Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Create, analyze, and visualize complex networks and graphs in Python with NetworkX. Use when working with network/graph data structures, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks (random, scale-free, small-world), reading/writing graph file formats, or drawing network topologies. Common applications include social, biological, transportation, and citation networks.
Design and audit offline sync, queued mutations, reconnect behavior, conflict resolution, local-first UX, draft persistence, tombstones, attachment sync, optimistic updates, multi-device edits, merge policies, data-loss recovery, and sync observability. Use when mobile, desktop, PWA, field, creator, or collaboration products must keep working without reliable connectivity.
Use this skill when the user asks for: the price of any asset, ticker, order book, candles, OHLCV, funding rate, open interest, OI change scanner, market screener (top movers, high-volume, newly listed), mark price, index price, recent trades, instrument list, stock tokens, metals prices (gold, XAU, XAG), commodities (oil, OIL), forex rates (EUR/USD, EURUSDT), bond instruments, non-crypto assets, or any technical indicator query (RSI, MACD, EMA, Bollinger Bands, KDJ, SuperTrend, AHR999, BTC rainbow, and 70+ more). All commands are read-only and do NOT require API credentials. Do NOT use for account balance/positions (okx-cex-portfolio), placing/cancelling orders (okx-cex-trade), or bots (okx-cex-bot). Do NOT use when the user wants to TRADE a directional view as an event contract — that is okx-cex-trade. Merely ASKING which way an asset's price is moving is a market-data question and belongs here.
'Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals are homozygous-reference at a position, which variants exist in the dataset or carried by specified individuals in a gene or region, the relatedness between two specified individuals. Variants are returned with 1000 Genomes allele frequencies (AF), gnomAD v4.1 exome and genome AF, AlphaMissense score, and HGVSp annotations.
Resolve free-text scientific labels to ontology term IDs and validate existing CURIEs against the EBI Ontology Lookup Service (OLS4). Also look up prefixes in Bioregistry, resolve compact identifiers via Identifiers.org, map lab shorthand with ZOOMA, and build Ontobee term pages. Use whenever an ontology identifier must be produced or checked - annotating tissue, cell type, disease, phenotype, assay, chemical, organism, sex, or developmental stage fields; preparing metadata for GEO, ENA, BioSamples, CELLxGENE, HCA, or ISA-Tab submission; auditing a metadata table of term IDs; checking whether a term is obsolete and what replaced it; or deciding HPO vs HP. Triggers include "ontology term", "ontology ID", "CURIE", "controlled vocabulary", "UBERON", "CL:", "MONDO", "HPO", "EFO", "ChEBI", "NCBITaxon", "GO term", "PATO", "Zooma", "Bioregistry", "Identifiers.org", "Ontobee", "annotate this tissue/cell type/disease", and any request to emit or verify an identifier shaped like PREFIX:0001234.
Classifies an opposing player, manager, or agent into one of a configurable archetype set using Bayesian inference over observed behavior (roster composition, transaction pattern, lineup moves, trade activity). Domain-neutral scaffold -- callers supply the archetype taxonomy (names, priors, characteristic feature distributions) and observed features; the skill returns a normalized posterior, MAP archetype, classification confidence, feature-contribution breakdown, and best-response hints. Use when modeling opponents, classifying player types, performing Bayesian archetype inference, producing opponent posteriors, or when user mentions opponent archetype, classify opponent, Bayesian archetype inference, player type classification, opponent modeling, or archetype posterior.
Guides use of Pinecone, a managed serverless vector database, through its Python client and the LangChain and LlamaIndex integrations. Covers creating indexes, upserting and querying vectors, metadata filtering, namespaces, hybrid dense and sparse search, index management, and deleting vectors. Use when building a production RAG system on a hosted vector store, adding semantic search or recommendations without running infrastructure, isolating per-user or per-tenant data with namespaces, combining dense and sparse vectors in one query, or filtering results by metadata. Do not use for self-hosted or local stores (Chroma, Weaviate) or offline similarity search (FAISS).
Build multimodal AI apps with Pixeltable. One application file (app.py) declares TableModel tables and FastAPIRouter routes. Create tables with pxt schema update. Start HTTP with pxt service update. Insert a row or POST to try the app. Use computed columns instead of LangChain, pandas-as-store, or a separate vector DB. Use when building RAG or tool-calling agents, processing images/video/audio/documents, or serving an API. Do NOT use for general Python or direct PostgreSQL administration.
High-performance DataFrame library for Python ETL, analytics, and pandas migration. Use for expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.
Tell it what your product is (URL or description) and it finds 5 competitors globally, fetches their actual pricing pages, extracts every tier and price point, and returns a complete pricing intelligence report: the dominant pricing model in your space, a benchmark price table, feature gate analysis, competitive positioning map, and a concrete recommended pricing strategy for your product. Use when asked to research competitor pricing, find pricing benchmarks, decide how to price a product, understand pricing models in a space, or build a pricing strategy.
Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Use when adapting Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or working with the redesigned native 4.0 source line.
