Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Expert knowledge for Azure Data Share development, including troubleshooting, decision making, security, configuration, and deployment. Use when estimating Data Share costs, securing invitations, fixing share errors, configuring datasets, or deploying across regions, and other Azure Data Share related development tasks. Not for Azure Data Box (use azure-data-box-family), Azure Data Explorer (use azure-data-explorer), Azure Data Factory (use azure-data-factory), Azure Open Datasets (use azure-open-datasets).
Expert knowledge for Azure Oracle development, including troubleshooting, security, and integration and coding patterns. Use when configuring Oracle TDE with Azure Key Vault, Exadata log export, Azure Monitor, Sentinel, or PPGs, and for other Azure Oracle development tasks. Not for Azure SQL Database (use azure-sql-database), Azure SQL Managed Instance (use azure-sql-managed-instance), SQL Server on Azure Virtual Machines (use azure-sql-virtual-machines), or SAP HANA on Azure Large Instances (use azure-sap).
Expert knowledge for Microsoft Planetary Computer Pro development, including troubleshooting, decision-making, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when working with GeoCatalog or STAC APIs, configuring collections or tiles, securing access, integrating QGIS or ArcGIS, troubleshooting ingestion, and other Microsoft Planetary Computer Pro development tasks. Not for Azure Maps (use azure-maps), Azure Open Datasets (use azure-open-datasets), or Azure Data Explorer (use azure-data-explorer).
Audit React Doctor against ReactBench or similar diagnostic benchmark corpora for confirmed false positives, false negatives, taxonomy gaps, and verifier artifacts. Use when analyzing rd.log, rd-before.json, rd-after.json, model.patch, result.json, reward/test logs, rule distributions, or when asked to perform a second adversarial pass over React Doctor benchmark findings.
An automated data exploration and visualization tool offering a complete EDA solution, from data loading to professional report generation. Supports multiple chart types, intelligent data diagnostics, model evaluation, and HTML report generation. Suitable for data analysis projects in healthcare, finance, e-commerce, and other fields.
Use when auditing or recalibrating game balance: build a source-driven Monte Carlo balance lab (Rust + rayon) that extracts live game data, simulates human playstyles (AFK→pro), emits win-rate/economy verdicts with confidence intervals, and bruteforce-tunes parameters. Trigger on unfair levels, unreachable shops, farm exploits, interest-curve cliffs, post-content recalibration, or CI balance JSON diffs. Keywords: balance lab, Monte Carlo, win rate, difficulty curve, economy career, playstyle simulation, Resource extraction, GDScript parser, bruteforce tuning.
When the user wants help setting up or auditing Google Ads conversion tracking, Google Tag, Google Tag Manager, enhanced conversions, conversion actions, attribution models, cross-channel attribution, GA4 import, phone call tracking, or troubleshooting conversion data issues. Triggers on 'conversion tracking', 'Google tag', 'gtag', 'GTM', 'Tag Manager', 'conversion action', 'enhanced conversions', 'attribution model', 'conversion window', 'tracking not firing', 'missing conversions', 'GA4 import', or 'phone call tracking'. This skill is a prerequisite for google-ads-bidding Smart Bidding and google-ads-audiences remarketing.
A specialist skill for building pages and working with data using the Mingdao Cloud HAP V3 API. Trigger immediately when the user mentions “HAP V3,” “HAP API,” “API call,” “data API,” “Appkey,” “Sign,” “API authentication,” “PAT,” “OAuth,” “Bearer,” “Filter,” “query data,” or “create record.” Provides a complete API usage guide covering authentication setup, API calls, filters, and data operations. If the user has configured HAP MCP, the AI should automatically extract the authentication key from the MCP configuration.
Deeply analyze Amazon niche markets by keyword, covering monopoly level, brand concentration, new product success rate, and market opportunity scores. Trigger this skill when the user mentions niche market analysis, keyword market research, monopoly assessment, brand concentration analysis, new product success rate, market demand score, competitive landscape, Amazon submarket exploration, niche market analysis, keyword market, monopoly level, brand concentration, new product success rate, market opportunity score, competitive landscape, or Jiimore data. Trigger it even if the user does not explicitly mention "niche market," as long as their request involves evaluating Amazon market competition, brand density, or opportunity potential for a keyword.
