Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.
Drive a Metabase instance from the terminal via the `mb` CLI: auth profiles, databases and schemas, schema sync and field-values rescan, tables, fields, cards (questions, models, metrics) run as JSON/CSV/XLSX, dashboards and dashcards, collections and their tree, snippets, segments, measures, transforms and transform-jobs, settings, search, git-sync. Use for any Metabase operation from the terminal: "log into metabase", "what profiles do I have", "list cards", "run card 42 as CSV", "create a transform", "list dashboards", "move a dashcard", "list collections", "what's in collection 4", "show the collection tree", "list snippets", "create a segment", "archive a measure", "search metabase for X", "import the latest changes", "add a directory to git sync", "set a setting", "what schemas are in this database", "trigger a sync", "rescan field values", or any `mb <verb>`. Whole data jobs go to `rde`.
Install, troubleshoot, and use Scrapling CLI to extract HTML, Markdown, or text from webpages. Use this skill whenever the user mentions Scrapling, `uv tool install scrapling`, `scrapling extract`, WeChat/mp.weixin articles, browser-backed page fetching, or needs help deciding between static and dynamic extraction.
Quantitative trading data analysis tool. Real-time quotes for A-shares, US stocks, Hong Kong stocks and precious metals, multi-dimensional scoring (technical + capital flow + fundamentals), limit-up/limit-down pool, northbound capital, minute-level capital flows. Use when: (1) querying real-time quotes and scores for any stock, (2) analyzing unusual limit-up/limit-down moves in A-shares, (3) checking northbound capital flows, (4) quotes for US stocks, Hong Kong stocks and precious metals, (5) global market overview, (6) stock-level capital flow analysis.
NetSuite Intelligence skill — teaches AI the correct tool selection order, output formatting, domain knowledge, multi-subsidiary and currency handling, and SuiteQL safety checklist for any AI + NetSuite AI Service Connector session.
Scrapes Google search results for any query using apidojo's Google Search scraper on Apify. Triggers when the user asks to: get Google search results for a keyword, scrape SERP data for a query, export Google results to a dataset, fetch URLs and snippets from Google for a search term, get all results from a Google search, or collect Google SERP data for multiple keywords. Returns URL, title, snippet, position, and SERP feature type per result. Ideal for SEO analysts, researchers, journalists, and competitive intelligence teams.
Extracts YouTube channel metadata, subscriber counts, video counts, and descriptions using apidojo's YouTube Channel Scraper on Apify. Triggers when the user asks to: get YouTube channel information, scrape YouTube channel stats, fetch subscriber count for a YouTube channel, export channel metadata in bulk, find YouTube channels by keyword, get channel descriptions and tags, check if a YouTube channel is verified, or research YouTube channels by niche. Returns channel name, subscriber count, video count, description, verification status, and keywords per channel. Ideal for influencer researchers, competitive analysts, and YouTube marketers.
Tracks and compares competitor follower growth across social platforms using apidojo's scrapers on Apify. Triggers when the user asks to: compare competitor social media growth, track how fast a competitor is growing on Twitter, TikTok, or Instagram, benchmark social media performance against competitors, monitor competitor follower counts over time, analyze a competitor's social media strategy, build a competitive social media analysis report, or see which competitor is winning on social. Returns platform, handle, follower count, growth indicators, and engagement benchmarks per competitor. Ideal for competitive intelligence analysts, CMOs, and growth strategy teams.
Benchmarks and compares Instagram influencer engagement rates using apidojo's Instagram scraper on Apify. Triggers when the user asks to: compare engagement rates of Instagram accounts, check if an influencer has real or fake followers, analyze Instagram account performance metrics, benchmark a creator against competitors on Instagram, find Instagram accounts with unusually high or low engagement, verify influencer stats before a paid partnership, or audit an Instagram account's post performance. Returns follower count, average likes, average comments, engagement rate, and recent post performance. Ideal for influencer agencies, brand marketing teams, and campaign performance analysts.
