Backend & Data · Data Science & ML
Data Science & ML tools
Every Data Science & ML tool worth a solo builder's time - the agent skills, MCP servers and marketplaces tagged Data Science & ML, ranked by community signal. A focused slice of the broader Backend & Data category.
What's in Data Science & ML
Data Science & ML collects 540 curated tools across agent skills, a focused part of the broader Backend & Data category. Every one is screened against a single quality bar and ranked by real community signal.
These tools span Idea, Validate, Build, Ship, Grow and Operate of the build journey.
Description
1Paper Context ResolverBackend & DataResolve narrow paper-backed gaps (splits, preprocessing, eval protocol, checkpoints, runtime) when README and repo files are insufficient for faithful ML paper reproduction.140k412
2Repo Intake And PlanBackend & DataScan an ML research repository, extract README commands, and recommend the smallest trustworthy inference or evaluation reproduction target.140k412
3Minimal Run And AuditBackend & DataRun documented inference, evaluation, or smoke commands and normalize evidence into standardized repro_outputs with patch notes.140k412
4Env And Assets BootstrapBackend & DataBootstrap conda-first environments plus checkpoints, datasets, and cache paths before a documented reproduction run.140k412
5Analyze ProjectBackend & DataMap a deep learning repo read-only—training, inference, and eval entrypoints, configs, and suspicious patterns—before you let an agent patch model code.47.2k412
6Ai Research ReproductionBackend & DataOrchestrate README-first, minimal-trustworthy reproduction of a deep learning repository with auditable repro_outputs evidence.47.1k412
7Run TrainBackend & DataRun a already-chosen deep-learning training command with conservative startup, short-run, full kickoff, or resume checks while writing command, config, seed, logs, checkpoints, status, and metrics int47.1k412
8Explore RunBackend & DataRun authorized exploratory ML variants in isolation, favoring small subsets and short cycles, then surface TOP_RUNS for human review—not auto-promoted baselines.47.1k412
9Firecrawl Company DirectoriesBackend & DataTurn YC, Crunchbase, Product Hunt, G2, or custom company directories into JSON, CSV, or CRM-ready research tables with Firecrawl.14.3k29
10Data StorytellingBackend & DataTurn data and analysis into a clear narrative with visuals and insights.11.7k36.5k
11Kpi Dashboard DesignBackend & DataStructure department KPIs and dashboard layouts for sales, marketing, product, and finance so a solo founder can see what to track.10k36.5k
12Powerbi ModelingBackend & DataName tables, columns, and DAX measures consistently and choose explicit vs implicit measures for solo-friendly Power BI semantic models.9.2k34.6k
13Power Bi Report Design ConsultationBackend & DataRun a structured Power BI visualization consultation so KPIs, audience, and chart choices are scoped before you build pages in the service.8.8k34.6k
14Power Bi Dax OptimizationBackend & DataTune slow or unreadable Power BI measures before sharing dashboards with stakeholders or investors.8.7k34.6k
15Power Bi Model Design ReviewBackend & DataRun a structured Power BI star-schema and relationship review so analytics models stay performant before reports ship.8.6k34.6k
16Bigquery Pipeline AuditBackend & DataReview Python BigQuery jobs for runaway cost, weak idempotency, and silent failures before production runs.8.6k34.6k
17Power Bi Performance TroubleshootingBackend & DataRun a structured Power BI performance diagnosis across models, reports, and queries when load times or visuals fail solo-builder SLA targets.8.5k34.6k
18Fabric LakehouseBackend & DataDesign Microsoft Fabric lakehouse pipelines with Data Factory activities, Spark notebooks, bronze/silver/gold layers, and Delta maintenance on OneLake.8.5k34.6k
