Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Acquire a page or site into the shared PageSnapshot every audit module reads — real HTTP status chain, headers, robots directives, raw HTML on disk, parsed document, optional headless-Chrome render with a raw-vs-rendered delta, and once-per-run site artifacts (robots, sitemaps, AI discovery files). Acquisition is done by the bundled scripts (snapshot.mjs / crawl.mjs), never by WebFetch. Records the data tier reached.
Searches Xiaohongshu(小红书) for a given keyword, extracts the top N posts (including text, images, and user comments), then synthesizes a comprehensive final analytical report. Use whenever the user wants to search Xiaohongshu for a specific topic, compile research seamlessly combining text and images, or needs an aggregated thematic summary of social media posts, comments, and visual data on a given subject.
This skill should be used when working with Convex actions, HTTP endpoints, validators, schemas, environment variables, scheduling, file storage, and TypeScript patterns. It provides comprehensive guidelines for function definitions, API design, database limits, and advanced Convex features.
Core workflow for in-depth individual stock analysis. Trigger when users request in-depth or comprehensive analysis, ask you to take a look or assess whether a stock is worth buying, or request DCF, institutional modeling, or an initiation of coverage, investment committee memo, or other individual stock research. Covers A-shares, Hong Kong stocks, and US stocks, producing 22-dimensional data, quantitative reviews by 66 experts, six institutional-grade valuation models (DCF/Comps/LBO/3-Stmt/Merger), seven research deliverables (initiation of coverage/earnings analysis/catalyst calendar/investment thesis tracking/morning brief/quantitative screening/industry overview), six decision methods (IC Memo/DD/Porter/unit economics/VCP/rebalancing), and pump-and-dump detection. Generates a Bloomberg-style HTML report and a social-sharing performance report. Keywords: stocks, individual stocks, in-depth analysis, valuation, DCF, comps, initiation of coverage, IC memo, pump and dump, top-trader list, akshare.
Sets up and manages ClickHouse using the clickhousectl CLI—installs and runs a local ClickHouse server for development, and creates managed ClickHouse Cloud services for production (authentication, service creation, schema migration, application connection). Use when the user wants to build an application with ClickHouse, set up a local ClickHouse dev environment, create tables and start querying, deploy ClickHouse to production or ClickHouse Cloud, or migrate from a local setup to the cloud.
Compare keyword search popularity and analyze trends with Google Trends, supporting global regions and custom time ranges. Trigger this skill when users mention Google Trends, keyword popularity over time, search interest comparisons, keyword trend analysis, seasonal trend detection, regional search popularity, keyword heatmaps, comparisons of multiple keywords on Google, Google Trends, keyword popularity comparison, search trends, seasonal analysis, regional popularity, or keyword comparison. Trigger it even if users do not explicitly say “Google Trends” as long as their request involves comparing keyword search popularity trends across different time periods or regions.
Explore and optimize simulation parameters via design of experiments (DOE), sensitivity analysis, and optimizer selection — generate Latin Hypercube, quasi-random, or factorial sample plans, rank parameter influence with sensitivity scores, recommend Bayesian optimization, CMA-ES, or gradient- based methods based on dimension and budget, and fit surrogate models for expensive evaluations. Use when calibrating material properties against experimental data, planning a parameter sweep, performing uncertainty quantification, or choosing an optimization strategy for a simulation with a limited evaluation budget, even if the user only says "which parameters matter most" or "how do I calibrate my model."
Web scraping from TypeScript or JavaScript with the Scrapfly SDK (`scrapfly-sdk`). Use when the user asks to scrape a URL, bypass anti-bot protection, render JavaScript, capture screenshots, or extract structured data from Node.js, Deno, or Bun.
Queries local analytics across OrchestKit projects for agent usage, skill frequency, hook timing, team activity, session replay, cost estimation, and model delegation trends. Privacy-safe with hashed project IDs. Supports time-range filtering and comparative analysis. Use when reviewing performance, estimating costs, or understanding usage patterns.
