Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF/GRIB/Zarr files, climate/weather/oceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.
ADF + Azure ML and analytics integrations. PROACTIVELY activate for: (1) Azure ML batch endpoints invoked from ADF, (2) Azure OpenAI Batch API pipeline patterns, (3) ADF ML scoring orchestration, (4) SQL to Storage archival pipelines, (5) AI Services integration via REST connector, (6) Databricks notebook execution from ADF, (7) Data Flow feature engineering, (8) Synapse / Fabric integration from ADF, (9) Cognitive Search indexer triggers, (10) Power BI dataset refresh via REST. Provides: REST connector recipes, Databricks linked service setup, Data Flow templates, and end-to-end ML scoring pipelines.
Produces a CPA-ready year-end COGS schedule for Amazon sellers from Inventory Valuation Report, Settlement reports, and supplier POs. Catches the ending inventory math errors that overstate taxable income by 8-15%. Use when a user asks about year-end taxes, COGS, inventory valuation, or "tax pack for my accountant". Trigger phrases: "year-end taxes", "COGS schedule", "inventory valuation", "FIFO LIFO Amazon", "tax pack for CPA". Works with zero tools.
Look up ArcGIS documentation against authoritative Esri sources and verify an API exists at a pinned version. Use when the user needs an ArcGIS API reference, ArcGIS Pro, Enterprise, or Notebook Server docs, or when another skill must confirm a class, method, global, or function is available at a target version.
Use when one validated cohort analysis must be repeated across many exposure/outcome pairs. Generates one R/Python script per combination from a single methodology template, changing only the variables, and aggregates the results into a summary matrix.
Create Confluent-specific skills for external users. Use this skill when users want to create, build, or author a new skill related to Confluent Cloud, Confluent Platform, Apache Kafka, WarpStream, Flink, Connectors, Schema Registry, Tableflow, CDC pipelines, or any Confluent product. Skills can be use-case focused (like data enrichment, CDC to Tableflow, stream processing workflows) or component-specific (like a Flink skill, Schema Registry skill, or Connector skill). Do NOT use this skill when users want to directly use Confluent products (e.g., build a pipeline, write a producer, deploy Flink SQL) — use the appropriate product-specific skill instead. This skill is specifically for creating new skills, not for using existing ones.
Manages Fabric Dataflow Gen2 items, including creation, M editing, connections, output destinations, getDefinition and updateDefinition inspection, executeQuery, refresh history, and Gen1-to-Gen2 save-as upgrades via saveAsNativeArtifact. Use for Dataflow items or Power Query M definitions. For pipeline JSON use pipeline-migration; for Spark or Warehouse transformations use their own skills.
Generates a Markdown bug report for an IBM watsonx.data integration session. User can invoke directly. The agent MUST propose it (and must wait for explicit acceptance) after 3 or more consecutive calls to the same tool or the same sequence of tools result in a failure or the same error. Skip for non-watsonx.data integration sessions.
Use when building Script Reports, Query Reports, dashboard charts, or Number Cards in ERPNext. Prevents empty report output from wrong column definitions, broken filters, and unoptimized SQL in large datasets. Covers Report Builder, Script Report (Python + JS), Query Report, Report filters, dashboard Chart DocType, Number Card, report permissions. Keywords: report, Script Report, Query Report, dashboard, chart, Number Card, filters, columns, execute, get_data, create report, custom report, dashboard chart, report empty, no data showing.
Use when building Query Reports, Script Reports, or configuring Report Builder, including chart data integration. Prevents report errors from wrong column definitions, missing permissions, and incorrect data formatting. Covers Query Report (SQL-based), Script Report (Python-based), Report Builder, report columns definition, filters, chart_data, report permissions, prepared_report. Keywords: Query Report, Script Report, Report Builder, report columns, filters, chart_data, frappe.query_report, prepared_report, report columns, how to build report, report not showing data, chart in report.
