Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Access the European Nucleotide Archive (ENA) via its API and FTP to retrieve DNA/RNA sequences, raw sequencing reads (FASTQ), and genome assemblies by accession, with support for multiple formats. Use when downloading reads or sequences for a study, run, or sample accession, or when sourcing nucleotide data for genomics and bioinformatics pipelines. Part of the AlterLab Academic Skills suite.
Manipulate, annotate, and render phylogenetic trees programmatically with the ETE Toolkit (ete3) — parse and edit Newick/NHX, detect duplication/speciation events, infer orthology and paralogy, query NCBI taxonomy, and export PDF/SVG figures. Use when traversing or reformatting tree files, doing phylogenomic comparative analysis, or producing publication tree graphics in Python. Part of the AlterLab Academic Skills suite.
Query the openFDA API for drugs, medical devices, adverse event reports, recalls, regulatory submissions (510k, PMA), and substance identification (UNII). Use when searching FDA safety data, pharmacovigilance and adverse-event signals, device clearances, drug labels, or recall records for regulatory data analysis and safety research. Part of the AlterLab Academic Skills suite.
Parse and write FCS (Flow Cytometry Standard) files v2.0-3.1 with FlowIO — extract event data as NumPy arrays, read $-keyword metadata and channel/parameter definitions, and convert events to CSV or pandas DataFrame. Use when loading raw .fcs flow-cytometry files, inspecting channels and metadata, or preprocessing cytometry data for downstream gating and analysis. Part of the AlterLab Academic Skills suite.
Query NCBI Gene via the E-utilities and Datasets APIs, searching by gene symbol or Gene ID and retrieving gene information (RefSeqs, GO terms, genomic locations, associated phenotypes) including batch lookups. Use when resolving gene symbols to IDs, annotating gene lists, or pulling functional and positional gene metadata for downstream analysis. Part of the AlterLab Academic Skills suite.
Covers geospatial science across remote sensing, GIS, spatial analysis, and machine learning for earth observation — satellite imagery processing (Sentinel, Landsat, MODIS, SAR, hyperspectral), raster and DEM operations, spectral indices (NDVI/EVI/NDWI), spatial statistics, point cloud processing, network analysis, and cloud-native workflows (STAC, COG, Planetary Computer), with examples across Python, R, Julia, JavaScript, C++, Java, Go, and Rust. Use for remote sensing workflows, satellite/raster image classification, terrain/slope/hillshade analysis, spatial ML on earth-observation data, hydrological modeling, marine spatial analysis, or atmospheric science. For pure tabular vector work with no raster/EO aspect (plain GeoPandas sjoin, buffer, overlay, dissolve, choropleths) prefer the geopandas skill; for celestial-sphere astronomy coordinates (ICRS/galactic, FITS, WCS) prefer the astropy skill. Part of the AlterLab Academic Skills suite.
Analyze and engineer protein glycosylation — scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and reach curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). Use when identifying or designing glycosylation sites, optimizing therapeutic-antibody or biologic glycoforms, or doing glycoprotein engineering and vaccine-design work. Part of the AlterLab Academic Skills suite.
Queries the OFR (Office of Financial Research) Hedge Fund Monitor API for time series on hedge fund size, leverage, counterparties, liquidity, complexity, and risk management, including SEC Form PF aggregated statistics, CFTC Traders in Financial Futures, FICC Sponsored Repo volumes, and FRB SCOOS dealer financing terms (no API key or registration required). Use when working with hedge fund data, systemic risk monitoring, financial stability research, hedge fund leverage or leverage ratios, counterparty concentration, Form PF statistics, repo market data, or OFR financial research data. Part of the AlterLab Academic Skills suite.
