Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Production Ray (open-source, pinned to 2.57) for classic-ML workloads from training to serving — Ray Train, Tune, Data, Serve, Core, and cluster deployment on KubeRay. Corrects the older-corpus defaults a model reaches for (ray.air session reporting, Trainer-inside-Tuner, tune.run, map_batches concurrency=, DatasetPipeline/to_torch, max_concurrent_queries, RayServeHandle + ray.get, Deployment.deploy, ray.state, ray.get-in-a-loop) with the 2.57 idioms that replaced them (Train V2 defaults, driver-function tuning, compute strategies, streaming datasets, DeploymentHandle/DeploymentResponse, serve build/deploy, ray.util.state, KubeRay CRDs and Jobs API). Use when writing, reviewing, or productionizing Python code that touches Ray distributed training, data pipelines, hyperparameter tuning, model serving, or Ray cluster operations. LLM serving/batch-inference on Ray lives in the sibling ray-llm skill.
Use this skill to analyze product reviews, find common issues, and prioritize improvements. Triggers: "analyze reviews", "review analysis", "customer feedback", "what are people saying", "product reviews", "review sentiment", "find complaints", "customer complaints", "improvement recommendations", "voice of customer", "VOC analysis", "feedback analysis" Outputs: Prioritized issues, sentiment analysis, improvement recommendations.
Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggregate findings", "deduplicate alerts", or "process sarif output". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does NOT run scans — use the Semgrep or CodeQL skills for that.
Use when the user wants to retrieve Twilio SendGrid global email statistics with GET /v3/stats. Supports start/end date ranges, day/week/month aggregation, limit/offset pagination, parent-account on-behalf-of lookups for subusers or customer accounts, global or EU SendGrid API base URLs, dry-run URL preview, and saved SendGrid API key reuse. Do not use for sending email or Email Logs status lookup.
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.
For searching financial markets, securities, listed-company fundamentals, prices, candlestick charts, disclosure filings, financial news, A-share data, Hong Kong stocks, or global tickers, using yfinance, mootdx, API scripts, or browser-use.
Use when researching China market, industry, macro, trade, procurement, listed-company disclosure, regulation, IP, healthcare, logistics, energy, environment, or industrial-operation information using free official sources with no registration, no API key, and no cryptocurrency data.
Use this skill when the user asks about Goldsky Subgraphs — deploying, managing, or querying subgraphs. Triggers on: 'deploy a subgraph', 'migrate from The Graph', 'what is a subgraph', 'GraphQL endpoint', 'low-code or no-code subgraph', 'subgraph tags', 'subgraph webhooks', 'cross-chain subgraph', 'subgraph stalled', 'subgraph API key', 'init subgraph', 'scaffold subgraph', 'subgraph logs', 'pause subgraph', 'start subgraph', 'graft subgraph'. Also use this skill when the user wants to build a GraphQL API over onchain data, power a dApp frontend with indexed blockchain data, or reuse an existing TheGraph subgraph on Goldsky. For questions about streaming raw chain data directly to a database without GraphQL, use the turbo-builder or mirror skills instead.
Implement Syncfusion WinUI Circular Charts (SfCircularChart) with pie and doughnut visualizations for proportional data display. Use this when working with circular charts, pie charts, or doughnut charts in WinUI applications. This skill covers chart series configuration, data labels, legends, tooltips, segment selection, exploding segments, and visual customization for interactive circular visualizations.
Implements Syncfusion WinUI Linear Gauge (SfLinearGauge) control for data visualization in desktop applications. Use this when building progress indicators, temperature displays, or data measurement gauges in WinUI. This skill covers axis configuration, pointer types (bar and shape), range customization, and animation.
Implement Syncfusion WinUI Pyramid Charts (SfPyramidChart) for visualizing hierarchical proportional data. Use this when working with pyramid charts, hierarchical visualization, or proportional data display in WinUI applications. This skill covers data binding, legend configuration, exploding segments, tooltips, data labels, selection interactions, and custom styling with palettes and gradients.
Create an Extruct company table from user-provided data, upload rows, and optionally add enrichment columns. Handles the full flow: parse input (CSV, pasted list, or structured data), create or reuse a table, upload domains in batches, add agent columns, and trigger enrichment. Triggers on: "create table", "upload companies", "add to extruct", "new extruct table", "import companies", "upload list to extruct".
When the user wants to optimize task assignments, match workers to jobs, or solve assignment problems. Also use when the user mentions "Hungarian algorithm," "assignment optimization," "worker-task assignment," "job allocation," "resource assignment," or "matching problem." For workforce scheduling, see workforce-scheduling. For routing, see picker-routing-optimization.
Get Chinese financial market data (A-shares, Hong Kong stocks, US stocks, funds, futures, bonds). Supports 220+ Tushare Pro interfaces: stock quotes, financial statements, macroeconomic indicators. Use when the user requests stock price data, financial analysis, index quotes, or macroeconomic data such as GDP/CPI.
Provides comprehensive guidance for uCharts chart library including chart types, data formats, chart configuration, and platform support. Use when the user asks about uCharts, needs to create charts, configure chart options, or work with uCharts in applications.
UiPath IXP (Document Understanding) via `uip ixp` — create projects (with autopilot taxonomy suggestion, an imported taxonomy file, or empty), upload/download/delete documents, author the taxonomy (field groups, fields, data types, per-field and overall extraction instructions), configure the extraction model and pre-processing, review/confirm/unconfirm predictions, mark fields missing, pull metrics and model versions, publish/tag/roll back model versions, deploy a trained version to an Orchestrator folder and move an existing deployment to another version (`deployments create`/`upgrade`/`list`). DO NOT TRIGGER during .flow / Maestro Flow work — discovering or listing IxP / document-extraction models, extractors, or nodes available to Maestro Flow, and adding or wiring an IxP node, belong to uipath-maestro-flow even when they sound like IXP model management.