19Shuffle Json DataBackend & DataRandomize or reorder repetitive JSON fixture objects for tests or demos after proving every object shares the same schema.8.5k34.6k
20Data VisualizationBackend & DataPick the right chart type and generate accessible, publication-quality Python figures with matplotlib, seaborn, or plotly.8.2k19.6k
21Dbt Transformation PatternsBackend & DataStructure warehouse layers, sources, staging, and tests in dbt when a solo builder ships analytics on Snowflake, BigQuery, or Postgres.7.5k36.5k
22Airflow Dag PatternsBackend & DataAuthor production Airflow DAGs with TaskFlow API, XCom data passing, and daily ETL extract-transform-load patterns on S3.7.5k36.5k
23Ml Pipeline WorkflowBackend & DataDesign and automate end-to-end MLOps pipelines from data prep through training, validation, deployment, and monitoring.7.4k36.5k
24Spark OptimizationBackend & DataTune PySpark jobs with partitioning, join strategies, and I/O patterns so solo-built data pipelines run faster and cheaper on Spark clusters.7.3k36.5k
25Datanalysis Credit RiskBackend & DataRun credit-risk variable selection, PSI stability checks, and LightGBM AUC screening on tabular loan or risk datasets before you ship a scoring model.7k34.6k
26Bigquery BasicsBackend & DataWire your agent to create BigQuery datasets, run SQL, manage jobs, and use BigQuery ML without guessing gcloud and bq CLI steps.6.1k12.1k
27Marimo PairBackend & DataStart, discover, and invoke marimo notebook servers correctly inside uv, pixi, or sandbox projects so agents can pair with live notebooks.4.4k321
28Pytorch PatternsBackend & DataApply idiomatic PyTorch patterns when you train models, load data, or harden experiments for reproducibility and GPU efficiency.4.2k210k
29Data AnalysisBackend & DataTurn Excel or CSV exports into summarized insights, charts, and markdown reports without leaving your agent session.4.1k196
30Data AnalystBackend & DataGet SQL, pandas, and statistics help to explore datasets, clean data, and summarize findings for product decisions.3.5k114k
31Pandas ProBackend & DataSummarize and transform tabular data with pandas GroupBy, named aggregation, pivot tables, and crosstab patterns for reports and product metrics.3.5k9.7k
32Explore DataBackend & DataProfile a new warehouse table or uploaded file so you know shape, nulls, duplicates, and which metrics to trust before building dashboards or models.3.3k19.6k
33AnalyzeBackend & DataTurn natural-language business questions into SQL-backed answers—from one number to a stakeholder-ready metrics narrative.3.3k19.6k
34Marimo NotebookBackend & DataScaffold bespoke light/dark anywidget UI for marimo notebooks without hand-rolling the full JS/CSS boilerplate.3.3k144
35Create VizBackend & DataTurn query results or pandas DataFrames into clear, publication-ready Python charts for reports, decks, and dashboards.3.1k19.6k
36Visualization ExpertBackend & DataPick the right chart type and dashboard layout so product metrics and research results communicate clearly to users and stakeholders.3k114k
37Senior Data ScientistBackend & DataApply production-minded experiment design, feature engineering, and ML-at-scale patterns when planning or building data products solo.2.8k27.8k
38Jupyter NotebookBackend & DataSpin up a structured Jupyter notebook with objective, setup, plan, and runnable cells for experiments, tutorials, or reproducible data checks without hand-wiring every section.2.7k21.7k
39Statistical AnalysisBackend & DataInterpret product and business metrics with the right center, spread, and tests instead of misleading averages.2.6k19.6k
40Real Estate SearchBackend & DataLook up Korean apartment, officetel, villa, and commercial 실거래가/전월세 via the k-skill-proxy without managing MOLIT API keys yourself.2.5k5.4k
41Computer Vision OpencvBackend & DataImplement image and video processing pipelines with OpenCV conventions, PyTorch-friendly structure, and GPU-aware CV best practices in Python.2.5k133