Extract and preprocess tiles from whole-slide images (WSI) with histolab — OpenSlide-backed slide loading, tissue detection and masks, Random/Grid/Score tile extraction, and image/morphological filters for H&E preprocessing. Use when the user needs lightweight WSI slide preprocessing — building tile datasets for ML training, tissue segmentation, or quick tile-based inspection of histopathology slides. For end-to-end computational-pathology, deep-learning model training, nucleus segmentation, or multiplexed/spatial-proteomics (CODEX, Vectra) pipelines prefer alterlab-pathml instead. Part of the AlterLab Academic Skills suite.
Query and download public cancer imaging data from the NCI Imaging Data Commons (IDC) using the idc-index Python package, filtering by metadata, visualizing in-browser, and checking licenses, with no authentication required. Use when obtaining large-scale radiology (CT, MR, PET) or digital pathology DICOM datasets for AI/ML training or cancer imaging research. Part of the AlterLab Academic Skills suite.
Query the EMBL-EBI InterPro REST API for protein family, domain, and functional-site annotations integrated from member databases (Pfam, PANTHER, PRINTS, SMART, SUPERFAMILY, CDD, ProSite, NCBIfam, and others). Use when predicting protein function, analyzing or comparing domain architecture, classifying a protein by family or homologous superfamily, resolving a Pfam/InterPro accession, or mapping a protein's signatures to GO terms. Not for raw UniProt entry/FASTA retrieval or AlphaFold 3D structures. Part of the AlterLab Academic Skills suite.
Prepares ISO 13485 certification documentation for medical device Quality Management Systems (QMS) — gap analysis of existing documentation, Quality Manuals, required procedures and work instructions, and Medical Device Files. Use for ISO 13485 QMS documentation, conducting a documentation gap analysis, drafting a Quality Manual or SOP/work instruction, assembling a Medical Device File, identifying missing documentation for medical device certification, or when medical device regulations, QMS certification, FDA QMSR, or EU MDR are mentioned. Part of the AlterLab Academic Skills suite.
Manage, annotate, and trace biological data with LaminDB, an open-source FAIR data framework that makes datasets queryable, versioned, and reproducible. Use when registering or querying biological datasets (scRNA-seq, spatial, flow cytometry), validating and curating data against ontologies (genes, cell types, diseases, tissues), tracking data lineage and computational workflows, building data lakehouses, or wiring integrations with Nextflow, Snakemake, W&B, or MLflow. Part of the AlterLab Academic Skills suite.
Writes Markdown documents and text-based Mermaid diagrams (flowcharts, sequence, class, ER, gantt, state, and more) with full style guides, 24 diagram-type references, and 9 document templates. Use when a diagram or technical document should live as version-controllable Markdown/Mermaid text rather than a rendered image — READMEs, methods and pipeline diagrams, analysis or status reports, ADRs, and project docs that render natively on GitHub and GitLab. For AI-rendered publication schematics use alterlab-scientific-schematics; for manuscript prose use alterlab-scientific-writing; for plots of numeric data use alterlab-matplotlib. Part of the AlterLab Academic Skills suite.
Access the NIH Metabolomics Workbench via its REST API (4,500+ public studies), querying metabolites, RefMet standardized nomenclature, MS/NMR data, m/z mass searches, and study metadata. Use when retrieving public metabolomics study data, standardizing metabolite names with RefMet, running m/z lookups, or doing biomarker discovery. Part of the AlterLab Academic Skills suite.
Featurizes molecules for machine learning with molfeat — ECFP/MACCS/MAP4 fingerprints, RDKit and Mordred physicochemical descriptors, pharmacophore and shape descriptors, and pretrained embeddings (ChemBERTa, ChemGPT, CheMeleon) exposed as scikit-learn transformers that convert SMILES into feature vectors. Use when turning molecules into ML-ready feature matrices for QSAR/QSPR or virtual screening, or benchmarking fingerprint against descriptor and embedding representations; for training models and MoleculeNet benchmarks on those features prefer alterlab-deepchem, and for low-level fingerprint or descriptor primitives prefer alterlab-rdkit. Part of the AlterLab Academic Skills suite.
