Data & Analytics

Data analysis, BI, visualization, datasets, statistics, and ML workflows

skills in category: 12,629
pages available: 527

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse data & analytics skills

Showing 145–168 of 12,629 skills

Method PubmedASearches PubMed/MEDLINE via E-utilities with MeSH-aware queries into a PMID and abstract CSV. Use when the user explicitly wants PubMed or PMIDs; broad asks go to method-lit-search.datapythongoVotes: 0GitHub stars: 3
Method PresubmitARuns the final gate on a manuscript, abstract, cover letter, or grant: section discipline, voice, and anti-slop passes. Use when a draft is about to go to co-authors.datagoVotes: 0GitHub stars: 3
Method PreregAGenerates preregistration and registry content for OSF, ClinicalTrials.gov, PROSPERO, or a study protocol. Use when the user asks to preregister or register a study.datapythongoVotes: 0GitHub stars: 3
Method PrACommits, pushes, and opens or updates a pull request with a value-first body, keeping data and PHI out. Use when the user asks to ship or open a PR.datagoshellVotes: 0GitHub stars: 3
Method PowerACalculates sample size and power for clinical, survival, cluster, and prediction-model studies, with a script, sweep, and SAP text. Use when the user asks for power or sample size.datapythonbashVotes: 0GitHub stars: 3
Method PlanACreates the durable plan for data-science work: an implementation plan or, for studies, a statistical analysis plan (SAP). Use when the user asks to plan work or write a SAP.datagogitVotes: 0GitHub stars: 3
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
Method PhenotypeAValidates a computable phenotype against chart review: 2x2 table, PPV, NPV, sensitivity, specificity, Wilson intervals. Use when checking a phenotype or code list.datapythonrustVotes: 0GitHub stars: 3
Method OptimizeARuns bounded, metric-scored experiment loops to improve a model, prompt, or pipeline without touching the test set. Use when a scored metric must improve; broken runs go to method-debug.datapythonrustVotes: 0GitHub stars: 3
Method Omics QcARuns sequencing and omics QA: FASTQ, BAM/CRAM, VCF, count matrices, methylation arrays, sample swaps, batch confounding. Use when omics data needs QC before analysis.datagoexpressVotes: 0GitHub stars: 3
Method NumbersALocks manuscript numbers to an analysis-written registry; a fail-closed gate traces each to its SAP output, script commit, and source hash. Use when reporting or checking results.datapythongoVotes: 0GitHub stars: 3
Method Notebook StandardsASets the structure and documentation contract for new or extended marimo, Jupyter, R Markdown, and Quarto notebooks. Use when creating notebook cells or chunks.datadocumentationVotes: 0GitHub stars: 3
Method Notebook EditAEdits existing Jupyter .ipynb notebooks with cell anchors, backups, and metadata-preserving writes. Use when the user asks to patch an existing .ipynb.datapythonbashVotes: 0GitHub stars: 3
Method Model ChoiceAChooses and justifies the statistical model (regression, mixed/GEE, survival, causal, prediction, Bayesian) after the estimand is set. Use when the user asks which model to fit.datapythongitVotes: 0GitHub stars: 3
Method Model CardAGenerates a clinical model card: intended use, data, performance with intervals, calibration, fairness, limits. Use when the user asks for a model card.dataperformancedocumentationVotes: 0GitHub stars: 3
Method Ml TrackAAdds reproducible ML experiment tracking (data hashes, splits, metrics, SAP links) with MLflow, W&B, DVC, or an offline log. Use when building or reviewing ML experiments.datapythongoVotes: 0GitHub stars: 3
Method Meta AnalysisAPools literature effects with REML/Hartung-Knapp. Use when power or a SAP needs a cited effect-size assumption and sensitivity range.datapythonrustVotes: 0GitHub stars: 3
Method MarimoACreates, edits, validates, and reviews marimo reactive Python notebooks (UI widgets, PEP 723, export). Use when working on a marimo notebook; Jupyter edits go to method-notebook-edit.datapythongoVotes: 0GitHub stars: 3
Method Language DetectADetects R, Python, or mixed-language signals in repo files and emits a language handoff. Use when a skill needs language evidence or the user asks the repo's stack.datapythongitVotes: 0GitHub stars: 3
Method IdeateAGenerates and ranks grounded research or analysis ideas from repo, literature, or topic context. Use when the user asks for ideas; developing one idea goes to method-brainstorm.datagobashVotes: 0GitHub stars: 3
Method HandoffACreates or resumes a portable continuity record for a data-science task, keeping SAP and real-data gates. Use when work moves to another agent or a later session.dataVotes: 0GitHub stars: 3
Method GrillAInterviews the user one question at a time to stress-test a study's goal, hypothesis, data, analysis, and journal, recommending answers. Use when the user says grill me.datagogitVotes: 0GitHub stars: 3
Method Genome BuildAPins genome build, annotation release, contig naming, and liftover for genomics data. Use when the user mentions GRCh37/38, hg19/hg38, T2T, GENCODE/Ensembl versions, or liftover.datapythongoVotes: 0GitHub stars: 3
Method FigureACreates and validates publication figures (ggplot2, matplotlib) with a journal-neutral clinical style and manifest. Use when the user wants a Kaplan-Meier, forest, calibration, ROC, or multi-panel figure.datapythongoVotes: 0GitHub stars: 3
Method FabricARoutes Microsoft Fabric work (OneLake, Lakehouse, Warehouse, PySpark, Data Factory, Direct Lake, Fabric ML, KQL) with research guardrails. Use when a project uses Fabric.datapythongoVotes: 0GitHub stars: 3