Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Extracts YouTube trending videos by category and country using apidojo's YouTube Trending Scraper on Apify. Triggers when the user asks to: get trending YouTube videos, scrape what's trending on YouTube today, fetch YouTube trending videos in a specific country, get trending gaming or music videos on YouTube, export the YouTube trending page data, find viral YouTube videos right now, or collect top trending YouTube content by category. Returns video title, URL, view count, like count, channel info, description, and thumbnail per video. Ideal for content researchers, trend analysts, and YouTube marketers.
Apply IRQL graph functions to KQL or IRQL query results for visualization in Kusto Explorer. Generates Lift_To_Graph mappings and composes Graph_Render_View, Graph_Fold_By_Property, Extract_Node_*, Enrich_Node_*, and Enrich_Graph_* calls. Accepts a supplied query or limited basic natural-language source request; it is not a general natural-language-to-KQL/IRQL skill. WHEN: Lift_To_Graph, Graph_Render_View, Graph_Fold_By_Property, IRQL graph enrichment, graph mapping for existing query results, icon-decorated graph, fold graph nodes. Use azure-kusto-graph for native make-graph analysis, graph-match, shortest paths, components, or persistent graphs.
Finds YouTube channels with high growth rates in a niche using apidojo's YouTube scraper. Triggers when the user asks to: find fast-growing YouTube channels in a niche, discover YouTube channels with high momentum, identify YouTube creators gaining subscribers quickly, find rising YouTube channels before they get big, discover YouTube channel growth trends in an industry, find channels to partner with early while still growing, or research which YouTube channels are gaining traction in a topic area. Returns channel name, subscriber count, growth signals, view momentum, upload frequency, and growth tier. Ideal for brand partnership managers, talent scouts, and early-stage sponsorship teams.
Documents the results of a completed experiment or A/B test with statistical analysis, learnings, and recommendations. Use after experiments conclude to communicate findings, inform decisions, and build organizational knowledge.
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202
Sort many texts into your own categories without reading them, using a keyless HTTP API that returns a calibrated confidence per answer. Use when triaging, filtering, routing or bucketing more items than are worth putting in context — search results before you read them, log lines, tickets, files, diffs, past conversations. Triggers on "filter these", "which of these are relevant", "triage", "bucket", "route", "categorise", or any loop that would otherwise read N items to keep a few.
Scrapes YouTube channel statistics and video catalog for any list of channels using apidojo's YouTube scraper on Apify. Triggers when the user asks to: get YouTube channel stats, fetch subscriber count and video count for YouTube channels, scrape channel metadata in bulk, export YouTube channel information by URL or handle, get all videos from a YouTube channel, or check channel growth data for a list of creators. Returns channel name, subscriber count, total views, video count, and recent video data. Ideal for competitor analysis, creator research, and audience benchmarking.
Design and manage market data infrastructure — real-time and delayed feeds, Level 1/2/3 depth, consolidated tape vs direct feeds, vendor selection, licensing, and distribution architecture. Use when choosing between real-time and delayed data, evaluating market data vendors like Bloomberg or Refinitiv, designing ticker plants or fan-out architecture, managing exchange data licensing and entitlements, diagnosing stale quotes or missing ticks, deciding between SIP and direct exchange feeds, or assessing Level 2/3 depth-of-book requirements for trading. Trigger on: market data, Level 1/2/3, depth of book, consolidated tape, SIP, direct feed, NBBO, ticker plant, B-PIPE, data license, non-display use, market data entitlements, conflation, tick data, real-time feed.
MPSTATS marketplace analytics API. Use when working with MPSTATS API, Wildberries analytics, Ozon analytics, Yandex Market analytics, marketplace data, product research, sales analytics, competitor analysis, niche research, SKU analysis, seller analytics, brand analytics
Plans the stack, database schema and API for an app clone, from the recon map replica-recon wrote. Picks boring, managed tech, turns the inferred data model into real SQL with indexes and access rules, lists every route by flow, and orders the build as a thin vertical slice first. Use when the user says "plan the clone", "what stack should I use", "design the database", "write the schema", "plan the API", "architecture for my version of X", or after /replica-recon finishes.
MLB data via ESPN public endpoints and the official MLB Stats API — scores, standings, rosters, schedules, game summaries, injuries, leaders, and news, plus an analytics backend: pitch-level velocity/spin/exit-velocity, career splits by stat group, league leaders, and schedules to 1901. Zero config, no API keys. Use when: user asks about MLB scores, standings, team rosters, schedules, game stats, box scores, play-by-play, injuries, transactions, depth charts, team/player statistics, MLB news, pitch speeds/spin/exit velocity, career stats, league leaders, or historical MLB seasons. Don't use when: user asks about minor league baseball, college baseball, or international baseball. For other sports use: nfl-data (NFL), nba-data (NBA), wnba-data (WNBA), nhl-data (NHL), football-data (soccer), tennis-data (tennis), golf-data (golf), cricket-data (cricket), cfb-data (college football), cbb-data (college basketball), fastf1 (F1). For betting odds use polymarket or kalshi. For news use sports-news.
