Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Dataflow workflow engine for scalable bioinformatics pipelines. Defines processes (containerized tasks) connected by channels; runs local, HPC (SLURM/SGE), cloud (AWS/GCP/Azure), or Kubernetes via a single config change. Powers nf-core. Use Snakemake for rule-based Python workflows; use Nextflow for containerized, cloud-native, and nf-core pipelines.
Open-source bio-image data management. Use the omero-py client to connect to an OMERO server, retrieve images as numpy arrays, annotate with tags and key-value pairs, manage ROIs, and feed image data into Python analysis pipelines — programmatically, no GUI.
Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log".
Use to write, debug, or explain code for remote LLM training and inference with PyTRIO/TRIO. Use when the user mentions pytrio, TRIO, PyTRIO SDK, ServiceClient, TrainingClient, SamplingClient, LoRA training, SFT, asynchronous SFT, PyTRIO-Jev, PyTRIO Decision Model, multimodal inference, multimodal training, Vision GRPO, visual RLVR, ImageChunk, RL, GRPO, OPD, Search-R1, ReTool, DAPO, GSPO, ALFWorld, TextWorld, Agentic RL, OPSD, On-Policy Self-Distillation, DPO, custom loss functions, forward_backward_custom, forward_backward_custom_async, tool-use reinforcement learning, HuggingFace datasets, the TRIO OpenAI-compatible API, SwanLab training logs, weight saving, checkpoints, or remote LLM post-training.
Redis database expert for caching, data structures, Pub/Sub, Streams, Lua scripting, and performance optimization using Bun.redis native client. Use when working with Redis, caching strategies, key-value stores, real-time data, vector search, or document databases. Works alongside bun-expert skill.
Corrects the wrong defaults a model has when designing a relational schema — the DDL decisions an experienced engineer makes differently. Use when creating or reviewing tables, migrations, ER models, or ORM schema definitions. Covers identity and keys (surrogate vs natural, identity vs serial, uuidv7, composite keys that make cross-tenant references impossible), relationships (polymorphic foreign keys the database cannot enforce, referential actions, unindexed FK columns, disjoint subtypes), invariants the engine can prove instead of application code (EXCLUDE, partial unique indexes, CHECK limits, deferrable cycles, NOT VALID), types (timestamptz, exact money, range types, enum vs lookup table), derived and encoded data (generated columns, JSONB as an escape hatch), and time (events vs in-place updates, soft-delete flags that silently disable constraints, temporal keys). NOT for query tuning, index selection for read paths, or connection pooling.
Designs retrieval strategies for querying knowledge graphs in RAG systems, covering pattern selection (global-first, local-first, U-shaped hybrid), query decomposition for multi-hop reasoning, ranking and constraint configuration, and provenance tracking for citation. Use when designing retrieval pipelines, orchestrating search over knowledge graphs, or when user mentions retrieval strategy, search orchestration, query decomposition, multi-hop reasoning, provenance tracking, or citation in GraphRAG.
Seata distributed transaction skill. Covers the decision tree for choosing among the four modes AT/TCC/SAGA/XA, the mandatory undo_log table in AT mode, useTCCFence in TCC mode to solve idempotency/hanging/empty rollback, SAGA state machine for long processes, global transaction timeout configuration (@GlobalTransactional timeoutMills), and read isolation enhancement (@GlobalLock + FOR UPDATE). Corrects LLM mistakes: not knowing which of AT/TCC/SAGA to choose, not creating the undo_log table, non-idempotent TCC Confirm, and not handling the watch dog.
Generate FK-aware, deterministic sample/seed data from a database schema, ORM model, or migrations — INSERT statements emitted in dependency order (parents first), values derived from row index so output is stable and reviewable. Read-only; never writes to a database. For dev/test fixtures only. Use when the user asks to seed, generate sample/test/fixture/dummy/fake data, populate tables, or create starter rows for Postgres, MySQL, SQLite, and friends.
Intelligent database querying skill. Connects to production databases through an SSH tunnel and supports natural language to SQL, query execution, and table schema exploration. Use this skill when users need to query a database, ask about data, or inspect table schemas.
Social Media Matrix Tracker dashboard template. Use when users ask for a cinematic, data-dense social media analytics dashboard with multi-platform metrics, interactive charts, hover insights, range compare, and dark/light theme switching in a single HTML artifact.
Use when defining or changing SpacetimeDB tables, columns, constraints, primary keys, unique constraints, indexes, auto-increment fields, default values, event tables, schedule tables, access permissions, file storage, or table performance. Triggers on: table, column, primary key, unique, index, btree, direct index, event table, schedule table.