42Lck AnalyticsBackend & DataTurn Oracle-style LCK match CSVs into cached historical JSON and dated match or live-game analysis reports inside your agent workflow.2.4k5.4k
43Data AnalysisBackend & DataRun SQL over Excel and CSV exports with DuckDB—schema inspection, queries, summaries, and exports—without standing up a warehouse.2.3k70.7k
44Data AnalyticsBackend & DataGenerate PlantUML data-pipeline and analytics architecture diagrams for docs, specs, and stakeholder reviews.2.3k2.9k
45Ml PipelineBackend & DataSet up reproducible ML experiment tracking with MLflow or Weights & Biases so solo builders can compare runs, version models, and ship models they can trust.2.3k9.7k
46Spark EngineerBackend & DataTune PySpark partitioning and caching so batch jobs finish without OOMs, shuffle storms, or runaway partition counts on modest clusters.2.3k9.7k
47Marimo BatchBackend & DataSample random hyperparameter grids and launch each combo as a Hugging Face Job from your marimo training script without hand-writing dozens of CLI invocations.2.1k144
48Dagster ExpertBackend & DataWrite correct Dagster AssetSelection filters and string syntax for UI, CLI, and Python when defining data pipelines.2.1k159
49Business Analytics ReporterBackend & DataTurn product and business metrics into clear analytics reports your agent can draft or structure for founder decision-making.1.9k399
50Validate DataBackend & DataRun a structured QA pass on an analysis, SQL, or notebook before you email slides, ship a dashboard, or defend metrics to stakeholders.1.9k19.6k
51Excel AnalysisBackend & DataLoad .xlsx workbooks with pandas, summarize tabular data, group and filter metrics, and write formatted outputs for solo founder reporting.1.8k27.8k
52Csv Data SummarizerBackend & DataDrop in a CSV and get immediate summary statistics and plots via pandas—no back-and-forth about which analysis to run.1.7k399
53Deepline AnalyticsBackend & DataAnswer revenue, pipeline, funnel, and warehouse questions through Deepline by starting from the Snowflake semantic layer instead of ad-hoc table guessing.1.7k0
54Chart VisualizationBackend & DataGenerate area and bar charts (and related Deer Flow chart specs) from structured data for dashboards, reports, and KPI storytelling.1.6k70.7k
55Tooluniverse Sequence RetrievalBackend & DataProduce complete, citation-ready gene and sequence profiles via ToolUniverse with correct NCBI versus ENA tool routing and curation tiers.1.5k1.4k
56Metal KernelBackend & DataAdd or migrate PyTorch operators to native Metal/MPS kernels on Apple Silicon using native_functions.yaml, Metal shaders, and host stubs—not MPSGraph.1.4k101k
57Exploratory Data AnalysisBackend & DataGenerate a structured EDA report for a local dataset file before modeling, cleaning, or dashboard work.1.4k27.8k
58Kibana DashboardsBackend & DataCreate and extend Kibana dashboards and visualization panels (markdown, metric, ES|QL bar charts) through structured JSON the agent can generate and apply via the Dashboards API.1.4k502
59Senior Data EngineerBackend & DataApply production-grade data modeling, pipeline architecture, and scale patterns when a solo builder designs warehouses, ETL, or real-time analytics beyond a single-database app.1.3k27.8k
60Jupyter Notebook WritingBackend & DataAuthor Milvus bootcamp tutorials as consistent Markdown or .ipynb files with Colab badges, pip blocks, and the standard section layout.1.3k0
Showing the top 534 of 4,059 tools · search to find the rest.
Explore more
Data Science & ML tools - common questions
What counts as a Data Science & ML tool?
Any agent skill, MCP server or marketplace tagged Data Science & ML - a focused slice of the broader Backend & Data category. Skillselion collects every Data Science & ML tool across types on one page.
How are Data Science & ML tools ranked?
By real community signal - installs, GitHub stars and votes - not paid placement. Sponsored slots, when present, are labelled and kept out of the ranking.