A-share quantitative data assistant — daily report snapshots, A-share calendar, margin trading, real-time news flashes, northbound capital, theme heat, board secretary Q&A, quantitative strategies, resonance and risk alerts, zero configuration with no dependencies to install.
Database specialist covering PostgreSQL, MongoDB, Redis, Oracle, and cloud database platforms (Neon, Supabase, Firestore). Use for schema design, query optimization, indexing strategies, data modeling, or cloud database selection. Cloud vendor guide absorbed from moai-platform-database-cloud.
Set up and operate Rekor — a headless system of record for AI agents. Use when: installing the `rekor` CLI, authenticating, creating a base, defining record_types, working in preview and promoting to production, managing config as code (rekor pull/push), upserting or querying records (Filter DSL or SQL), managing relationships, storing versioned files or attachments (incl. S3 mounts), configuring inbound webhooks, triggers, batch operations, or seed fixtures for agent evals, backing a record_type with an external API (external sources, executors), storing credentials in the secret vault, importing or exporting tool definitions across providers (OpenAI/Anthropic/Google/MCP), creating curated MCP Factory toolsets and Actions, scoping API tokens, modeling record_types and toolsets so LLM agents use them reliably, or interpreting any Rekor concept (base, record_type, record, relationship, preview/production, promotion, external_id).
Design, implement, migrate, test, and operate Rust database access, including SQLx, Diesel, SeaORM, schema evolution, transaction boundaries, connection pools, retries, type mapping, concurrency control, and real-database verification. Use when users ask about Rust SQL or ORM code, migrations, transactions, PostgreSQL or MySQL integration, connection pools, query safety, or database production readiness.
Download live chat transcripts from YouTube videos. Use when the user asks for live chat, chat messages, or chat replay from a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Works with live streams and past streams that have chat replay enabled.
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics. For page-level conversion optimization, see cro.
Query blockchain data using the allium CLI. Two products: Explorer (SQL analytics on Allium's data warehouse — any table, any timeframe, 150+ chains) and Realtime (3-5s freshness lookups for prices, balances, transactions, PnL, positions across 80+ chains). Supports API key, x402 micropayments, and Tempo MPP
Generally-applicable backend/data best practices. Use whenever writing or modifying backend/data code — API routes, server actions, DB writes, background jobs, agent tools, import flows, webhooks, paste handlers, or anywhere data enters the system. Consult BEFORE writing the code so the patterns are baked in, not retrofitted. If a scenario described in the skill body matches the work, apply the pattern — don't ask, just follow it (call out the choice in one line so the user can override).
Production guidance for converting sourced data and approved claims into truthful, accessible, deterministic animated visualizations with D3. Use for data-driven charts, maps, networks, hierarchies, transitions, annotations, responsive video variants, frame-by-frame browser rendering, and visualization QA; not for generic dashboards, unsourced decorative charts, or ordinary motion graphics without a data contract.
Process JSON with jq and YAML/TOML with yq. Filter, transform, query structured data efficiently. Triggers on: parse JSON, extract from YAML, query config, Docker Compose, K8s manifests, GitHub Actions workflows, package.json, filter data.
Build and maintain Dexie.js data layers for IndexedDB-backed offline-first web applications. Use when tasks involve Dexie setup, schema/index design, CRUD/query implementation, transactions, live queries, migrations, or debugging in Vanilla JS, React, Next.js, TanStack Start, Svelte, or SvelteKit.
Owns data understanding before any model is designed. Place `data_analysis/data_analysis.py` and do not execute it. Run `materialize.py` once, write `data_analysis.md` and JOURNAL § Data understanding. Never design the model, edit `src/<pkg>/`, or modify raw data files. TRIGGER when the user asks to explore, profile, or understand the data; triage sent them here (`status.data_analysis` missing); a data source changed; they want to refresh a recorded EDA; or leakage or research arises on a recorded EDA. STOP when `status.setup.pending` is non-empty (load `setup-ml-project`), when there is no data (send to triage), the request is not raw-data exploration, or EDA is recorded with no refresh and no methodology concern. Do not invent a package root or a root `JOURNAL.md` while setup is pending. HOW TO USE: G-TABULAR via `add-python-package`, infer or ask the targets, load `plot-ml-figure` if installed, then ask the five-option continuation board, including Close.