Builds the backend of an app clone: auth, database migrations and access rules, payments with Stripe, email, background jobs and third-party integrations through official APIs only, plus a security checklist. Use when the user says "add login", "set up auth", "wire up the database", "add payments", "connect Stripe", "add Google Calendar", "send emails", "backend for my clone", or when /replica-build is running on fake data.
Extracts definitions, examples, and community votes from Urban Dictionary using apidojo's Urban Dictionary Scraper on Apify. Triggers when the user asks to: get Urban Dictionary definitions for a word or phrase, look up slang terms on Urban Dictionary, scrape definitions for internet slang or memes, export Urban Dictionary entries for a keyword, find how a term is defined by the internet community, collect crowd-sourced definitions for multiple words, or analyze slang usage and voting patterns. Returns word, definition, example, author, upvotes, downvotes, and timestamp. Ideal for linguists, brand researchers, content teams, and cultural trend analysts.
An all-in-one assistant for data analysis and office productivity. Covers end-to-end workflows for data processing, analysis insights, report writing, PPT creation, and data visualization. Always start from an expert perspective and help the user think one step ahead. Proactively confirm with the user when questions are unclear. Supports: Excel data analysis, campaign data review, ROI estimation, data visualization, report generation, PPT creation, formula generation. Use this skill when the user mentions "analyze data", "make a report", "make a PPT", "Excel", "campaign analysis", "ROI", "review", "weekly report", "monthly report", "data processing", "charts", "visualization", "reporting", "tables", "formulas"
Answer questions about spatial data using DuckDB. Use when the user mentions locations, coordinates, lat/lng, distances, maps, addresses, "near", "within", "closest", geographic names, or spatial file formats (GeoJSON, Shapefile, GeoPackage, GPX, GeoParquet). Also triggers when the user wants to find places, buildings, or roads — Overture Maps provides free global data on S3 with zero API keys. Handles spatial joins, distance calculations, containment checks, density analysis, and format conversions for geographic data.
Industry data query and analysis tool. Connects to multiple compliant public data sources, supporting exact matching, fuzzy search, aggregate statistics, grouped sorting and other query methods. It currently covers most scenarios such as basic business registration information, regional indicators for supply chain nodes, supply chain enterprise information, A-share related information and more. The complete list of available data sources and their field structures must be obtained dynamically through the describe_datasource interface. Trigger this Skill whenever the user expresses any intent to query data about enterprises, companies, industries or supply chains. Typical scenarios include but are not limited to: - Querying a company's business registration information (name, legal representative, registered capital, date of establishment, business scope, shareholders, financing history, etc.) - Querying fundamentals, securities information, F10 data, IPO information, dividends, executive information of A-share listed companies - Querying the structure of a supply chain, including node enterprises, regional distribution, statistics of enterprises with various labels (leading, high-tech, specialized and innovative, unicorn, little giant, etc.) - Querying regional supply chain indicators (revenue, assets, profit margin, ROE, intellectual property, bidding data, etc.) - Aggregate statistics or group analysis by region, industry, enterprise label and other dimensions - Any public data query intent such as "look up such and such company", "help me look at this enterprise", "which leaders are in the xx industry" Even if it cannot be determined whether the required data is covered, the data source list interface should be called first to probe, without refusing or guessing directly. Data comes from compliant public channels and is for reference only, not a basis for decision-making.
Assists with SAP HANA Developer CLI (hana-cli) for database development and administration. Use when: installing hana-cli, connecting to SAP HANA databases, inspecting database objects (tables, views, procedures, functions), managing HDI containers, executing SQL queries, converting metadata to CDS/EDMX/OpenAPI formats, managing SAP HANA Cloud instances, working with BTP CLI integration, or troubleshooting hana-cli commands. Covers: 91 commands, 17+ output formats, HDI container management, cloud operations.
Quantify realized risk from historical data using volatility estimators, drawdown analysis, and downside risk metrics. Use when the user asks about historical volatility, maximum drawdown, drawdown duration, historical VaR, downside deviation, semi-variance, or tracking error. Also trigger when users mention 'how risky has this been', 'worst decline', 'Parkinson estimator', 'Yang-Zhang', 'peak-to-trough loss', 'recovery time', 'annualized volatility', or ask how to measure past investment risk.