Governs the on-device Drift/SQLite data layer: package:drift and package:sqlite3 confined to lib/data/ behind DAOs that map rows to immutable value objects (no Drift symbol leaks past the repository), invariants pushed into the schema (STRICT tables, CHECK/FK/partial-UNIQUE indexes), foreign_keys/WAL pragmas re-asserted idempotently in beforeOpen, one db.transaction per mutation, persist-before-publish, every query awaited, canonical integer storage, derived state recomputed-on-read never stored, scoped .watch streams, keyset (seek) pagination not OFFSET, and WAL-safe backups (checkpoint + VACUUM INTO, verify-by-reopen, never File.copy a live WAL DB). Use when defining or altering a Drift Table, Companion, DAO, index, or CHECK; writing a repository transaction or scoped watch provider; wiring the connection/beforeOpen pragmas; adding SQLCipher; building or verifying a backup; or reviewing a data-layer diff. Migrations and their tests live in run-migration.
Twilio Conversation Intelligence development guide. Use when building real-time or post-call conversation analysis, language operator pipelines, sentiment analysis, agent assist, cross-channel analytics, or querying aggregated conversation insights (sentiment trends, escalation rates, dashboards).
Expert knowledge for Azure Import Export development including troubleshooting, limits & quotas, and security. Use when setting CMK via Key Vault, checking drive limits, validating prerequisites, or debugging Import/Export job failures, and other Azure Import Export related development tasks. Not for Azure Data Box (use azure-data-box-family), Azure Blob Storage (use azure-blob-storage), Azure Files (use azure-files).
Expert knowledge for Azure Open Datasets development including limits & quotas. Use when handling non-Spark dataset downloads, throttling behavior, quota limits, retry logic, or rate-limit workarounds, and other Azure Open Datasets related development tasks. Not for Azure Data Explorer (use azure-data-explorer), Azure Synapse Analytics (use azure-synapse-analytics), Azure Databricks (use azure-databricks), Azure Machine Learning (use azure-machine-learning).
ADF + Microsoft Fabric / OneLake 2025 integration. Proactively activate for: (1) the Fabric Lakehouse connector in ADF, (2) the Fabric Warehouse connector in ADF, (3) OneLake shortcuts and cross-workspace data, (4) Invoke Pipeline activity for cross-platform orchestration (ADF -> Fabric, Fabric -> ADF), (5) copying data between ADF and Microsoft Fabric workspaces, (6) authenticating with Fabric workspace identity, (7) cross-platform parameter passing, and (8) hybrid ADF + Fabric pipeline patterns. Provides Fabric connector setup, Invoke Pipeline templates, OneLake shortcut patterns, and ADF-to-Fabric migration guidance
Access and compare Israeli supermarket prices using mandatory Price Transparency Law data feeds. Use when the user asks about “supermarket prices Israel,” “price comparison Shufersal,” “Rami Levy prices,” “grocery prices,” “Price Transparency Law,” “shopping list optimizer,” “food costs Israel,” or “השוואת מחירי סופר.” Covers chain-specific XML feed parsing, cross-chain price comparison, shopping list optimization, price trend tracking, and restaurant ingredient cost analysis. Do NOT use for restaurant operations (use israeli-restaurant-ops) or non-food retail prices.
Query and analyze Jiimore data on Amazon niche market insights, including market metrics, buyer reviews, competitive landscape, price trends, and growth trends. Trigger this skill when the user mentions niche market analysis, market insights, niche market data, market competition analysis, brand concentration, new product launch success rate, out-of-stock rate, price trends, review insights, market demand score, niche market insights, market metrics, competition analysis, price trends, growth trends, Jiimore data, market intelligence, or out-of-stock rate. Even if the user does not explicitly mention “Jiimore” or “niche market,” trigger this skill whenever their request involves querying market-level intelligence for a specific Amazon niche using a market ID.