GoldRush Streaming API — real-time blockchain data via GraphQL subscriptions over WebSocket. Use this skill whenever the user needs live price feeds (OHLCV candles), real-time DEX pair monitoring (new pairs, liquidity updates), wallet activity streaming, decoded swap/transfer events, token search, trader PnL analysis, or any sub-second latency blockchain event push. This is the right skill for trading bots, live dashboards, alerting systems, copy-trading, DEX sniping, and real-time analytics. Also covers one-time GraphQL queries for token discovery and profitability analysis. If the user needs historical data, batch queries, or paginated REST results, use goldrush-foundational-api instead. If the user needs pay-per-request access without an API key, use goldrush-x402 instead.
Financial data query skill based on the 同花顺 iFind API. Use to obtain stock quotes, fund net asset values, index data, financial statements and more for A-shares, Hong Kong stocks, and US stocks. Trigger scenarios: (1) query real-time stock quotes or historical prices, (2) get fund NAV and performance data, (3) query index constituents and valuations, (4) natural-language stock screening (问财), (5) get financial data and valuation metrics. Supports both local SDK and HTTP API calls.
Lead sources by use case with a data workspace delivery-ready templates - Apollo, LinkedIn Sales Navigator, a data workspace, Ocean.io, Openmart, and Local Directories. Use when choosing lead sources, building prospecting workflows, or setting up data enrichment.
Automate construction data processing using LLM (ChatGPT, Claude, LLaMA). Generate Python/Pandas scripts, extract data from documents, and create automated pipelines without deep programming knowledge.
Format reference for Power BI Enhanced Report (PBIR) JSON schemas and patterns. Automatically invoke when the user asks about PBIR JSON structure, visual.json properties, PBIR expressions, objects vs visualContainerObjects, theme inheritance, conditional formatting patterns, extension measures, bookmarks, field references, filter formatting, query roles, PBIR page structure, report wallpaper, or any PBIR metadata format question.
Provider-independent production guidance for converting observed video into precise, objective, temporally ordered language. Use for shot descriptions, searchable metadata, dataset captions, reference logs, generation-prompt handoffs, and analysis across subject, scene, motion, spatial, and camera aspects; not for deciding what to shoot, accessibility captions, creative interpretation, or provider-specific video analysis APIs.
Use when applying a published cohort study's methodology to a different database. Extracts the design from the source paper, maps variables to the target database with a harmonization table, generates the analysis code and reports every forced deviation.
Customer retention analysis, churn prediction, cohort analysis, win-back campaigns, and loyalty program design. Use when the user asks about churn, retention, customer lifetime value, cohort analysis, or win-back strategies.
Downloads and starts a local CockroachDB cluster for development using the official binary. Use when a developer needs a local CockroachDB instance, when no cluster is available, or when setting up a new development environment.
Assess whether structured data, query results, dashboards, or analytical evidence are trustworthy enough to use. Use when the task is to check data quality, reconcile conflicting sources or metric definitions, or decide whether evidence is safe to cite.
Use when analyzing a researcher's publication record from PubMed. Fetches an author's papers, classifies study types and author position, charts the patterns and writes a strategy report, with an optional trajectory-archetype classification. Works from PubMed metadata only.
Systematically investigates causal relationships to identify true root causes rather than correlations or symptoms. Distinguishes genuine causation from spurious associations, tests competing explanations, and designs interventions addressing underlying drivers. Use when investigating why something happened, debugging systems, analyzing failures, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?"
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.