Data & Analytics
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
-
holobiomicslab Skill CSV Format Specification Compliance 2Use when after feature extraction or feature alignment when you have FeatureSet or Sample objects that must be exported as CSV files for sharing, archival, or downstream analysis. Specifically: (1) when exporting single-sample feature tables from find_feature() output;
- holobiomicslab Skill Mass Accuracy Tolerance Calibration 3
Use when you have experimental fragment m/z values from HRMS/MS instruments (Q-Exactive orbitrap, Q-TOF) in CSV or mzML-derived peaklist format, and need to match them against a library of 500,000+ in-silico fragmented lipid species.
- holobiomicslab Skill Mass Spectrometry Fragment Matching 3
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.
- holobiomicslab Skill Hrms Feature Annotation Integration 3
Use when you have LC- or GC-HRMS data in mzML format and a feature list (CSV/TSL/Excel) from external feature detection software (e.
- holobiomicslab Skill Candidate Metadata Record Serialization 3
Use when after computing InChIKey and neighbourhood scores for library match candidates, you need to write results to a persistent format (CSV, JSON, or database) for storage, sharing, and interpretation.
- holobiomicslab Skill Dataframe Lazy Loading Comparison 3
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.
- holobiomicslab Skill Mass Spectrometry Peak Classification 3
Use when you have raw mzML files and feature tables (CSV format from mzMine or XCMS) from untargeted LCMS experiments and need to distinguish true metabolite peaks from false positives introduced by the peak-picking algorithm.
- holobiomicslab Skill Quality Control Threshold Optimization 2
Use when when you have extracted a peak feature table (CSV or tabular format) with mass-to-charge ratios, retention times, and intensity values across multiple samples, and you need to distinguish genuine differential metabolic signals from instrumental noise or low-abundance background before.
- holobiomicslab Skill Multi Dataset Integration Mzrt Space 2
Use when you have multiple CSV feature tables from independent metabolomic experiments, each with RT and m/z annotations, and you need to produce a single consolidated feature matrix for comparative analysis across all samples.
- holobiomicslab Skill Breath Volatile Peak Classification 2
Use when after feature extraction and alignment when you have a numerical feature table (CSV or dataframe) with intensity values across retention time or m/z dimensions, and you need to identify and rank peaks by signal quality and prominence rather than relying on all extracted features equally.
- holobiomicslab Skill Dataframe And Numericlist Manipulation 2
Use when you are implementing a new MsBackend subclass and need to store spectra metadata (sample names, retention times, precursor m/z, etc.) separately from peak data (m/z and intensity pairs) while maintaining row-wise alignment.
- holobiomicslab Skill CSV File Parsing And Peak Indexing 2
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.
- holobiomicslab Skill Elemental Ratio Histogram Visualization 2
Use when after loading a numeric elemental ratio column (H/C, O/C, N/C, etc.) from a CSV file into Punc'data, when you need to visualize the distribution of molecular formulas across a sample and want bin spacing to adapt automatically: narrow bins (0.1) for low-range data (span ≤ 3.
- holobiomicslab Skill Lexical Tokenization And Grammar Design 2
Use 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.
- holobiomicslab Skill Mass Spectrometry Peak Pair Analysis 3
Use when you have preprocessed MSI data (as a CSV intensity matrix or Cardinal MSProcessedImagingExperiment object) and suspect that observed peaks include both parent ions and their adducts formed with matrix or salt species.
- holobiomicslab Skill SQL Query Optimization For Similarity Search 2
Use when when migrating spectral library data from file-based formats (JSON, CSV, binary) into a persistent store and need to support fast filtered queries on metadata and similarity computations against query spectra.
- holobiomicslab Skill Mass Spectrometry Plot Type Specialization 3
Use when you have a Pandas DataFrame containing mass spectrometry data (e.
- holobiomicslab Skill Feature Table Generation From Aligned Spectra 2
Use when after retention-time and m/z-based peak alignment has been completed across a cohort of LC-MS samples, and you need to create a unified quantitative matrix for statistical testing, multivariate analysis, or annotation workflows.
- holobiomicslab Skill Metabolite Quantification Accuracy Assessment 3
Use when you have executed mzExacto() on a preprocessed GC-MS dataset and need to verify that the returned dataframe correctly matches query chemicals to their m/z peaks, retention times, and quantitative measurements (area values).
- holobiomicslab Skill Dataframe Construction From Backend Sources 3
Use when when implementing a new MsBackend subclass that stores only a subset of core spectra variables (e.
- holobiomicslab Skill Spectral Array Extraction And Reconstruction 2
Use when your input is an mzPeak archive (ZIP of Parquet files) and you need to recover spectrum signal data (m/z values and intensities) for downstream analysis, visualization, or format conversion. Use this skill when working with profile or centroid mode spectra stored in `spectra_data.