Break down traffic sources for all competing ASINs under a given keyword, including organic search, SP ads, SB brand ads, SBV video ads, SP recommendations, and recommendation placements such as AC/ER/TR. Filter by ASIN, date range, new traffic keywords, and other criteria. Trigger when the user mentions keyword traffic sources, which competitors are competing for traffic under a keyword, organic versus paid traffic share, SP ad impressions, brand ad share, SP recommendations, ad/non-ad recommendation placement breakdown, search display analysis, Amazon's Choice or editorial recommendation impressions, keyword competition landscape, ASIN traffic composition, keyword traffic, traffic structure analysis, search share, ad share, traffic source distribution, SIF, traffic analysis, SP recommendation, or recommend position breakdown. Even if the user does not explicitly mention “SIF,” trigger this skill whenever their request involves analyzing traffic source distribution for competing ASINs under a keyword.
Build n8n workflows using the Pinecone Assistant node or Pinecone Vector Store node. Use when building RAG pipelines, chat-with-docs workflows, configuring Pinecone nodes in n8n, troubleshooting Pinecone n8n nodes, or asking about best practices for Pinecone in n8n
Advanced SQLModel patterns and comprehensive database migrations with Alembic. Use when creating SQLModel models, defining relationships (one-to-many, many-to-many, self-referential), setting up database migrations, optimizing queries, solving N+1 problems, implementing inheritance patterns, working with composite keys, creating indexes, performing data migrations, or troubleshooting Alembic issues. Triggers include "SQLModel", "Alembic migration", "database model", "relationship", "foreign key", "migration", "N+1 query", "query optimization", "database schema", or questions about ORM patterns.
When the user wants to define GTM metrics, build a metrics dashboard, measure pipeline efficiency, or track AI product performance. Also use when the user mentions 'GTM metrics,' 'revenue latency,' 'pipeline metrics,' 'TTFV,' 'time-to-first-value,' 'data health,' 'attribution,' 'conversion rate,' 'CAC,' 'LTV,' 'NRR,' 'GTM dashboard,' 'magic number,' 'pipeline velocity,' or 'funnel metrics.' This skill covers GTM measurement from metric selection through dashboard design, including AI-specific cost metrics, attribution models, and weekly review cadences. Do NOT use for technical implementation, code review, or software architecture.
Create, validate, run, inspect, reuse, and edit Jinkō virtual-population subsampling designs with the jinko-sdk. Use whenever a completed Trial's simulated patients must be filtered or selected to match population-level targets, then emitted as a matched Vpop. This is SDK mechanics only: do not use it to choose scientific targets, filters, or algorithm settings; do not use it to create or run the source Trial, author a Vpop, or orchestrate a calibration workflow.
Find competing Amazon products in the same niche by ASIN, with potential competitors filterable by click-through conversion rate, overall conversion rate, clicks, sales, reviews, ratings, price, gross margin, and other dimensions. Trigger this skill when the user mentions same-niche competitors, ASIN competitor discovery, Niche competitor analysis, comparable products, ASIN benchmarking, niche competitor lists, high-conversion competitor screening, Jiimore product discovery, niche competitor by ASIN, ASIN competitor analysis, same niche products, similar products discovery, conversion rate comparison, potential competitor screening, or Jiimore ASIN mining. Even if the user does not explicitly mention “niche market” or “Niche,” trigger this skill whenever their request involves finding a list of competitors in the same niche or screening potential competitors based on an ASIN.
Administer an Omni Analytics instance — manage connections, users, groups, user attributes, permissions, schedules, and schema refreshes via the Omni CLI. Use this skill whenever someone wants to manage users or groups, set up permissions on a dashboard or folder, configure user attributes, create or modify schedules, manage database connections, refresh a schema, set up access controls, provision users, or any variant of "add a user", "give access to", "set up permissions", "who has access", "configure connection", "refresh the schema", or "schedule a delivery".
