Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Export PostHog events, persons, sessions, or the results of a HogQL query on demand and download the resulting files. Use when the user asks to download/export raw PostHog data, export HogQL query results, create a one-off file export, fetch a Parquet or JSONLines export, or use the file_download_batch_exports API. Covers starting the export with MCP, polling completion, and downloading via the existing REST redirect endpoint.
Analyze financial statements for investment decisions: derive EBITDA and free cash flow (FCFF/FCFE) from the income statement and cash flow statement, compute ROIC, margins, and DuPont ROE decomposition, and assess quality of earnings via accruals and working capital trends. Use when the user asks about “reading a 10-K,” “income statement vs cash flow statement,” “how to calculate free cash flow,” “FCFF vs FCFE,” “EBITDA adjustments,” “ROIC vs WACC,” “DuPont analysis,” “quality of earnings,” “accruals ratio,” “cash conversion cycle,” “revenue recognition red flags,” “deferred taxes,” or “cost basis and embedded capital gains.” Also trigger for fundamental analysis questions like whether reported earnings are backed by cash, whether a company creates value above its cost of capital, or the tax consequences of selling an appreciated position
Import CSV or Excel files into seekdb vector database and manage collections. Supports automatic vectorization of specified columns using embedding functions. When users need to: (1) Read and preview Excel files, (2) Import CSV/Excel data into seekdb, (3) Create vector collections from tabular data, (4) Vectorize specific text columns for semantic search, (5) Batch insert product/document data with embeddings, (6) Delete collections, or (7) Access sample data files (sample_products.csv/xlsx) for testing - IMPORTANT: sample files are located in this skill's example-data/ directory, you MUST read this skill file first to get the correct path.
Use seekdb-cli to interact with seekdb/OceanBase databases via shell commands. Use when: (1) querying databases with SQL, (2) exploring table schemas and structure, (3) profiling table data distributions, (4) inferring table relationships, (5) managing vector collections and semantic search, (6) adding/exporting collection data, (7) managing AI models, (8) checking database connection status, or (9) performing any database operation via command line.
This skill should be used when the user needs a "sharded counter", "distributed counter", to "count likes / views at scale", handles a "high-write counter" or "hot counter contention", asks about "approximate counting", "real-time counts", or "HyperLogLog". It gives the recipe for absorbing write-heavy counting without a single hot row. Use it whenever one row/key takes concurrent increments faster than it can serialize them, even if the user doesn't say "sharded counter".
Expert guidance for designing, implementing, migrating, and debugging SwiftData persistence in Swift and SwiftUI apps. Use with @Model schemas, @Relationship/@Attribute rules, Query or FetchDescriptor data access, ModelContainer/ModelContext configuration, CloudKit sync, SchemaMigrationPlan/history APIs, ModelActor concurrency isolation, or Core Data to SwiftData adoption/coexistence.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Workflow required before any Mule flow and integration work. Call use_skill as your FIRST action — before reading project files — whenever the user asks to create, generate, update, fix, modify, change, edit, tweak, adjust, or rework any Mule flow, sub-flow, or component. Do not read project files and attempt the change yourself — even targeted single-component changes like 'modify the choice router', 'fix the until-successful', or 'update the catch block' require this workflow. Covers all change types, new integrations and targeted changes to error handlers, catch blocks, choice routers, DataWeave transforms, HTTP listeners, foreach loops, retry policies, scatter-gathers, connectors, and variable assignments. Prompts beginning with 'This code defines...' or 'This flow...' are generation requests, not analysis. When you call this skill, it must be the only tool call in that response.
Connect Workers to PostgreSQL/MySQL with Hyperdrive's global pooling and caching. Use when: connecting to existing databases, setting up connection pools, using node-postgres/mysql2, integrating Drizzle/Prisma, or troubleshooting pool acquisition failures, TLS errors, or nodejs_compat missing. Prevents 11 documented errors.
Create HTML dashboards with KPI metric cards, bar/pie/line charts, progress indicators, and data visualizations. Use when users request dashboards, metrics displays, KPI visualizations, data charts, or monitoring interfaces.