Write, review, and rewrite Django migrations for PostgreSQL with zero-downtime guarantees. Use this skill whenever the user mentions migrations, Django schema changes, or deployment safety — even if they don't say "zero downtime" explicitly. Trigger on: "review this migration", "is this migration safe?", "write a migration for...", "rewrite this migration", "how do I add a NOT NULL column / drop a column / add an index / rename a column / add an FK without downtime", "will this migration cause locks?", "this migration is blocking production". Covers: SeparateDatabaseAndState two-file splits, AddIndexConcurrently, FK NOT VALID + VALIDATE, db_default for NOT NULL columns, lock_timeout, and RunPython safety rules.
Pro+ subscription required. Tenant-wide Power Automate monitoring using the FlowStudio MCP cached store: failure rates, run-health trends, maker/app inventory, inactive owners, and compliance/health reports. Use only for aggregated tenant views. For one environment, one flow, run control, or root-cause debugging, use flowstudio-power-automate-mcp, flowstudio-power-automate-debug, or the server monitor-flow bundle. Requires FlowStudio for Teams or MCP Pro+.
Monitors trending topics and conversations in a specific niche on Twitter using apidojo's Twitter Search scraper. Triggers when the user asks to: monitor trending topics in a niche on Twitter, track what's being discussed in an industry on X right now, find emerging conversations in a sector on Twitter, see what topics are trending in a specific community, track real-time buzz around a business topic on Twitter, or identify breaking trends before they hit mainstream media. Returns trending topics, tweet velocity, engagement signals, and top voices in the trend. Ideal for social media managers, PR teams, and real-time content strategists.
Explains how to query PostHog data, defaulting to typed runners for supported product analytics. Read it before you write HogQL/SQL. Also read it before you call execute-sql against PostHog. Use it to find or aggregate PostHog entities. These entities include insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, warehouse data, and persons. Use it for trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, and LLM traces. Before you calculate a governed business or telemetry measure, check system.information_schema.metrics for an approved definition. Examples include MRR, activation, billable usage, active organizations, and failure rates. Use the approved definition before you derive a measure from raw events or use a typed domain tool. It also covers HogQL differences, system table schemas, functions, query examples, and schema discovery
Extracts tweets, reply threads, and engagement metrics from a specific Twitter/X profile using apidojo's Twitter Profile Scraper on Apify. Triggers when the user asks to: get all tweets from a Twitter account, scrape tweets from a specific user's profile, export tweet history from a Twitter handle, get recent tweets from a Twitter account with engagement stats, fetch tweet timeline for a specific user, or collect posts from a Twitter profile by username. Returns tweet text, likes, retweets, replies, views, bookmarks, and author info per tweet. Ideal for social media monitors, journalists, and competitive intelligence teams.
Use when YouTube data is needed without Google API quotas or OAuth setup: transcripts, video metadata, channel info, search results, playlists. Triggers on pasted YouTube links, creator names, @handles, topic research, video summaries, channel browsing, or any request where YouTube content would help — even if not mentioned explicitly. Not for uploads, account management, or written-source-only research.
Extracts all videos from a YouTube playlist using apidojo's YouTube Playlist Scraper on Apify. Triggers when the user asks to: get all videos from a YouTube playlist, scrape a YouTube playlist for video data, export playlist video metadata, fetch video stats from a YouTube playlist URL, collect all videos in a YouTube channel playlist, download YouTube playlist contents, or analyze a curated list of YouTube videos. Returns video title, URL, view count, like count, duration, channel info, and description per video. Ideal for content curators, educators, and YouTube channel analysts.
Serverless vector and raster tiles with PMTiles for MapLibre GL JS — single-file format, HTTP range requests, hosting on S3/R2/GitHub Pages, generating with Planetiler or tippecanoe, and the pmtiles protocol. Use when you need no tile server or want to host tiles from static storage.