ByteHouse slow query analysis and performance optimization tool for identifying and analyzing slow queries, query performance optimization suggestions, viewing query execution plans, and analyzing query history trends. Use this Skill when users need to identify and analyze slow queries in ByteHouse databases, get query performance optimization suggestions, view query execution plans, or analyze query history trends.
Extract, analyze, and summarize simulation output data — pull spatial fields at specific timesteps, compute time-series trends and detect steady state, extract line profiles through the domain, generate statistical summaries and distributions, calculate derived quantities (gradients, fluxes, volume fractions, interface area), compare results against analytical solutions or experimental data, and produce automated analysis reports. Use when interpreting finished simulation results, checking mass or energy conservation, comparing two runs or meshes, extracting interface profiles from phase-field output, or preparing publication-quality analysis, even if the user only says "what do my results look like" or "did my simulation reach steady state."
Every SEC filing, every XBRL fact, every insider trade — synced into a local SQLite store you can pivot, search, and watch offline. Trigger phrases: `look up an SEC filing`, `check insider trading on`, `compare quarterly financials for`, `watch SEC filings for`, `use sec-edgar`.
Know the metrics that matter at each stage and what investors actually look for. Master the A16Z and YC frameworks for measuring startup progress. Use when: **Fundraising prep** to know which metrics to highlight; **Board meetings** to report on the right KPIs; **Strategic planning** to set goals that matter; **Product decisions** to understand what to optimize; **Diagnosing problems** to find what's broken
Implements Syncfusion® .NET MAUI Linear Gauge (SfLinearGauge) for data visualization with scales, pointers, and ranges. Use when creating linear gauges, displaying measurements on linear scales, showing progress indicators, or building thermometer-style visualizations. Covers gauge pointer configuration, bar pointers or shape markers, draggable gauge pointers, and animated gauge transitions.
Implements the Syncfusion .NET MAUI Range Selector (SfRangeSelector) component. Use when working with range selection with embedded charts, numeric range input, RangeStart/RangeEnd, track customization, or thumb styling in .NET MAUI. Covers tooltip configuration, label formatting, ticks/dividers, selection modes, events, and embedding SfCartesianChart inside a range control.
Persists task and asset state across retries and DAG runs using Airflow 3.3's AIP-103 key/value stores (`task_state_store`, `asset_state_store`) and the crash-safe `ResumableJobMixin`. Use when the user asks about task state store, checkpointing in tasks, persisting state across retries, job IDs surviving worker crashes, watermarks, asset metadata, resumable tasks, crash-safe operators, or "what's new in Airflow 3.3". Also use proactively when reading a DAG that uses Variables or XCom for intra-task coordination state (flag the anti-pattern), or when reviewing any DAG that submits a job to an external system (Databricks, Snowflake, BigQuery, Redshift, Spark, dbt Cloud, EMR, AWS Batch, etc.) and waits for it to finish, whether as one submit-and-wait operator or split into submit + sensor/polling tasks; covers `wait_for_termination`, `deferrable`, `durable`, and hand-rolled polling sensors. State-persistence pieces require Airflow 3.3+; submit+poll architecture guidance applies on any version.
Use this skill when the user needs to set up a DataHub connection, install the DataHub CLI, configure authentication, verify connectivity, set default scopes, or create agent configuration profiles. Triggers on: "set up DataHub", "connect to DataHub", "install datahub CLI", "configure DataHub", "set default platform", "focus on domain X", "create profile", or any request to establish, configure, or troubleshoot DataHub connectivity.
Help existing PostHog customers improve their PostHog instance. Triggers on “help [customer] improve their PostHog setup”, “audit [company]'s PostHog instance”, “create tracking plan for [company]”, “design data schema for [customer]”, or requests to improve analytics coverage, fix instrumentation gaps, expand PostHog usage, or build better insights for customers already using PostHog. Use when working with a customer who already has PostHog installed.