Creates, analyzes, and visualizes complex networks and graphs in Python with NetworkX. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing topologies — applicable to social, biological, transportation, citation, and any pairwise-relationship networks. This is classical graph analytics, not deep learning — for training graph neural networks (GCN/message passing, node/edge/graph classification on Cora-style data) use alterlab-torch-geometric instead. Part of the AlterLab Academic Skills suite.
Analyze Neuropixels 1.0/2.0 extracellular electrophysiology with SpikeInterface — load SpikeGLX/Open Ephys recordings, preprocess and motion-correct, run Kilosort4 spike sorting, compute quality metrics, apply Allen/IBL curation, and do AI-assisted visual inspection. Use when working with neural recordings, spike sorting, or extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation. Part of the AlterLab Academic Skills suite.
Run full computational-pathology workflows with PathML — whole-slide-image (WSI) analysis across 160+ slide formats, multiplexed immunofluorescence (CODEX, Vectra, MERFISH), nucleus segmentation/classification (HoVer-Net, HACTNet), tissue- and cell-graph construction, HDF5 dataset management, and deep-learning model training on pathology data. Use when the user builds end-to-end deep-learning pathology pipelines, analyzes multiplexed or spatial-proteomics slides, or segments nuclei. For lightweight H&E slide preprocessing, tissue masking, or plain Random/Grid/Score tile extraction prefer alterlab-histolab instead. Part of the AlterLab Academic Skills suite.
Trains and differentiates quantum circuits with PennyLane, a hardware-agnostic quantum machine-learning framework with automatic differentiation and PyTorch/JAX integration. Use when training quantum circuits via gradients (parameter-shift, backprop, adjoint), building hybrid quantum-classical models or quantum neural networks, or running differentiable variational algorithms (VQE, QAOA). For IBM Quantum hardware and Qiskit Runtime prefer alterlab-qiskit; for Google Quantum AI or NISQ circuits prefer alterlab-cirq; for open-system Lindblad/master-equation dynamics prefer alterlab-qutip. Part of the AlterLab Academic Skills suite.
Bayesian modeling and probabilistic programming with PyMC 6 and ArviZ 1.x — hierarchical models, MCMC (NUTS via PyMC, nutpie, NumPyro, or BlackJAX), variational inference, PSIS-LOO model comparison, and prior/posterior predictive checks. Use when fitting Bayesian or hierarchical models, estimating posteriors and credible intervals, diagnosing divergences, R-hat, or ESS, running probabilistic inference, or comparing models with LOO (WAIC was removed from ArviZ 1.x). Part of the AlterLab Academic Skills suite.
Read and write genomic alignment and variant files in Python with pysam (htslib bindings) — SAM/BAM/CRAM alignments, VCF/BCF variants, and FASTA/FASTQ sequences, plus region extraction and per-base coverage/pileup. Use when scripting NGS data-processing pipelines that parse, filter, index, or compute coverage over BAM/CRAM/VCF files. Part of the AlterLab Academic Skills suite.
Provides the RDKit cheminformatics toolkit for low-level, fine-grained molecular primitives — SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure/SMARTS search, 2D/3D coordinate generation, similarity, and reaction handling. Use when custom sanitization, specialized fingerprint or descriptor algorithms, reaction enumeration, or conformer generation demand direct API control; for a high-level pandas-friendly wrapper over RDKit prefer alterlab-datamol, and for turning molecules into ML feature vectors prefer alterlab-molfeat. Part of the AlterLab Academic Skills suite.
Orchestrates the full academic research pipeline (research, write, integrity check, review, revise, re-review, re-revise, final integrity check, finalize), coordinating alterlab-deep-research, alterlab-paper-writer, and alterlab-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Use when the request mentions academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, or complete paper workflow. Part of the AlterLab Academic Skills suite.