- holobiomicslab Skill Mass Spectrometry Data Visualization Pandas 3
Use when when you have mass spectrometry data (mzML, Bruker .d, or CSV) loaded into a Pandas DataFrame with columns for m/z, retention time, ion mobility, or intensity values, and you need to render spectrum plots, chromatograms, mobilograms, or 2D peak maps.
- holobiomicslab Skill S4 Class Extension For Backend Implementation 3
Use 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.
- holobiomicslab Skill Metabolite Compound List Mapping With Adduct Assignment 2
Use when when you have mzML files from targeted or untargeted metabolomics experiments run in multiple ionization modes (e.g., KO_NEG, KO_POS, STD_NEG, STD_POS, WT_NEG, WT_POS) and a CSV list of reference compounds (e.
- holobiomicslab Skill Backend Compatibility Verification Visualization Library 3
Use when you have mass spectrometry data loaded into a pandas DataFrame with m/z, retention time, and intensity columns, and need to confirm that pyOpenMS-Viz can produce visualizations (spectra, chromatograms, or peak maps) using a specific plotting backend (matplotlib, Bokeh, or Plotly) on real.
-
tools-only Bundle Dasel Reference 2Complete dasel v3 query syntax reference — selectors, functions, conditionals, variables, spread operator, type casting, and format-specific patterns for JSON, YAML, TOML, XML, CSV, HCL, INI
7 - tools-only Bundle M4 API 2
Use the M4 Python API to query clinical datasets programmatically. Use when writing code to access clinical databases, executing SQL via Python, or performing multi-step data analysis.
7 - tools-only Bundle Yandex Wordstat 2
Анализ поискового спроса через Yandex Wordstat API. Используй когда нужно: исследовать спрос, семантическое ядро, частотность запросов, сезонность или региональный спрос. Топ до 2000 запросов, ассоциации, динамика, экспорт CSV.
7 - tools-only Bundle Openbb Crypto 2
Cryptocurrency market analysis using OpenBB - price data, on-chain metrics, DeFi analytics, whale tracking, and market sentiment
7 - tools-only Bundle Cosmos Dbt Core 2
Use when turning a dbt Core project into an Airflow DAG/TaskGroup using Astronomer Cosmos. Does not cover dbt Fusion. Before implementing, verify dbt engine, warehouse, Airflow version, execution environment, DAG vs TaskGroup, and manifest availability.
7 - tools-only Bundle Using Dbt For Analytics Engineering 2
Use when doing any dbt work - building or modifying models, debugging errors, exploring unfamiliar data sources, writing tests, or evaluating impact of changes. Use for analytics pipelines, data transformations, and data modeling.
7 - tools-only Bundle Cosmos Dbt Fusion 2
Use when running a dbt Fusion project with Astronomer Cosmos. Covers Cosmos 1.11+ configuration for Fusion on Snowflake/Databricks with ExecutionMode.LOCAL. Before implementing, verify dbt engine is Fusion (not Core), warehouse is supported, and local execution is acceptable. Does not cover dbt Core.
7 - tools-only Bundle Bio Variant Calling Joint Calling 2
Joint genotype calling across multiple samples using GATK CombineGVCFs and GenotypeGVCFs. Essential for cohort studies, population genetics, and leveraging VQSR. Use when performing joint genotyping across multiple samples.
7 - tools-only Bundle 328 Description Skill Fad02ab4
This skill should be used when analyzing Claude Code session transcripts, reviewing agent performance, finding anti-patterns or tool misuse, detecting user frustration signals, mining workflow patterns, running kaizen analysis, debugging agent behavior, or performing session forensics. Provides JSONL schema with field paths, DuckDB SQL query patterns, 10 analysis dimensions, and PM4Py process mining methodology.
7 - tools-only Bundle Transcript Analyst 2
Deep-dive into Claude Code session transcripts using DuckDB SQL and process mining tools — spawned by analyze and explore commands to query JSONL data, detect anti-patterns, extract frustration signals, and mine workflow patterns across sessions
7 - tools-only Bundle 669 Patient Cohort Analysis 989f1534
Patient Cohort Analysis Guide
7
Frequently asked questions
What are Data & Analytics agent skills?
Data agent skills make AI agents useful for data work: writing SQL, cleaning datasets, building pipelines, working with spreadsheets, and producing analyses. Each skill is a reviewed SKILL.md file that teaches the agent one workflow well, ready to install in seconds.
Which Data & Analytics skills are most installed?
Popular Data & Analytics skills on SkillMD right now include csv-format-specification-compliance, mass-accuracy-tolerance-calibration, mass-spectrometry-fragment-matching. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Data & Analytics skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.