown and known metabolites) with annotated structural similarity labels, and you need to learn a generalizable model that can rank candidate structures for novel unknowns by predicting their similarity to reference compounds in a database.
Neural network architecture design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/neural-network-architecture-design Skill
16★ repoUse when you have raw mzML files and feature tables (CSV from mzMine or XCMS) for LCMS data, have generated training/validation/test batches with known class imbalance, and need to train a CNN model from scratch to achieve AUC ROC > 0.9 for distinguishing true from false positive MS1 peaks.
Neural network layer design and implementation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/neural-network-layer-design-and-implementation Skill
16★ repoUse when when replacing deprecated model components (e.
Neural network module architecture design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/neural-network-module-architecture-design Skill
16★ repoUse when when building an end-to-end deep learning model that must predict multiple correlated peptide properties (charge, isotope count, retention time) simultaneously from mass spectrometry data, and you need a principled way to merge learned representations from separate task-specific branches.
Neural network projection module design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/neural-network-projection-module-design Skill
16★ repoUse when when you have 512-dimensional (or other fixed-size) representation vectors output from paired encoders processing augmented versions of the same input (e.
Object oriented class hierarchy design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/object-oriented-class-hierarchy-design Skill
16★ repoUse when when you need to create a plotting or visualization framework that must support multiple plot kinds (spectrum, chromatogram, mobilogram, peakmap) each backed by multiple rendering engines (matplotlib, bokeh, plotly), and you want to avoid combinatorial explosion of concrete classes while.
Object oriented design analysis
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/object-oriented-design-analysis Skill
16★ repoUse when you need to understand or document the extensibility architecture of a modular OOP codebase—specifically when developers must identify which classes, interfaces, or modules to extend or improve, or when onboarding contributors to a project whose documentation does not explicitly expose its.
Orchestrator architecture design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/orchestrator-architecture-design Skill
16★ repoUse when when building a multi-backend visualization library where users specify both a plot type (spectrum, chromatogram, peakmap) and a backend (matplotlib for static output, Bokeh or Plotly for interactive), and you need to avoid code duplication across backends while keeping the user-facing API.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/parameter-search-space-design Skill
16★ repoUse when when beginning an untargeted LC-MS analysis and either (1) the dataset characteristics (sample complexity, instrument platform, or polarity) differ from previously optimized cohorts, (2) multiple peak-picking algorithms (Centwave, FeatureFinderMetabo, ADAP) are available and their relative.
Parameter sharing mechanism design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/parameter-sharing-mechanism-design Skill
16★ repoUse when designing a contrastive learning pipeline for ion images or other data modalities where you need to process multiple augmented versions of the same input through an encoder and enforce similarity between the resulting representations.
Plate layout parameter configuration
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/plate-layout-parameter-configuration Skill
16★ repoUse when after uploading a sample list to InjectionDesign and before performing inter-batch balancing and intra-batch randomization.
Proteomics data structure design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/proteomics-data-structure-design Skill
16★ repoUse when when building a mass-spectrometry analysis pipeline that must support multiple vendor and open formats (mzML, mzXML, Thermo, Agilent, Bruker, etc.) and you need to shield downstream tools from format-specific parsing logic.
Python class design with dunder methods
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/python-class-design-with-dunder-methods Skill
16★ repoUse when when you need to enable bracket notation (e.g., handler[5]) for random access to blocks within a large compressed or remote data source, or when you want to support both random access and sequential iteration over data without materializing all records upfront.
Python class interface design for ml libraries
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/python-class-interface-design-for-ml-libraries Skill
16★ repoUse when when building a machine learning library for scientific workflows where users need to: (1) prepare domain-specific data (e.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/query-language-grammar-design Skill
16★ repoUse when when you need to enable non-programmer mass spectrometry users to express complex spectral search patterns (e.g., isotope patterns, precursor mass constraints, scan-type filters) without writing procedural code.
Random access seekable file interface design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/random-access-seekable-file-interface-design Skill
16★ repoUse when you have a large mzML file or text corpus (e.g., Moby Dick, proteomics run) stored in compressed or database format and need to retrieve specific spectra or chapters by ID without sequential iteration or full decompression.