Builds, fits, checks, and compares Bayesian models in Python with PyMC and ArviZ. Covers hierarchical (multilevel) models, NUTS MCMC sampling, variational inference (ADVI), prior and posterior predictive checks, convergence diagnostics (R-hat, ESS, divergences), and LOO/WAIC model comparison. Use when writing a PyMC model for regression, count, or binary data. Use when fitting a hierarchical model with partial pooling. Use when diagnosing divergences, low ESS, or high R-hat. Use when comparing candidate models with LOO. Use when choosing priors or running prior predictive checks. Not for non-Bayesian regression; use statsmodels or scikit-learn instead.
Uses the PyTDC package (import tdc, Therapeutics Data Commons) to discover therapeutic ML tasks from tdc.metadata, plan and load approved datasets, apply task-aware splits (random, scaffold, cold_split, combination, time), run evaluator metrics, evaluate benchmark groups such as admet_group, and run bounded molecular-oracle scoring. Use when selecting a TDC task or dataset, planning a download-free split, scoring predictions with TDC evaluators, running a benchmark group evaluation, or checking dataset licenses and cache effects before downloading. Use when scoring molecules with TDC oracles like QED. Not for generic RDKit cheminformatics or training molecule generators.
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
Multivariate severity assessment and humane endpoint prediction for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast forecasting. Use when combining welfare readouts — body weight or weight loss, body temperature, clinical or nesting scores, biomarkers, activity, heart rate, burrowing, wheel running — into one severity score per animal per day, when asking which animals are at risk of reaching a humane endpoint or when one will be reached, when defining attention/danger zones or thresholds on a severity scale by kernel density estimation, or when reporting severity for a 3Rs, refinement, animal-welfare, or EU Directive 2010/63/EU severity-assessment context. Covers directionality ("turned" variables), baseline normalization, reference sets, RELSA weights, ARIMA prediction intervals, and RMSE/PICP/MPIW evaluation.
Builds the "RHDH CVE Management - <version>-plugins.csv" export by walking `rhdh-plugin-export-overlays` git history on a release branch since a revision, scoped to generally-available plugin workspaces, then enriching each CVE from Jira RHIDP, RHDHBUGS, and RHDHPLAN. Use for "generate the plugin overlay CVE CSV for 1.10.3", "what CVEs were fixed in plugins since 1.10.2", or "rebuild the plugin CVE list with the ProdSec CVSS scores".
Extract anonymized frame-by-frame body and hand trajectories from an authorized reference video, with skeleton previews, confidence evidence, and machine-readable keypoints. Use when the user asks to 提取博主动作, 提取人体动作轨迹, 做姿态参考, 生成骨架视频, or prepare motion control data for an avatar; do not route graphic-animation replication here.
Skrapp.io platform help — B2B email finder and datan enrichment with 200M+ contacts and 40M+ company profiles. Use when you can't find a prospect's email, LinkedIn profiles don't show contact info, your CSV of leads is missing emails and firmographics, email verification is bouncing too many contacts, the Chrome extension isn't pulling data from LinkedIn, or the Skrapp API isn't returning results. Do NOT use for general enrichment strategy (use /sales-enrich), deliverability/warmup (use /sales-deliverability), or building prospect lists strategy (use /sales-prospect-list).
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.
Answer business questions about the org's RevOS data directly in chat by querying its live semantic model over MCP — "how many orders…", "revenue by…", "top N…", "trend over time…", "compare X to Y…" — and schema-discovery questions like "what's in my semantic model", "what can I query", "list cubes/datasets/fields", "describe a cube" — or when explicitly asked to "query the semantic model", "run a cube query", "show me a chart", "plot…", "graph…". Use this whenever you would otherwise call the RevOS api_read tool against the `cubes` resource directly — this skill is what turns its raw JSON into a rendered table, a chart when the shape fits, a safe choice of join path when a query spans multiple cubes, and a plain-English explanation, instead of a dumped tool result. This applies even when the question names a specific source system (HubSpot, Zammad, Exact Online, …) — answer aggregate/analytical questions from the semantic model, not a direct source connector.
Generates sentence, text, and image embeddings locally with the Python sentence-transformers (SBERT) library, using pre-trained Hugging Face models such as all-MiniLM-L6-v2, all-mpnet-base-v2, and multilingual variants. Covers encoding, cosine similarity, semantic search, batch encoding, fine-tuning, and LangChain/LlamaIndex integration. Use when building embeddings for RAG, running semantic search or similarity scoring, clustering or classifying text, embedding multilingual text without an API, or fine-tuning an embedding model on domain data. For API-based or managed embeddings, use OpenAI or Cohere Embed instead.
When the user wants to solve set covering problems, determine minimum coverage sets, or optimize facility coverage. Also use when the user mentions "set cover," "minimum set cover," "coverage optimization," "facility coverage problem," "service coverage," "location set covering," "maximal covering location problem," or "covering design." For general facility location, see facility-location-problem. For specific applications, see warehouse-location-optimization or hub-location-problem.