Run the standard single-cell RNA-seq analysis pipeline with Scanpy on AnnData — QC filtering, normalization, dimensionality reduction (PCA, UMAP, t-SNE), Leiden/Louvain clustering, marker/differential expression, PAGA trajectories, and plotting. Use when analyzing scRNA-seq data through clustering, cell-type annotation, DE, or pseudotime workflows; for building or reading the .h5ad data structure itself (layers, obs/var, concatenation, backed mode) prefer alterlab-anndata instead, and for RNA velocity from spliced/unspliced counts prefer alterlab-scvelo instead. Part of the AlterLab Academic Skills suite.
Run RNA velocity analysis with scVelo on single-cell RNA-seq data — estimate cell-state transitions from spliced/unspliced mRNA dynamics, infer trajectory direction, compute latent time, and identify driver genes. Use when adding directionality to trajectories or studying differentiation dynamics from spliced/unspliced layers (velocyto/STARsolo output); for the general QC, clustering, UMAP, and differential-expression analysis pipeline prefer alterlab-scanpy instead, and for .h5ad data-structure I/O and layer wrangling prefer alterlab-anndata instead. Part of the AlterLab Academic Skills suite.
Trains single-agent reinforcement learning agents with Stable-Baselines3 — PPO, SAC, DQN, TD3, DDPG, and A2C behind a scikit-learn-like API. Use for standard single-agent RL experiments, quick prototyping, well-documented algorithm implementations on Gymnasium environments, or adding callbacks and evaluation. For high-throughput parallel training, multi-agent systems, or custom vectorized environments prefer alterlab-pufferlib. Part of the AlterLab Academic Skills suite.
Query the STRING API for protein-protein interactions (59M proteins, 20B+ interactions across 12,500+ organisms), building interaction networks, discovering functional partners, and running GO/KEGG/Pfam enrichment on protein lists. Use when constructing a protein-protein interaction network, expanding from seed proteins to functional partners, or running PPI-based enrichment for systems biology; for curated metabolic pathway maps and reactions prefer alterlab-kegg, and for protein sequences, annotations, or accession ID mapping prefer alterlab-uniprot instead. Part of the AlterLab Academic Skills suite.
Forecasts time series zero-shot with Google's TimesFM foundation models — TimesFM 2.5 (200M, Apache-2.0 weights; ForecastConfig API, XReg covariates) and TimesFM 3.0 (~330M, multivariate with native past/future covariates; non-commercial weights) — producing point forecasts and quantile prediction intervals from CSV/DataFrame/array inputs, with a preflight system checker for RAM/GPU. Use when forecasting univariate or multivariate series (sales, sensors, energy, vitals, weather) without training a custom model, batch-forecasting many series, or flagging anomalies against forecast intervals. Part of the AlterLab Academic Skills suite.
Builds PyTorch-native graph neural networks with TorchDrug for molecules and proteins, exposing custom GNN architectures, task/dataset abstractions, molecular generation, retrosynthesis planning, and knowledge-graph reasoning. Use when a project specifically needs TorchDrug's datasets and tasks — GearNet protein-structure models, center-identification/synthon-completion retrosynthesis, or Hetionet knowledge-graph baselines. TorchDrug has had no release since 0.2.1 (July 2023) and needs Python < 3.11, so for new custom GNN work prefer alterlab-torch-geometric, and for ready-made featurizers, MoleculeNet benchmarks, and pre-trained models prefer alterlab-deepchem. Part of the AlterLab Academic Skills suite.
Loads, runs, and fine-tunes pretrained models with Hugging Face Transformers v5 (PyTorch-only) — pipeline() inference for chat-model text generation, text classification, NER, zero-shot, speech recognition, image classification, object detection, and image-text-to-text VLMs; AutoModel/AutoTokenizer loading with dtype, device_map and bitsandbytes quantization; generate() decoding control; and Trainer fine-tuning with optional PEFT/LoRA. Use when running inference with a Hugging Face Hub checkpoint, fine-tuning BERT/ModernBERT/Qwen-style models on a custom labelled dataset, controlling generation (sampling, beam search, streaming, chat templates), or porting v4 code (torch_dtype, removed summarization/translation/QA pipelines, TF/Flax) to v5. Part of the AlterLab Academic Skills suite.