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that don't fit in memory.
Finds what over-performs in the creator's niche and writes it to video-agent/swipe.md. Use when the user asks what goes viral, viral hooks, what works in my niche, competitor research, swipe file, outliers, my best videos, my stats, or "find hooks that work". Scores recent Shorts from 10 to 12 accounts against each account's median (YouTube free with yt-dlp; TikTok, Instagram and their own stats through Treg), pulls the first 3 seconds of each outlier and tags the hook formula so video-script reuses the shape, never the words.
Use when working with GravityView or GravityKit products: creating Views to display Gravity Forms entries on the front-end, configuring search/sort/filter, entry approval workflows, edit-entry forms, role-based access, merge tags, shortcodes, or the GravityActions/GravityBoard extensions.
Use when working with the Pods Framework: creating or managing custom post types (CPTs), custom taxonomies, custom database tables (ACTs — Advanced Content Types), or custom fields via Pods. Critical for AI agents: always declare whether a Pod uses wp_postmeta or ACT storage before writing any DB queries, WP_Query, or pods_field() calls.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Use when Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc.), including: (1) creating new spreadsheets with formulas and formatting, (2) reading or analyzing data, (3) modifying existing spreadsheets while preserving formulas, (4) data analysis and visualization in spreadsheets, or (5) recalculating formulas
Batch download WeChat public-account article bodies, historical article lists, original-article filtering, historical count conventions, read counts, like/share metrics, comments and comment replies. Use when the user asks to batch fetch mp.weixin.qq.com articles, export WeChat public-account history, distinguish publish groups vs expanded article URLs vs original articles, use wechat-article-exporter, use wxdown-service credentials, collect read/comment metrics, or create an archive for Obsidian/Feishu/local analysis. Do not use for ordinary one-off article summarization unless batch/enhanced data is requested.
YouTube video comment analysis tool. Enter a video link to get comment data, with paging for further lookup and four-dimension sentiment analysis (positive / negative / needs / competitors), giving a quick full picture of user feedback under any video. Use when the user needs to view YouTube video comments, analyze a video's public sentiment, or understand user feedback. Trigger words: YouTube comments, comments, video comments, comment lookup, comment analysis, comment sentiment, read comments, youtube comments, YT comments.
Complete, populate and fill out 3-statement financial model templates (Income Statement, Balance Sheet, Cash Flow Statement). Use when asked to fill out model templates, complete existing model frameworks, populate financial models with data, complete a partially filled IS/BS/CF framework, or link integrated financial statements within an existing template structure. Triggers include requests to fill in, complete, or populate a 3-statement model template
This skill should be used when the user asks about "consumer insights", "audience research", "buyer personas", "customer journey mapping", "survey design", "focus group guide", "target audience analysis", "psychographics", "consumer behavior", "audience segmentation", "act as a consumer researcher", "consumer insight mode", "empathy mapping", "research debrief", "qualitative research", "quantitative research", "ethnography", "depth interviews", "laddering technique", "means-end chain", "consumer motivations", or needs expertise in understanding audiences through research methodologies and insight development. Part of the AlterLab FC Skills collection (Public Relations & Advertising department).
This skill should be used when the user asks about "interview methodology", "semi-structured interview", "interview guide", "interview questions", "probing techniques", "interview transcription", "interview analysis", "narrative analysis", "phenomenological analysis", "IPA", "interpretive phenomenological analysis", "focus group", "focus group facilitation", "participant recruitment", "informed consent", "qualitative interviewing", "act as an interview analyst", "interview analyst mode", "interview coding", "thematic analysis of interviews", "member checking", "theoretical saturation", "purposive sampling", "snowball sampling", "interview protocol", "research interviews", "Braun and Clarke", "grounded theory coding", "framework analysis", "Labov narrative", or needs expertise in qualitative interview design, facilitation, and systematic analysis. Part of the AlterLab FC Skills collection (Research Methods & Academic Writing department).
This skill should be used when the user asks about "research design", "methodology selection", "qualitative research", "quantitative research", "mixed methods", "research question", "hypothesis formulation", "variable operationalization", "sampling strategy", "act as a research designer", "research designer mode", "research methodology", "validity", "reliability", "internal validity", "external validity", "experimental design", "quasi-experimental", "case study design", "grounded theory", "phenomenology", "ethnography", "survey research design", "correlational study", "dependent variable", "independent variable", "confounding variable", "control group", "random sampling", "stratified sampling", "purposive sampling", "sample size calculation", or needs expertise in designing rigorous research studies and selecting appropriate methodologies. Part of the AlterLab FC Skills collection (Research Methods & Academic Writing department).
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
Edit features with the Editor component/widget, configure forms, manage subtypes, handle attachments, and work with branch versioning. Use when adding, updating, or deleting features, building edit forms, managing feature attachments, or working with versioned edits.
Computation and publication-grade plotting for atmospheric and climate research on local data files (NetCDF, GRIB, HDF5, Zarr; ERA5, CMIP, reanalysis). Use whenever the user works with gridded lat/lon or pressure-level data and needs diagnostics (climatology, anomalies, composites, regression/correlation, trends, EOF, extremes) or figures (Cartopy maps, cross-sections, time series), even if they do not say “paper figure”.
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.