Guided, jargon-free starting point for people with no schema and no database yet — a short 7-question wizard that turns "I want to build an app" into a concrete engine recommendation and a first data model. Zero artifacts required. Use when the user has nothing to audit, asks how to begin, says they're not technical, or doesn't know what database or schema they need.
Develop high-performance C/C++ plugins for Stata using the stplugin.h SDK. Use when the user asks to create a Stata plugin, write C/C++ code for Stata, accelerate a Stata command with C, build cross-platform Stata plugins, or translate/port a Python or R package into Stata. Covers the full lifecycle: SDK setup, data flow, memory safety, .ado wrappers with preserve/merge, cross-platform compilation, performance optimization (pthreads, pre-sorted indices, XorShift RNG), debugging, and distribution via net install. Also includes a translation workflow for porting Python/R packages to Stata — wrapping existing C++ backends when available, or writing C from scratch when not.
Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.
Guided statistical analysis for research data — test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required sample sizes, or write up results — even if they never name a specific test. Covers t-tests, ANOVA, chi-square, correlation, regression, non-parametric and Bayesian methods. For low-level model APIs, see the statsmodels and pymc skills.
Python library for single-particle tracking (SPT) in video microscopy via the Crocker-Grier algorithm. Locate particles (fluorescent spots, colloids, vesicles, cells) per frame, link into trajectories, filter short tracks, and compute MSD for diffusion analysis. 2D/3D with subpixel accuracy; reads TIF stacks, AVI, image series via pims. Use for quantitative SPT and diffusion coefficient extraction from fluorescence or brightfield video.
Analyze and synthesize user research findings into structured, actionable insights. Use when given user research data, interview transcripts, survey results, or user feedback that needs to be analyzed and summarised. Produces a themed synthesis with prevalence data, supporting quotes, pain points analysis, feature request prioritisation, and recommended next steps. For interview transcripts specifically use user-interview-synthesis instead.
Access USPTO patent data via PatentsView REST API and Google Patents Public Data (BigQuery). Search by inventor, assignee, CPC, or keywords; download metadata and claims; analyze portfolios; track tech trends. For IP landscape analysis, competitor monitoring, prior art search, and tech forecasting in life sciences and biotech.
Predict RNA secondary structure, MFE folding, base-pair probabilities, RNA-RNA interactions via ViennaRNA Python bindings. Pipeline: sequence → MFE → partition function and pair-probability matrix → dot-bracket → duplex. Use for siRNA/sgRNA targeting, ribozyme design, RNA accessibility. Use RNAfold CLI for batch use without Python.
Use when writing or reviewing SQL, schema definitions, or application code that targets YugabyteDB's PostgreSQL-compatible YSQL API (port 5433). Triggers on CREATE TABLE, indexes, connections, transactions, sharding, migrations from PostgreSQL, or any mention of YugabyteDB with SQL.
DTC full-funnel diagnostics and attribution — anomaly detection, cross-business-line problem localization, root cause analysis, ICE prioritization. Trigger words: 诊断, diagnose, 归因, 根因, 指标下降, 问题出在哪, 为什么下降, 全链路, sales dropped, revenue drop, root cause, funnel diagnosis, attribution.
Data pipelines, feature stores, and embedding generation for AI/ML systems. Use when building RAG pipelines, ML feature serving, or data transformations. Covers feature stores (Feast, Tecton), embedding pipelines, chunking strategies, orchestration (Dagster, Prefect, Airflow), dbt transformations, data versioning (LakeFS), and experiment tracking (MLflow, W&B).
Runs time series machine learning with the aeon library — classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search via scikit-learn compatible APIs. Use when working with temporal data, sequential patterns, or time-indexed observations (univariate or multivariate) that need specialized algorithms beyond standard ML approaches. Part of the AlterLab Academic Skills suite.
Build, slice, concatenate, read, and write AnnData annotated data matrices (obs, var, X, layers, obsm, uns) — the scverse data STRUCTURE, not an analysis pipeline. Use when creating or wrangling .h5ad/zarr files, managing cell and gene annotations, concatenating batches, or handling layers/obsm/backed-mode; for the QC, normalization, clustering, UMAP, and differential-expression analysis pipeline prefer alterlab-scanpy instead, and for RNA velocity from spliced/unspliced layers prefer alterlab-scvelo instead. Part of the AlterLab Academic Skills suite.