This skill should be used when the user asks to "write a SQLScript procedure", "create HANA stored procedure", "implement AMDP method", "optimize SQLScript performance", "handle SQLScript exceptions", "debug HANA procedure", "create table function", "inspect a browser-based Datasphere SQL editor with Microsoft Edge CDP", or mentions SQLScript, SAP HANA procedures, AMDP, EXIT HANDLER, or code-to-data paradigm. Comprehensive SQLScript development guidance for SAP HANA database programming including syntax patterns, built-in functions, exception handling, performance optimization, cursor management, and ABAP Managed Database Procedure (AMDP) integration.
Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy. Use when the user asks about market conditions, wants to pick a strategy for current conditions, or before running a backtest/signal that should be regime-aware.
Generate embeddings via npx [email protected] embed text (ONNX all-MiniLM-L6-v2, 384-dim), normalize, and store in HNSW index
Analyzes sales pipeline health, revenue forecasting accuracy, and go-to-market efficiency metrics for SaaS revenue optimization. Use when analyzing sales pipeline coverage, forecasting revenue, evaluating go-to-market performance, reviewing sales metrics, assessing pipeline analysis, tracking forecast accuracy with MAPE, calculating GTM efficiency, or measuring sales efficiency and unit economics for SaaS teams.
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm
Cluster code by graph community detection via npx [email protected] hooks graph-cluster (spectral / Louvain)
Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success. Use when analyzing customer accounts, reviewing retention metrics, scoring at-risk customers, or when the user mentions churn, customer health scores, upsell opportunities, expansion revenue, retention analysis, or customer analytics. Runs three Python CLI tools to produce deterministic health scores, churn risk tiers, and prioritized expansion recommendations across Enterprise, Mid-Market, and SMB segments.
Set up, audit, and debug analytics tracking implementation — GA4, Google Tag Manager, event taxonomy, conversion tracking, and data quality. Use when building a tracking plan from scratch, auditing existing analytics for gaps or errors, debugging missing events, or setting up GTM. Trigger keywords: GA4 setup, Google Tag Manager, GTM, event tracking, analytics implementation, conversion tracking, tracking plan, event taxonomy, custom dimensions, UTM tracking, analytics audit, missing events, tracking broken. NOT for analyzing marketing campaign data — use campaign-analytics for that. NOT for BI dashboards — use product-analytics for in-product event analysis.
Apply when deciding whether VTEX Master Data is the right storage for a given workload, designing JSON Schemas with v-indexed, v-cache, v-security, and v-triggers, planning entity capacity and lifecycle, or auditing existing Master Data usage. Covers when to use MD versus Catalog, OMS, VBase, or external databases, schema design best practices, indexing strategy, trigger patterns, and operational considerations. Use before creating any new Master Data entity.
Embed hierarchical data via npx [email protected] embed text and project into the Poincare ball in user code (no --model poincare flag in 0.2.25)
Explore and query data on S3, Cloudflare R2, GCS, MinIO, or any S3-compatible storage. Use when the user mentions an s3://, r2://, gs://, or gcs:// URL, asks "what's in this bucket", wants to list remote files, preview remote Parquet/CSV/JSON, or query data on object storage without downloading it. Also triggers when the user wants to know the size, schema, or row count of remote datasets.
Model, forecast, and interpret volatility using time-series models and options-implied measures. Use when the user asks about EWMA, GARCH models, implied volatility, volatility surfaces, volatility term structure, or the VIX. Also trigger when users mention 'volatility smile', 'volatility skew', 'realized vs implied vol', 'volatility risk premium', 'vol clustering', 'mean-reverting volatility', 'options pricing inputs', 'RiskMetrics', 'decay factor', or ask how to forecast future volatility for risk management.
Use when structured YouTube data is needed: pasted video/channel/playlist links, transcripts for analysis, video metadata, channel upload history, search results, or playlist contents — without Google API quotas or OAuth. Triggers on YouTube URLs, creator names, topic research, or any request needing YouTube content, even if not mentioned explicitly. Not for uploads, account management, or written-source-only research.
Design and operate data quality programs for financial data — validation rules, pricing validation, data lineage, exception management, profiling, and governance. Use when building validation rules for pricing or client data pipelines, detecting stale prices, designing a data quality monitoring framework, calibrating validation thresholds, implementing data lineage for BCBS 239 or MiFID II, investigating reconciliation breaks or billing errors traced to bad data, preparing for regulatory exams on data accuracy, building data quality scorecards, or defining data stewardship roles. Trigger on: data quality, pricing validation, stale prices, data lineage, data validation, data profiling, exception management, data governance, BCBS 239, data completeness, data accuracy, validation rules, data anomaly, data stewardship, data quality scorecard.
Generate and modify SurrealQL queries to interact with SurrealDB databases. This includes creating and retrieving records, designing and managing schemas, establishing and querying graph relationships, performing live (real-time) queries, and leveraging all unique SurrealQL features for advanced database workflows. Use this skill whenever users need to write, adapt, or troubleshoot SurrealQL statements.
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
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.