Builds, tests, and analyzes bounded process-based discrete-event simulations in Python with SimPy 4.1.2: Environment, Timeout, Process, AnyOf/AllOf conditions, interrupts, Resource, PriorityResource, PreemptiveResource, Container, Store, time-weighted monitoring, and replication-based output analysis, plus bundled safe CLIs. Use when modeling queues, production lines, logistics, or service operations with generator processes; when contending entities need shared resources or preemption; when instrumenting queue length or utilization correctly; when running independent replications with seeds and confidence intervals; when debugging event ordering or run(until=) boundaries. Not for continuous-time ODE or agent-based modeling frameworks.
@DataJpaTest requires TestEntityManager + flush()/clear() before assertions — without this, tests read from Hibernate L1 cache and pass falsely. Read before writing any JPA test. Triggers: @DataJpaTest, JpaRepository, TestEntityManager, @ServiceConnection, Testcontainers, @Modifying, Hibernate 6/7, @AutoConfigureTestDatabase, flush and clear in tests, @Transactional in tests, jakarta.persistence.EntityManager.
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
Build, review, debug, migrate, or plan TanStack Charts Alpha (0.18.x) charting with current docs. Use for @tanstack/charts, @tanstack/charts/react, @tanstack/charts/react-native, @tanstack/charts/scales/*, defineChart, scales registry (scales.x/scales.y, named scales, multiple axes), svgAnimation, motion(), tooltip/portal, layout stack/group, groupBy/binX/rollingWindow/rank/normalize/fold/waterfall/mosaic, lineY, areaY, barY (corner radius), boxY, violinY, waffleY, ridgelineY, differenceY, linearRegressionY, rect, cell, dot, hexagon, crosshair, whenFocused, decorative, facet, polar, geoShape, treemap, sunburst, sankeyDiagram, hexbin, contour, brushX, zoomX, keyedSelection, colorLegendItems, gradients, focusRing, Chart, Canvas, canvasChartRenderer, grammar-of-graphics marks/channels/scales, and migrations from Recharts, Chart.js, ECharts, Observable Plot, archived react-charts, @tanstack/react-charts, @tanstack/charts-scales, or pre-Alpha TanStack Charts 0.0.x–0.15.x (root x/y scales).
Logs and views ML training data in TensorBoard using PyTorch SummaryWriter and TensorFlow/Keras callbacks: scalars, images, text, histograms, model graphs, embedding projector, hyperparameter tables, PR curves, and TensorFlow or PyTorch profiler traces. Use when plotting loss and accuracy curves during training, comparing multiple runs in one dashboard, inspecting weight and gradient distributions, projecting embeddings with PCA or t-SNE, tracking hyperparameter experiments, or finding performance bottlenecks in a training loop. Not for hosted experiment tracking with team collaboration; use a dedicated tracking service for that.
Use when coding cross-source evidence with Word-of-Mouth Motivation Theory to classify altruistic, social identity, self-enhancement, and emotional expression motives, and when optionally exporting theory_annotations compatible with review-mining-stp.
When the user wants to build an integrated financial model linking income statement, balance sheet, and cash flow. Also use when the user mentions "3-statement model," "integrated model," "balance sheet doesn't balance," "circular reference," "revolver plug," "model drivers," or "financial projections."
Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.
PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.
Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library.
Reduces and embeds high-dimensional data with umap-learn (UMAP) in Python, including 2D/3D visualization, supervised and semi-supervised UMAP, DensMAP, AlignedUMAP, Parametric UMAP (Keras), transform() on new data, and inverse transforms. Use when visualizing high-dimensional data as a 2D or 3D embedding, preprocessing features for HDBSCAN clustering, using partial labels to guide an embedding, aligning embeddings across time points or batches, or projecting unseen samples into a trained embedding. Tune n_neighbors, min_dist, n_components, and metric. Not for linear PCA or t-SNE-specific workflows.
Query the U.S. Treasury Fiscal Data REST API for federal financial data. No API key required. Use for national debt (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates, foreign exchange rates, savings bonds, or U.S. government revenue and spending statistics.
Processes and analyzes tabular datasets too large for RAM using Vaex, a Python library for lazy, out-of-core DataFrames over memory-mapped HDF5 and Arrow files, with CSV and Parquet import/export. Covers virtual columns, filtering, groupby aggregations, large-data heatmaps and histograms, and vaex-ml transformers, PCA, and K-means. Use when opening or converting multi-gigabyte CSV/HDF5/Arrow/Parquet files, computing fast statistics on billions of rows, visualizing massive datasets, building ML pipelines that do not fit in memory, or speeding up slow aggregations with lazy evaluation and delay=True. Prefer polars when data fits in RAM, or dask for cluster-distributed work.
Run a standalone Xiaohongshu data workflow with bundled JS signing and Cookie/QR code login, for login, search, extraction, export, and creator data collection; use when you need to reliably reuse Spider_XHS core capabilities without the original repository, or when the user explicitly asks to download Xiaohongshu images, videos, or media files and the workflow should default to the no-watermark download path. Use this skill to run a standalone Xiaohongshu workflow with bundled JS signing assets and cookie or QR login for authentication, plus search, extraction, export, and creator data collection when you need Spider_XHS-derived capabilities without depending on the original repository, especially when the user asks to download XHS images, videos, or media files and the workflow should default to no-watermark downloads.
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.