Manipulate biological sequences, parse FASTA/GenBank/PDB files, run phylogenetics, and access NCBI/PubMed programmatically via Biopython (Bio.SeqIO, Bio.Entrez, Bio.PDB, Bio.Blast). Use when scripting custom bioinformatics pipelines, batch-processing sequence files, automating BLAST, or fetching records from Entrez — for quick one-off database lookups use gget, for unified multi-service integration use bioservices. Part of the AlterLab Academic Skills suite.
Query 40+ bioinformatics web services through one consistent Python API with bioservices (UniProt, KEGG, ChEMBL, Reactome, Ensembl, NCBI and more). Use when a workflow must hit multiple databases together, map identifiers across services, or run cross-database analyses — for quick single-database lookups use gget, for sequence and file manipulation use biopython. Part of the AlterLab Academic Skills suite.
Query the CZ CELLxGENE Census (200M+ cells) programmatically via cellxgene-census and TileDB-SOMA, slicing expression by tissue, disease, or cell type and returning AnnData. Use when pulling reference single-cell RNA-seq data from the largest curated public atlas, running population-scale queries, or benchmarking your data against a reference — for analyzing your own dataset use scanpy or scvi-tools. Part of the AlterLab Academic Skills suite.
Build and analyze genome-scale constraint-based metabolic models with COBRApy — flux balance analysis (FBA), flux variability analysis (FVA), gene and reaction knockouts, flux sampling, and SBML model I/O. Use when simulating metabolic networks, predicting growth or knockout phenotypes, or running systems-biology and metabolic-engineering analyses on SBML genome-scale models. Part of the AlterLab Academic Skills suite.
Query Google Data Commons for public statistical data aggregated from global sources, resolving geographic entities and pulling time-series statistics. Use when working with demographic data, economic indicators, health statistics, or environmental data — population counts, GDP figures, unemployment rates, disease prevalence — or when resolving places to DCIDs and exploring relationships between statistical entities. Part of the AlterLab Academic Skills suite.
Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. Use when identifying cancer-specific genetic vulnerabilities, finding synthetic lethal interactions, checking whether a gene is essential in given cell lines, or validating oncology drug targets. Part of the AlterLab Academic Skills suite.
Exploratory data analysis (EDA) on a scientific data file — auto-detects the format, runs structure/quality/statistics checks, and writes a markdown EDA report with downstream recommendations. Use when asked to "explore", "analyze", "summarize", "profile", or "QC" a data file, or to understand its structure/content/quality before deciding what analysis to run. Covers tabular (.csv .tsv .xlsx .parquet), arrays (.npy .npz .hdf5 .h5 .mat .fits), sequence/genomics (.fasta .fastq .sam .bam .vcf .bed .gff .gtf .h5ad), microscopy (.tif .nd2 .czi .lif .ims .dcm .nii), spectroscopy/MS (.mzML .mzXML .mgf .fid .jdx), chemistry (.pdb .cif .mol .sdf .xyz .gro), and proteomics/metabolomics (.pepXML .mzid .mzTab). For zero-shot forecasting of a series use alterlab-timesfm; to create/configure a chunked cloud array store use alterlab-zarr. Part of the AlterLab Academic Skills suite.
Accesses, analyzes, and extracts data from SEC EDGAR filings using the edgartools Python library. Use when working with SEC filings, financial statements (income statement, balance sheet, cash flow), XBRL financial data, insider trading (Form 4), institutional holdings (13F), company financials, annual/quarterly reports (10-K, 10-Q), proxy statements (DEF 14A), 8-K current events, company screening by ticker/CIK/industry, multi-period financial analysis, or any SEC regulatory filings. Part of the AlterLab Academic Skills suite.
Run ESM protein language models — ESMC for embeddings and representations, ESMFold2 for structure prediction, and ESM3 for generative multimodal protein design across sequence, structure, and function — locally or through the hosted Biohub Platform API (formerly Forge). Use when working with protein sequences, structures, or function prediction, designing novel proteins, generating protein embeddings, performing inverse folding, or doing protein-engineering tasks. Part of the AlterLab Academic Skills suite.
Queries the FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources, covering GDP, unemployment, inflation, interest rates, exchange rates, housing, and regional data. Use for macroeconomic analysis, financial research, policy studies, economic forecasting, fetching U.S. or international economic indicators by FRED series ID, and academic research requiring historical economic time series. Part of the AlterLab Academic Skills suite.