Use the Docyrus CLI (`docyrus`) to interact with the Docyrus platform from the terminal. Use when the user asks to authenticate, list apps, query or manage data records (`ds`), manage dev app data source schema objects (`studio`) including data sources, fields, enums, data views, forms, webforms, HTML/PDF export templates, and email templates, manage automations and their triggers/action nodes (`automation`), build or edit custom AI agents and their sub-resources (`agent`), set an app's AI agent context or manage app-scoped AI tools (`apps`), list tenant email accounts and send emails (`messaging`), manage tenant account settings — brands, the current user's profile, and tenant regional/formatting preferences (`account`), discover and call connectors (`connect`), send API requests, switch tenants/accounts, discover tenant OpenAPI specs, drive browser automation (`browser`), chat with platform agents (`docy`), launch the pi cowork/coding agents (`worky`/`cody`/`coder`), run the agent bridge server (`server`), manage the repo knowledge graph (`knowledge`) and project plan (`project-plan`), cut releases (`release`), or use the terminal UI via `docyrus tui`. Triggers on `docyrus ds list`, `docyrus ds comments`, `docyrus ds files upload`, `docyrus studio`, `docyrus studio search-fields`, `docyrus automation`, `docyrus automation create-node`, `docyrus agent`, `docyrus apps create`, `docyrus apps set-agent-context`, `docyrus apps ai-tools`, `docyrus messaging email send`, `docyrus account brands`, `docyrus account user-profile`, `docyrus account tenant-preferences`, `docyrus connect`, `docyrus discover`, `docyrus auth`, `docyrus browser`, `docyrus knowledge`, `docyrus project-plan`, `docyrus release`, `docyrus server`, `docyrus tui`, or any terminal-based Docyrus workflow.
Extracts and analyzes TikTok comments from any video or creator using apidojo's TikTok Comments scraper on Apify. Triggers when the user asks to: scrape TikTok comments from a video, analyze what viewers say about a TikTok post, extract comment data for sentiment analysis, find top comments on a viral TikTok video, collect TikTok user feedback from comments, build a dataset of TikTok community reactions, study audience sentiment on TikTok content, or research what a target audience cares about from TikTok comments. Returns commenter username, comment text, likes on comment, reply count, and timestamp. Ideal for market researchers, brand managers, content creators, and academic researchers.
Extracts comments from Instagram posts using apidojo's Instagram Comments Scraper on Apify. Triggers when the user asks to: get all comments on an Instagram post, scrape Instagram comment data, export comments from an Instagram URL, fetch comment text and engagement from Instagram posts, collect commenter usernames from a post, or download audience reaction data from Instagram content. Returns comment text, like count, reply count, commenter username, verified status and timestamp. Ideal for sentiment analysts, community managers and social media researchers.
Use when the user asks about RevenueCat data, analytics, charts, or KPIs — querying charts with get-chart-options-schema and get-chart-data, interpreting subscription metrics, or sharing dashboard chart links. For forecasts, projections, or run-rates, use revenuecat-forecasting.
Scrapes all members and their profile data from any public Twitter/X list using apidojo's Twitter List scraper on Apify. Triggers when the user asks to: get all members of a Twitter list, export accounts in a Twitter list, scrape profiles from a curated Twitter list, fetch the usernames in a public Twitter list, download data from a Twitter list URL, or collect profile stats for everyone on a list. Returns username, bio, follower count, and profile metadata for each list member. Ideal for competitive intelligence teams, curators, and list-based outreach pipelines.
CCXT cryptocurrency exchange library for TypeScript and JavaScript developers (Node.js and browser). Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors. Use when working with crypto exchanges in TypeScript/JavaScript projects, trading bots, arbitrage systems, or portfolio management tools. Includes both REST and WebSocket examples.