Design and operate Redis for caching, queues, sessions, rate limiting, distributed locks, streams, and ephemeral data with explicit limits and failure modes. Use when working with Redis or compatible clients (Valkey), TTLs, Lua, Cluster, Sentinel, or RDB/AOF persistence; do not treat Redis as a durable source of truth without an explicit requirement and evidence of acceptable RPO/RTO
Comprehensive Stata reference for writing correct .do files, data management, econometrics, causal inference, graphics, Mata programming, and 20 community packages (reghdfe, estout, did, rdrobust, etc.). Covers syntax, options, gotchas, and idiomatic patterns. Use this skill whenever the user asks you to write, debug, or explain Stata code
Implements Syncfusion® .NET MAUI TreeMap (SfTreeMap) for visualizing hierarchical data with rectangles sized and colored by values. Use when implementing hierarchical data visualization, heat maps, squarified layouts, multi-level data grouping, or brush settings for hierarchical displays. This skill covers installation, data binding, layout types, hierarchical levels with GroupPath, legend configuration, tooltips, and TreeMap customization.
This skill should be used when implementing Convex mutation functions. It provides comprehensive guidelines for defining, registering, calling, and scheduling mutations, including database operations, transactions, and scheduled job patterns.
Handle spreadsheet operations (Excel/CSV) with high-fidelity modeling, financial analysis, and visual verification. Use for budget models, data dashboards, and complex formula-heavy sheets. Use proactively when zero formula errors and professional standards are required. Examples: - user: "Build an LBO model" -> create Excel with banking-standard formatting - user: "Analyze this data and create a dashboard" -> use openpyxl + artifact_tool - user: "Verify formulas in this spreadsheet" -> run recalc.py to check for errors
Design hypothesis-driven experiments and A/B tests with proper methodology. Use when asked to design an A/B test, validate a hypothesis, plan an experiment, or set up a test for a product change. Covers hypothesis writing, sample size, and common mistakes.
Define product metrics with a North Star, input/output tree, and counter-metrics. Use when asked to define metrics, set up measurement, choose KPIs, pick a north star metric, or build a metrics framework. Prevents vanity metrics and gaming.
Use when connecting cloud storage (AWS S3 / S3-compatible or Google Cloud Storage) to Roboflow to mirror images into a workspace — creating storage credentials, defining datasources (bucket-mirror configs), selecting objects with glob rules, validating access, and running/scheduling mirror jobs.
Converts Synapse workspaces to Fabric: Spark items, Lake Databases, Linked Services, and Dedicated SQL Pool schema/procedures for Lakehouse or Warehouse. During Pool-to-Lakehouse migration only, can migrate approved dependent procedure callers after notebook readiness. Excludes standalone pipelines and Warehouse administration. Triggers: Synapse workspace to Fabric, Dedicated SQL Pool to Lakehouse, Dedicated SQL Pool to Fabric Warehouse.
Implements Syncfusion .NET MAUI Smart DataGrid (SfSmartDataGrid) with AI-powered features. Use when working with SfSmartDataGrid, AI-powered grid operations, natural language data commands, AI sorting, AI filtering, or conversational grid interaction. Covers Azure OpenAI grid integration and natural language commands for grids.
Implements Syncfusion® .NET MAUI Sunburst Chart (SfSunburstChart) for hierarchical data visualization using a radial, multi-level circular layout. Use this for sunburst charts, radial hierarchical charts, multi-level pie charts, or hierarchical data visualization with drill-down capabilities. Ideal for visualizing organizational structures, file systems, or nested categorical data.
Use when you need framework-agnostic MongoDB and non-relational database query guidance—document schema design, collection modeling, JSON Schema validation, indexes, aggregation pipelines, query performance, consistency trade-offs, transactions, and operational safety—without choosing Spring Boot, Quarkus, or Micronaut. This should trigger for requests such as Design MongoDB document schemas; Review MongoDB queries and indexes; Improve aggregation pipeline performance; Model non-relational data access patterns; Review NoSQL consistency and transaction trade-offs. Part of Plinth Toolkit
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.