Builds INTERACTIVE charts with the Plotly Python library (plotly.express / graph_objects) — hover tooltips, zoom/pan, animations, rangesliders, 3D rotation, and standalone HTML/web-embeddable output. Use when a chart must be interactive or web-embedded, for dashboards (incl. Dash), exploratory data analysis, or rotatable 3D plots. For static publication figures defer to alterlab-matplotlib (or alterlab-scientific-viz for journal formatting); for static statistical charts (heatmaps, distributions) defer to alterlab-seaborn; for diagrams/schematics defer to alterlab-scientific-schematics or alterlab-mermaid. Part of the AlterLab Academic Skills suite.
Analyzes and manipulates materials with the pymatgen toolkit — crystal structures and molecules, phase diagrams and thermodynamic stability, electronic structure (band structures, DOS), surfaces and interfaces, and Materials Project database access. Use when working with crystal structures in materials science, converting between structure formats (CIF, POSCAR, XYZ), analyzing symmetry or space groups, computing phase diagrams, querying the Materials Project API, or handling VASP, Gaussian, or Quantum ESPRESSO output. Part of the AlterLab Academic Skills suite.
Build complete mass-spectrometry workflows with pyOpenMS — feature detection, peptide identification, protein quantification, and full LC-MS/MS pipelines across many MS file formats (mzML, mzXML) and algorithms. Use for comprehensive proteomics and MS data processing — for simple spectral comparison and metabolite identification use matchms. Part of the AlterLab Academic Skills suite.
Analyze biological data with scikit-bio — sequence analysis and alignments, phylogenetic trees, alpha/beta diversity metrics (including UniFrac), ordination (PCoA), PERMANOVA statistics, and FASTA/Newick I/O. Use for microbiome and community-ecology analysis — computing diversity, distance matrices, and ordination from feature tables. Part of the AlterLab Academic Skills suite.
Survival analysis and time-to-event modeling in Python with scikit-survival. Use when working with censored survival data, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating predictions with concordance index or Brier score, handling competing risks, or implementing any time-to-event workflow. Part of the AlterLab Academic Skills suite.
Train deep generative models for single-cell omics with scvi-tools — probabilistic batch correction and integration (scVI), reference-mapping transfer learning (scArches), differential expression with uncertainty, and multimodal models (totalVI for CITE-seq, MultiVI for multiome). Use when correcting batch effects, integrating multimodal data, or doing advanced probabilistic single-cell modeling — for standard analysis pipelines use scanpy. Part of the AlterLab Academic Skills suite.
Model interpretability and explainability with SHAP (SHapley Additive exPlanations) — feature importance and plots (waterfall, beeswarm, bar, scatter, force, heatmap). Use when explaining ML model predictions, computing feature importance, debugging models, analyzing bias or fairness, comparing models, or implementing explainable AI across tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model. Part of the AlterLab Academic Skills suite.
Graph Neural Networks with PyTorch Geometric (PyG) — node and graph classification, link prediction, GCN, GAT, and GraphSAGE layers, heterogeneous graphs, and molecular property prediction. Use when building or training GNNs for geometric deep learning on graph-structured data. Part of the AlterLab Academic Skills suite.
Out-of-core tabular analytics with Vaex — memory-mapped HDF5/Arrow/Parquet via vaex.open, lazy virtual columns, delayed single-pass aggregations on billion-row tables, binned histograms/heatmaps, and vaex.ml transformers on one machine. Vaex is in minimal-maintenance mode (vaex-core 4.19 from Sep 2025 supports only Python 3.9–3.12 and pandas < 3), so use it to run, fix, or migrate existing Vaex code; for new larger-than-RAM work prefer Polars lazy/streaming queries (alterlab-polars) or Dask (alterlab-dask). Use when a project already depends on Vaex, when opening memory-mapped HDF5/Arrow files, batching aggregations with delay=True, or porting a Vaex pipeline to Polars. Part of the AlterLab Academic Skills suite.
This skill should be used when the user asks to "analyze this dataset", "run datavoyager", "run data voyager", "explore this data", "what's in this CSV", "statistical analysis of", "find patterns in", or wants an AI-driven, code-executing analysis of a tabular dataset that answers a specific research question.
Use when writing Java (or other JVM language — Kotlin, Scala) application code that connects to a data source through a CData driver, after the connection and SQL have been validated with the cdata-cli discovery skill. Covers the CData JDBC Driver edition: reusing the same jar cdata-cli already downloaded and activated, putting it on the classpath (or adding it as a Maven/Gradle dependency), and connecting via JDBC (DriverManager, the jdbc:<source>: URL, PreparedStatement). This is the JVM build-phase companion to cdata-cli.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.