Regex pattern design for value format validation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/regex-pattern-design-for-value-format-validation Skill
16★ repoUse when when you have a metabolomics metadata table and need to automatically identify and standardize database-ID columns (HMDB_ID, PubChem_ID, KEGG_ID, etc.) whose values follow known format conventions.
Repeated measures anova design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/repeated-measures-anova-design Skill
16★ repoUse when you have an imputed, long-format metabolomics dataset with repeated measurements (multiple time points) per subject, a categorical grouping variable (e.
Sequence to sequence architecture design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/sequence-to-sequence-architecture-design Skill
16★ repoUse when when you have encoder-produced fixed-size embeddings and need to generate variable-length discrete sequences (e.g., SMILES tokens, protein sequences, chemical formulas) as outputs.
Shiny ui component implementation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/shiny-ui-component-implementation Skill
16★ repoUse when you have an existing R package with statistical or data-processing functions and need to expose its functionality through an interactive web interface where end users (non-R programmers) can upload datasets, configure analysis parameters (e.
Siamese neural network architecture design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/siamese-neural-network-architecture-design Skill
16★ repoUse when when you have pairs of mass spectrometry spectra and need to predict their molecular structural similarity as a scalar Tanimoto score in the range [0, 1].
Sinusoidal positional encoding design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/sinusoidal-positional-encoding-design Skill
16★ repoUse when you have variable-length lists of MS/MS peaks (m/z and intensity pairs) that need to be encoded into a fixed-dimensional representation compatible with transformer architecture.
Smarts pattern design for microbial degradation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/smarts-pattern-design-for-microbial-degradation Skill
16★ repoUse when you need to predict small molecule metabolism in soil or aquatic microbiota and must translate published biotransformation rules (reaction types, enzyme families, substrate patterns) from EAWAG or similar biodegradation databases into executable chemical pattern-matching rules compatible.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/spectral-token-design Skill
16★ repoUse when when you need to prepare mass spectra and molecular structures for joint modeling in a BART or transformer-based sequence model, and you lack a unified representation scheme that allows both modalities to be encoded and decoded without collision or information loss.
Targeted transition list generation
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/targeted-transition-list-generation Skill
16★ repoUse when you have a set of lipid targets defined by species name, acyl chain composition, and expected adducts, and you need to configure a targeted mass spectrometry workflow (PRM or MRM) in Skyline.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/tensor-embedding-design Skill
16★ repoUse when when you need to represent discrete chemical formulae (e.
Transformer encoder architecture design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/transformer-encoder-architecture-design Skill
16★ repoUse when when you need to learn chemical-rational embeddings of tandem MS/MS spectra for library matching or molecular property prediction, and you want to leverage self-supervised learning through masking.
Transition group feature extraction
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/transition-group-feature-extraction Skill
16★ repoUse when when you have loaded a TransitionGroup (extracted ion chromatogram or mobilogram from DIA mass spectrometry data) and need to identify precise peak boundaries, apex retention/drift time, and intensity values for quantitative feature detection.
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/transition-group-peak-picking Skill
16★ repoUse when you have loaded extracted ion chromatogram (XIC) data from DIA mass spectrometry and need to identify peak boundaries for peptide precursor transitions.
Transition list formatting for targeted analysis
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/transition-list-formatting-for-targeted-analysis Skill
16★ repoUse when you have generated or assembled a lipid spectral library with precursor m/z values, adduct information, and fragmentation patterns, and you need to import those spectra into Skyline for targeted data-independent or parallel-reaction-monitoring (PRM) analysis.
Treatment group comparison design
HolobiomicsLab/asb-skill-collections/collections/metabolomics/v2/skills/treatment-group-comparison-design Skill
16★ repoUse when you have paired metabolomics count data and metadata with at least two treatment groups (e.g., Strep vs Mock), a clear Factor column identifying group membership, and a research question about which metabolites differ significantly in abundance between treatments.