Use when training Roboflow models, diagnosing why a model underperforms, improving accuracy, or setting up a production feedback loop — covers architecture selection, model IDs, checkpoints, Model Evaluation (confusion matrix, per-class metrics, MCP eval tools), the diagnosis-first improvement playbook, and Active Learning through the Project Model Workflow block
Xiaohongshu low-follower viral posts focuses on uncovering data about viral posts on Xiaohongshu from accounts with few followers, finding rankings of posts with fewer than 5,000 followers but over 500 interactions. Find quality examples that reveal viral patterns and popular trends.
Create Databricks AI/BI dashboards. Must use when creating, updating, or deploying Lakeview dashboards, as Databricks Dashboard has a unique JSON structure. CRITICAL: You MUST test ALL SQL queries via CLI BEFORE deploying. Follow guidelines strictly.
Use this skill when the user needs a "unique ID generator", "distributed IDs", a "Snowflake ID", asks "UUID vs auto-increment", wants a "time-sortable ID", a "monotonic sequence", a "ticket server", or "ID generation at scale". It gives a menu of ID schemes (UUID/ULID, Snowflake-style, DB ticket/range) with their causality, ordering, and clock-skew trade-offs. Use it whenever a design needs collision-free identifiers across many nodes, even if the user doesn't say "sequencer".
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g. adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases
Guides developers through integrating and using Viking SDK, covering installation, authentication, API calls, and troubleshooting for the Viking vector database, knowledge base, and memory store. Use when users need to develop business code with Viking SDK or ask questions about Viking.
Write and run Contentful content model migration scripts using the contentful-migration library and the Contentful CLI. Covers creating, editing, and deleting content types and fields, validations, editor interface configuration, editor layouts, sidebar widgets, entry transformations, tags, annotations, and the migration context object. Use when asked to write a migration, create or add a content type, add, rename, or delete fields, change or update a content model, transform entries, derive linked entries, configure editor controls, or run a migration script. Also triggers on "migration script", "contentful-migration", "schema migration", "content model migration", "field validation", "editor interface", "editor layout", "sidebar widget", "moveField", "changeFieldId", "rich text field", "reference field", "link field". Not for SDK client setup or Next.js integration (contentful-nextjs). Not for Contentful terminology or API routing (contentful-guide).
Build and deploy Streamlit apps natively in Snowflake. Covers snowflake.yml scaffolding, Snowpark sessions, multi-page structure, Marketplace publishing as Native Apps, and caller's rights connections (v1.53.0+). Use when building data apps on Snowflake, deploying SiS, fixing package channel errors, authentication issues, cache key bugs, or path resolution errors
Configure a Trade Promotion Management (TPM) org's RTR (Real Time Reporting) export pipeline to push promotion measures into Data Cloud (Data 360) for Trade Promotion Effectiveness (TPE) dashboards. Use when a customer or admin wants to set up the RTR export for Data Cloud measures, configure the RTR report for TPE, or as a delegated step from consumer-goods-tpe-dashboard-configure.
Comprehensive guide to Spark Structured Streaming for production workloads. Use when building streaming pipelines, working with Kafka ingestion, implementing Real-Time Mode (RTM), configuring triggers (processingTime, availableNow), handling stateful operations with watermarks, optimizing checkpoints, performing stream-stream or stream-static joins, writing to multiple sinks, or tuning streaming cost and performance.
Use when creating, reviewing, or styling charts, graphs, dashboards, sparklines, or any data visualization. Applies to Recharts, ECharts, Chart.js, matplotlib, Plotly, seaborn, D3.js, and SVG. Enforces Tufte principles (data-ink ratio, direct labeling, range-frame axes) plus modern screen-first standards (accessibility, responsive, dark mode)
Use when you need to add or review Flyway database migrations in a Quarkus application — quarkus-flyway extension, db/migration scripts, quarkus.flyway.* configuration, migrate-at-start, and alignment with JDBC or Panache. This should trigger for requests such as Add or review Flyway migrations in a Quarkus project; Configure quarkus-flyway or db/migration layout; Add versioned Flyway SQL migrations for Quarkus; Review Quarkus database migration ordering; Configure Flyway clean migrate or baselines in Quarkus. Part of Plinth Toolkit
End-to-end guidance for solving mathematical modeling competitions. Covers all problem types (A–F) in the national contest (CUMCM) and MCM/ICM, with 12 analyses of problem fundamentals, a decision matrix for 95+ scenarios, 5 algorithm Cookbooks, 11 complete example Playbooks, and 22 Python + 7 MATLAB runnable code templates. Pairs with math-modeling-paper for “problem solving → writing.” Use this skill when users mention modeling approaches, choosing a model, how to model, contest problem solving, pasting problem text, MCM/national contest problem analysis, CVaR/NSGA-II/Monte Carlo/time series/ANOVA/grey relational analysis, network flow/graph theory/ecological modeling, model naming, Memo/Letter/Our Work flowcharts.
