Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
A Pythonic interface to the HDF5 binary data format. It allows you to store huge amounts of numerical data and easily manipulate that data from NumPy. Features a hierarchical structure similar to a file system. Use for storing datasets larger than RAM, organizing complex scientific data hierarchically, storing numerical arrays with high-speed random access, keeping metadata attached to data, sharing data between languages, and reading/writing large datasets in chunks.
DWS cluster high memory root cause diagnosis skill, based on KooCLI v3.2.0+ and DWS Autopilot MCP Server. Automatically collects memory metrics, analyzes root causes (customer-side / system-side), and outputs a standardized diagnosis report. Applicable to scenarios where DWS cluster memory usage is too high, memory alarms, and OOM. Trigger words: 内存高, 内存告警, 内存诊断, 内存使用率过高, 内存不足, OOM, 内存溢出, 动态内存使用率超阈值, high memory, memory alarm, memory diagnosis.
JimuReport generator — describe report requirements in natural language or provide a screenshot to automatically generate JimuReport reports (supporting all types: data reports, print reports, grouped reports, loop reports, data entry, and more). Use when the user says "积木报表", "jmreport", "Excel report", "data entry", "visual report", "print report", "grouped report", "loop report", "generate a report from a screenshot", "create a JimuReport", "make a visual report", "JimuReport designer", "create jimureport", "visual report". Also triggers when the user describes report requirements involving Excel-like layouts, data binding with #{}, or multi-sheet reports, or provides a screenshot to generate a report.
Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies
Top-level Lytics CDP agent - routes user intent to the appropriate skill for audience management, profile exploration, data integration, and schema browsing. Use when the user has a general Lytics question or request that doesn't clearly map to a specific skill.
Read or write data files in MATLAB. Use when the task involves tables, spreadsheets, delimited text, or structured files in CSV, Excel, Parquet, JSON, or XML format — including but not limited to importing, exporting, loading, parsing, converting, validating, configuring import options, reading from URLs, handling locales or encodings, diagnosing file errors, and modernizing legacy file I/O code. MATLAB provides built-in functions for these workflows with no additional products required.
Add SQLite local database storage to .NET MAUI apps using sqlite-net-pcl. Covers data models with ORM attributes, async database service with lazy init, DI registration, WAL mode, and file management. Works with any UI pattern (XAML/MVVM, C# Markup, MauiReactor). USE FOR: "SQLite database", "local database", "sqlite-net-pcl", "offline storage", "CRUD database", "database service", "WAL mode", "CreateTableAsync", "local data persistence", "ORM attributes". DO NOT USE FOR: REST API data fetching (use maui-rest-api), secure credential storage (use maui-secure-storage), or file picking (use maui-file-handling).
This skill should be used when the user asks to automate Azure ML and Azure Data Factory production workflows. PROACTIVELY activate for: (1) Azure ML code asset registration, azure-ai-ml SDK, AML code versions, `result.version`, requested-vs-actual versions, (2) ADF to Azure ML orchestration, ADF WebActivity, managed identity blob reads, `connectVia`, managed VNet IR, (3) code asset version pointer blobs, latest.json contracts, training/scoring code version propagation, (4) private storage firewalls, Microsoft-hosted CI agents, temporary network rules, storage data-plane smoke tests, (5) marshmallow<4 pinning, AML SDK import failures, runtime validation for Azure ML infrastructure. Provides: operationally safe Azure ML + ADF automation patterns.
A drawing tool supporting multiple chart types, including mind maps, flowcharts, data visualization charts, and mathematical function graphs; it can generate charts in formats such as Mermaid, ECharts, Mindmap, DrawIO, and GeoGebra according to user needs, and export them to PNG, SVG, HTML, and other formats
NetBox Branching plugin — create isolated branch schemas for safe change staging, review, and merge. Use when working with branch lifecycle, the X-NetBox-Branch header, async provisioning/sync/merge jobs, conflict resolution, or Change Request integration.
NetBox Data Exchange (NDX) — a curated catalog of infrastructure component metadata. The device/module/rack type definitions are open to the world (browse + manual YAML download); the "enrichment data" (lifecycle dates, thermal, environmental, operational, platform/NOS, observability protocol metadata) and the built-in NDX features in NetBox Cloud/Enterprise are commercial. Use when consuming enrichment data via the API, running EOL/lifecycle analyses, importing device types, or understanding how NDX data is structured.
Audit and review NetBox data model design choices. Use when evaluating site hierarchy, IPAM organization, device modeling, tenancy patterns, custom field vs tag decisions, naming conventions, and extensibility strategy. Identifies modeling anti-patterns and suggests improvements aligned with NetBox best practices.
Design ontologies and build knowledge graphs. Cover OWL/RDF ontologies, SKOS taxonomies, SPARQL querying, knowledge graph construction, semantic reasoning, and linked data patterns. Triggers on "build ontology", "design knowledge graph", "create taxonomy", "SPARQL query", "semantic reasoning", "linked data", "RDF modeling", "ontology alignment", or "knowledge representation".