Generates concise (3-4 page), focused medical treatment plans in LaTeX/PDF format across all clinical specialties — general medical treatment, rehabilitation therapy, mental health care, chronic disease management, perioperative care, and pain management — using SMART goal frameworks, evidence-based interventions with minimal citations, HIPAA compliance, and professional formatting. Use when drafting a brief, actionable patient treatment or care plan with measurable SMART goals and structured follow-up for any specialty. Part of the AlterLab Academic Skills suite.
Nonlinear dimensionality reduction with UMAP — fast manifold learning for 2D/3D visualization, clustering preprocessing (e.g., HDBSCAN), and supervised or parametric UMAP. Use when projecting high-dimensional data to low dimensions for visualization, embedding generation, or as a preprocessing step before clustering. Part of the AlterLab Academic Skills suite.
Provide direct REST API access to UniProt (Swiss-Prot/TrEMBL) for protein sequence searches, FASTA retrieval, functional annotations (GO terms, domains), and cross-database ID mapping. Use when looking up a protein entry, fetching a protein FASTA sequence, or mapping accessions between databases over raw HTTP/REST; for EXPERIMENTAL 3D structures prefer alterlab-pdb, for AI-PREDICTED 3D structures prefer alterlab-alphafold-db, for protein-protein interaction networks prefer alterlab-string-db, and for Python workflows spanning many databases prefer alterlab-bioservices instead. Part of the AlterLab Academic Skills suite.
Queries the U.S. Treasury Fiscal Data API across 50+ datasets and roughly 180 data tables (no API key required) for federal financial data on national debt, government spending, revenue, interest rates, exchange rates, and savings bonds. Use when working with U.S. federal fiscal data, national debt tracking (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates on Treasury securities, foreign exchange rates, savings bonds, or any U.S. government financial statistics. Part of the AlterLab Academic Skills suite.
Access USPTO patent and trademark data through the Open Data Portal (ODP) APIs — Patent File Wrapper search, examination history (the PEDS successor), continuity, assignments, office actions, PTAB decisions — and trademark status via TSDR. Use when searching patents or trademarks, conducting prior art searches, retrieving patent examination or assignment records, or doing intellectual property (IP) analysis. Part of the AlterLab Academic Skills suite.
Access the ZINC database of 230M+ commercially available (purchasable) compounds, searching by ZINC ID or SMILES, running similarity searches, and downloading 3D-ready structures. Use when assembling a compound library for virtual screening, finding purchasable analogs, or obtaining docking-ready 3D structures for drug discovery. Part of the AlterLab Academic Skills suite.
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," or "tracking plan." For A/B test measurement, see ab-test-setup.
Set up, audit, and debug analytics tracking implementation — GA4, Google Tag Manager, event taxonomy, conversion tracking, and data quality. Use when building a tracking plan from scratch, auditing existing analytics for gaps or errors, debugging missing events, or setting up GTM. Trigger keywords: GA4 setup, Google Tag Manager, GTM, event tracking, analytics implementation, conversion tracking, tracking plan, event taxonomy, custom dimensions, UTM tracking, analytics audit, missing events, tracking broken. NOT for analyzing marketing campaign data — use campaign-analytics for that. NOT for BI dashboards — use product-analytics for in-product event analysis.
Reverse engineer compiled binaries, firmware, and mobile app packages using triage, static disassembly, decompilation, and dynamic instrumentation. Use when analyzing an executable, ELF/PE/Mach-O file, firmware image, or stripped binary, recovering an algorithm or protocol, or working a CTF reversing challenge.