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Run a Cube.js query against the semantic model and show the result inline in chat as an ASCII table and (where it makes sense) an ASCII bar chart. Use whenever the user asks a business question that can be answered from the cubes — "how many orders…", "top N…", "revenue by…", "trend over time", "compare X to Y" — or explicitly asks to "query the semantic model", "run a cube query", "show me a chart", "plot…", "graph…". Discovers measures and dimensions via `revos cubes meta`, executes the query with `revos cubes query`, and renders the results without leaving the chat.
Comprehensive guide for implementing Syncfusion WPF 3D Charts (SfChart3D) control for 3D data visualization in Windows Presentation Foundation applications. Use this when working with 3D charts, 3D visualization, or depth axis configurations. This skill covers 3D series types (column, pie, bar), Manhattan charts, 3D rotation, X/Y/Z coordinate plotting, and depth axis configuration for WPF applications.
Comprehensive guide for implementing Syncfusion WPF TreeGrid (SfTreeGrid) control in Windows Presentation Foundation applications. Use this when displaying hierarchical or self-relational data in a grid format with expandable tree structure. Supports column configuration, sorting and filtering hierarchical data, editing tree nodes, cell merging, exporting, and conditional styling.
Converts engineering analytics (PR / CI) data into saved PostHog insights, dashboards, and subscriptions, and explains how to query the product data directly with SQL. Covers discovering per-team GitHub warehouse tables via engineering-analytics-sources, replicating curated column semantics in HogQL, reading exposed engineering_analytics_* warehouse views where product logic is involved (CI cost, fingerprinted failure lines, commit attribution), saving queries with insight-create, and scheduling delivery with subscriptions-create. Use when asked to "save this as an insight", "put CI health / merge times on a dashboard", "email me PR throughput weekly", "chart CI cost", "track time to first review", "subscribe to these numbers", "alert on CI success rate", or "what data/tables/views does engineering analytics read". For ad-hoc CI and merge questions use diagnosing-ci-and-merge-bottlenecks; to investigate one specific CI failure use investigating-ci-failures.
AI autonomous research agent for LLM training optimization using opencode as the agent. The agent autonomously modifies train.py, runs experiments, evaluates val_bpb, and iterates to find the best model. Use when: “run autoresearch”, “start experiment”, “train model”, “autonomous research”, “optimize LLM training”.
Creates rigorous, validated models of entities, relationships, and constraints for database schemas (SQL, NoSQL, graph), knowledge graphs, ontologies, API data models, and taxonomies. Covers relational, document, graph, event/time-series, and dimensional schema patterns with lifecycle modeling, soft deletes, polymorphic associations, and hierarchies. Use when user mentions "schema", "data model", "entities", "relationships", "ontology", "knowledge graph", or when data structures need formalization.
Create FAIR-minded reproducibility bundles for materials simulations by collecting input/output file inventories, hashes, units, engine versions, structure identifiers, provenance, and NOMAD/OPTIMADE/Materials Project friendly metadata. Use before publishing, sharing, archiving, or handing simulation results to another agent
Run systematic growth experiments to increase acquisition, activation, retention, and revenue. Use when optimizing conversion funnels, running A/B tests, improving metrics, or when users mention growth, experimentation, optimization, or scaling user acquisition
Implements complete GTM tracking, including dataLayer events in code and GTM configuration via API. Use when users need to “implement GTM tracking,” “add dataLayer events,” “create GTM variables and tags,” “set up CTA tracking,” “implement event tracking,” or execute a tracking plan. Automatically handles both code implementation (dataLayer.push) and GTM container configuration (variables/triggers/tags) via API. Supports incremental updates and framework-specific patterns (React, Next.js, Vue, etc.).
Use the hap-cli command-line tool to operate the HAP enterprise platform. This is the main entry point for hap-cli skills. Covers contacts, chat messages, posting updates, calendar management, and app and data operations (creating, reading, updating, and deleting worksheet records; workflows; pending approvals; custom pages; role permissions; file uploads, and more). Trigger whenever the user wants to find people, send messages, post updates, view or create calendar events, read or write records in a table, or handle approvals in HAP, even if they do not explicitly mention the tool.
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.