Plan and execute ambiguous or multi-stage GIS work, jointly choosing authoritative sources, compute, storage and delivery for the scale and team. Covers vector/raster/point-cloud analysis, routing, QGIS, tiles and web maps. Use for unresolved geospatial architecture and end-to-end analysis; prefer installed geospatial-data-discovery, spatial-sql or reproducible-gis-project for their bounded tasks. Retains standalone GIS support when specialists are absent. Do not use for casual place lookups, ordinary travel directions or non-spatial coding
Guides engineers and QA professionals in interpreting performance test results, identifying bottlenecks, and producing two types of reports: a technical report (for engineers and QA) and a business report (for stakeholders and executives). Use this skill whenever the user shares load test results, CSV stats, HTML reports, percentile data, or test output from k6, Gatling, Locust, JMeter, Artillery, or any other tool — and wants to understand what the numbers mean, diagnose problems, or communicate findings. Trigger on phrases like "analyze my test results", "what do these numbers mean", "my p95 is high", "error rate under load", "write a performance report", "explain the results to my manager", "how do I present this to stakeholders", or "I found a bottleneck".
Prepare organized packages of project files for sharing at different levels - from summary PDFs to fully reproducible archives. Creates copies with cleaned notebooks, documentation, and appropriate file selection. After creating sharing package, all work continues in the main project directory.
Publish quantitative analysis or existing JPG/PNG, HTML, PDF as a Quant Buddy shareable live page or real-time dashboard, supporting creation, update, reuse, acceptance and public link delivery. Applies to pages such as single-stock profiles, valuation and financials, index moves, multi-factor screening, commodity daily reports, templates, sharing shells and cards. Also use when the user provides a QuantBuddy live page URL and asks for interpretation. When /quant-buddy-view, /qbv, qbv or QBV is explicitly invoked and the request is not purely consultation, code maintenance or documentation explanation, treat it by default as a shareable live page task. Inputs that uniquely identify an A-share name, short name or code, or a simple request for single-stock comprehensive analysis (such as "贵州茅台", "600519", "分析一下贵州茅台") all default to a single-stock quick page; first verify via QBS and reply with the complete single-stock analysis, then new_asset_page in the same round, without the user needing to add "generate a page". When a WebAgent host requires financial questions to deliver both Q&A and a live page uniformly, one-off quotes, price changes, valuation, concept explanations and colloquial status questions are also handed off to this skill after the first QBS answer. Without such a host agreement, one-off questions are answered by QBS; operations such as review, monitoring, charting, backtesting and K-line still default to live page intent. Do not create a page when the user explicitly does not want a web page or wants text only.
R visual creation and ggplot2 patterns for PBIR reports. Automatically invoke when the user mentions "R visual", "ggplot2", "ggplot in Power BI", or asks to "create an R visual", "add an R chart", "write an R visual script", "inject an R script into Power BI".
Use when building interactive 2D or 3D graph or network visualizations in React with the reagraph library (GraphCanvas, node-link diagrams, force-directed layouts). Covers data shapes (GraphNode, GraphEdge), 16 layout algorithms, selection, lasso, camera controls, sizing strategies, and theming.
Research analysis strategy planning assistant. Based on the user's research analysis needs, it surveys analysis methods from top journals and conference papers to formulate a personalized, actionable optimal analysis strategy. Suitable for scenarios that require designing experiments, data analysis workflows, or technical roadmaps; also triggers the prompt for the legacy name make-research-plan.
Structure a retention analysis, churn investigation, or engagement deep-dive for any product team. Use when asked to analyse user retention, investigate churn, measure DAU/MAU, or build a retention improvement plan. Produces a retention snapshot with root cause hypotheses, aha-moment correlation, and prioritised interventions.
Analyze and improve retention cohorts for SaaS, mobile apps, games, developer tools, marketplaces, subscriptions, content products, and communities including activation cohorts, D1/D7/D30, weekly/monthly retention, rolling retention, resurrection, churn, segment bias, lifecycle events, monetization impact, cohort dashboards, and experiment readouts. Use when retention looks weak, confusing, misleading, or needs an action plan.
RootData is a leading Web3 data platform covering crypto projects, investors, funding data, and personnel movements. This skill is the OKX-dedicated integration, isolated from the standard RootData skill with its own API key namespace and endpoints.
Machine learning in Python with scikit-learn. Use for supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
Analyze credential-free public website monitoring evidence from server access logs, HTTP fetches, robots/llms/sitemap checks, and exported summaries while protecting raw IP and private query data. Use this skill when the user asks whether crawlers or AI bots reached a site, whether public SEO/LLM discovery files respond, or how to separate observed facts from unknown Search Console, rank, analytics, or citation claims.
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.
Implement SPC charting, process capability analysis, and control chart interpretation. Covers control chart selection, capability indices, and out-of-control rules. USE WHEN user says 'SPC', 'Cpk', 'Ppk', 'control chart', 'process capability', 'X-bar R', 'statistical control', or 'out of control'. Integrates with ControlPlan, MSA, and AutomotiveManufacturing skills.
Diagnoses and optimizes SQL Server database performance. Use when diagnosing slow T-SQL queries, tuning indexes, reading execution plans, fixing parameter sniffing, optimizing batch operations, reducing transaction log bloat, troubleshooting locking and blocking, configuring tempdb, or when a query that used to be fast is now slow. Also use when writing high-throughput INSERT/UPDATE/DELETE operations, implementing minimal logging, designing covering indexes, or analyzing wait statistics.
General guide for using the sqlite3 CLI to build composable knowledge databases. Use this skill when creating SQLite databases, designing schemas, querying data, managing relationships, or building new sqlite-based domain skills. Provides the foundational patterns that all specialized sqlite skills build upon.
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.