Provides comprehensive guidance for Angular framework including components, modules, services, dependency injection, routing, forms, and TypeScript integration. Use when the user asks about Angular, needs to create Angular applications, implement Angular components, or work with Angular features.
Detect, review, prevent, and remove AI-generated UI convergence patterns ("AI slop") in frontend code. Use whenever building or styling a UI, reviewing frontend changes, refining visual design, or when the user asks to remove the AI look, make an interface feel human-designed, polish a page, audit UI quality, or explain why a design feels generic. Covers HTML, CSS, JSX/TSX, Vue, Svelte, and Tailwind; audits 46 catalogued patterns plus composition-level checks, separates source-confirmed, rendered, and judgment-based evidence, and rewrites authorized code toward a product-specific design direction without requiring external dependencies.
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
Use when deciding HOW an Apple-style interface should BEHAVE — the functional UX/interaction logic, not the looks. Navigation-model decisions (push vs sheet vs modal vs tab vs popover vs split-view vs full-screen, back behavior, deep-linking, state restoration), state & feedback behavior (loading/skeleton timing, empty/error/disabled states, optimistic UI, pull-to-refresh, pagination), perceived-performance rules (latency thresholds, instant feedback, prefetch, progressive loading), input/focus/keyboard/pointer handling + hit-target affordances, and scroll-as-input decisions (when cinematic scroll helps vs hurts, scroll affordance, momentum, inertia, scroll-jacking prohibition, scroll-driven UX decision). Part of the apple-design family. Keywords: navigation model, push pop, sheet vs modal, tab bar, back behavior, deep link, state restoration, loading state, skeleton, empty state, optimistic UI, pull to refresh, perceived performance, latency threshold, prefetch, focus order, keyboard navigation, hit target, affordance, pointer vs touch, scroll as input, scroll affordance, momentum, inertia, scroll-jacking, when cinematic scroll, scroll-driven UX decision.
Define a professor's recent and trending research direction from publications, lab pages, grants, talks, students, and public materials before writing PhD application fit notes or cold emails. Use this skill whenever the user asks what a professor is working on now, whether a faculty member's research is shifting, how to infer current interests from recent papers, how to prepare for contacting a professor, or how to turn scattered professor evidence into application-ready research-fit angles.
Use when recording an architectural decision so future maintainers know why—phrases like "ADR", "architecture decision record", "why did we pick X", "lightweight architecture documentation", "decision log", "should this be an ADR", "tribal knowledge", "we chose this two years ago and now nobody remembers why". Defines an ADR as a short, structured document capturing what was decided, why, alternatives considered, and consequences—written at the time of the decision and kept in the repo
Use when protecting a service from a degraded or failing dependency—phrases like "circuit breaker", "bulkhead", "retry policy", "exponential backoff", "fail fast", "fallback", "cascade failure", "open/closed/half-open state", "resilience4j", "Polly", "Hystrix". Defines the circuit breaker pattern and related failure-isolation tools (bulkhead, retry-with-backoff, timeout, fallback)
Use when separating read and write models — phrases like "CQRS", "Command Query Responsibility Segregation", "read model vs write model", "denormalized read side", "materialized view", "different scaling for reads and writes", "command bus", "query bus", "should we use CQRS here". Defines CQRS as keeping reads and writes on separate models, with picking criteria that resist over-application.
Use when designing a system around asynchronous events—phrases like "event-driven architecture", "EDA", "event broker", "Kafka", "publish-subscribe at scale", "event-first design", "choreography vs orchestration", "event broker vs message queue", "broker topology vs mediator topology". Defines event-driven as a macro architectural style where components emit and react to events, not direct calls
Use when persisting state as a sequence of events—phrases like "event sourcing", "event store", "append-only log of facts", "replay events to rebuild state", "audit log as source of truth", "temporal queries", "snapshot", "should we event-source this aggregate". Defines event sourcing as storing the history of what happened as the canonical state, with current state derived by replay
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.