Answer natural-language questions about a user's OpenRouter usage data — spend, request volume, model breakdown, latency, token usage, and cost optimization. Use when the user asks about their API usage, billing, costs, top models, traffic patterns, or wants to optimize their OpenRouter spend.
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
Use when you need programmatic JDBC in Quarkus — Agroal DataSource, parameterized SQL, transactions, batching, and Dev Services. This should trigger for requests such as Review JDBC or SQL data access in a Quarkus project; Improve transactions and parameter binding for Quarkus JDBC; Translate SQLException to domain exceptions or stream large result sets; Fix CDI self-invocation bypassing @Transactional in Quarkus; Review Agroal DataSource usage in Quarkus JDBC. Part of Plinth Toolkit
Analyze production Agentforce agent behavior using session traces and Data Cloud, and manage Agent Health Monitoring (AHM) alerts. TRIGGER when: user queries STDM session data or Data Cloud trace records; investigates production agent failures, regressions, or performance issues; asks about session traces, conversation logs, or agent metrics; wants to reproduce a reported production issue in preview; runs findSessions or trace analysis queries; creates, lists, updates, or deletes an AHM data alert on an agent metric (escalation rate, deflection, etc.); asks why an alert is not firing or wants to check whether alerts have fired (notification counts, or the per-alert Incidents view). DO NOT TRIGGER when: user creates, modifies, or debugs .agent files during development (use agentforce-generate); writes or runs test specs (use agentforce-test); uses sf agent preview for local development iteration; deploys or publishes agents.
Deploy the TPM Accruals Data Kit components specifically required for Trade Promotion Effectiveness (TPE) dashboards. Use when a customer or admin wants to install or deploy the TPM data kit for TPE dashboards, or as a delegated step from consumer-goods-tpe-dashboard-configure. Do not use this skill if the customer wants to deploy the TPM Accruals Data Kit for the Accruals feature
Build a guided requirements-to-implementation workflow for new Power BI reports and dashboards from semantic models, datasets, or PBIP projects. Use when the user wants to: (1) plan then implement a report, (2) define audience, scope, page plan, design direction, dependencies, and delivery target, (3) create a locked report spec with approval before PBIR authoring. For direct edits to existing report files, use `powerbi-report-authoring`. For design-only critique or redesign, use `powerbi-report-design`. Triggers: “build me a dashboard,” “create a new report,” “plan then implement,” “define and build Power BI report,” “walk me through creating a report.”
Persist canister state across upgrades. Covers StableBTreeMap and MemoryManager in Rust, persistent actor in Motoko, and upgrade hook patterns. Use when dealing with canister upgrades, data persistence, data lost after upgrade, stable storage, StableBTreeMap, pre_upgrade traps, or heap vs stable memory. Do NOT use for inter-canister calls or access control — use multi-canister or canister-security instead
Deploy, manage, and optimize vector databases for AI applications. Covers Qdrant, Weaviate, pgvector, and Pinecone — collection management, indexing strategies, backup, and performance tuning for production RAG and semantic search workloads
Customize the Trade Promotion Effectiveness (TPE) Analytics dashboards' generic KPI slots (Promotion Measure 1-3, Tactic Measure 1-2) with customer-chosen KPI measure codes and display names, without touching the shipped base model. Use when a customer/admin wants to \"customize TPE dashboards\", \"change the KPIs on the Promotion/Tactic Analysis dashboard\", or \"swap in our own measure codes on the TPE dashboard\"
Use this skill whenever a task involves a document file (PDF, DOCX, PPTX, XLSX, or image) and you need to read it or pull text, tables, or specific values out of it — to answer a question about its contents, look up a figure, or extract data. Provides fast, local, model-free extraction via the `lit` CLI with disciplined, low-cost search patterns.
Retrieve detailed metadata and stored content for individual OpenRouter generations. Use when the user wants to inspect a specific request — its cost, latency, token usage, provider routing, or the actual prompt/completion text — or is debugging a failed or unexpected generation.
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.