Scrapes TikTok videos for any hashtag or keyword using apidojo's TikTok scraper on Apify. Triggers when the user asks to: get all TikTok videos for a hashtag, scrape TikTok content by topic or tag, export TikTok video data for a keyword, fetch TikTok posts under a challenge or trend, collect TikTok video metrics for a hashtag, or download TikTok video metadata by tag. Returns video URL, view count, like count, comment count, share count, author handle, caption, and timestamp per video. Ideal for trend researchers, data analysts, and social media teams.
Use for Deepline SDK/CLI V2 GTM work: route, build, run, debug, and export durable plays; find companies or contacts; enrich email, phone, LinkedIn, or custom signals; migrate Clay-like tables; configure cron/webhook/API plays; control Deepline spend; and recover from play/tool shape failures. Triggers on deepline CLI work, CSV enrichment, prospecting, waterfalls, outbound lists, provider routing, play authoring, SDK V2 syntax, staleAfterSeconds, datasets, and eval-style GTM tasks.
Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline', 'gst-launch pipeline', 'process video with detection', 'build a pipeline', or any request involving GStreamer/DeepStream elements (nvinfer, nvstreammux, nvtracker, etc.).
Use the Alchemy CLI (`@alchemy/cli`) for live blockchain data, transaction lookups, NFT/token/portfolio queries, simulation, tracing/debugging, contract reads/writes, wallet-signed sends, swaps and cross-chain bridges, Solana RPC/DAS plus wallet sends, webhook management, and Alchemy app administration. Preferred runtime path for live agent work (querying, admin, local automation) when the CLI is installed locally — or when both CLI and MCP are available. If neither is installed, install the CLI with `npm i -g @alchemy/cli`. Use for live agent work in this session, not for building application code that ships to production. For application code, use the `alchemy-api` skill (with API key) or `agentic-gateway` skill (without).
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, distributed SQL database, serverless PostgreSQL-compatible database, migrate to DSQL, DSQL query plan, DSQL EXPLAIN ANALYZE, DSQL ENUM, DSQL foreign key, DSQL OCC retry, DSQL multi-region, DSQL JSONB, DSQL GIN index, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.
Extracts Instagram user profiles, followers, and following lists using apidojo's Instagram User Scraper on Apify. Triggers when the user asks to: find Instagram users by keyword or name, get follower lists for Instagram accounts, get following lists for Instagram accounts, export Instagram profile data in bulk, fetch public email addresses from Instagram business profiles, search for Instagram users by username or handle, or build a dataset of Instagram account metadata. Returns username, follower count, bio, post count, verification status, public email, and more. Ideal for influencer researchers, outreach teams, and competitive intelligence analysts.
This Skill is built on authoritative databases and the latest underlying market data from East Money, and supports natural-language queries for market data (real-time quotes, main fund flows, and valuations for stocks, industries, sectors, indices, funds, and bonds), financial data (basic listed company information, financial indicators, executive information, main business, etc.), and relational and operational data (relationships, business operations). It prevents models from answering financial data questions with outdated knowledge and provides authoritative, timely financial data.
Interact with Excel files (.xlsx, .xlsm, .xlsb, .xls, .ods) using the agent-xlsx CLI for data extraction, analysis, writing, formatting, visual capture, VBA analysis, and sheet management. Use when the user asks to: (1) Read, analyse, or search data in spreadsheets, (2) Write values or formulas to cells, (3) Inspect formatting, formulas, charts, or metadata, (4) Take screenshots or visual captures of sheets, (5) Export sheets to CSV/JSON/Markdown, (6) Manage sheets (create, rename, delete, copy, hide), (7) Analyse or execute VBA macros, (8) List/export embedded objects (charts, shapes, pictures), (9) Check for formula errors, or (10) Any task involving Excel file interaction. Prefer over openpyxl/pandas scripts — faster, structured JSON optimised for AI.
Specifies what questions a dashboard must answer and the metrics, visualizations, filters, and data sources it needs, so data teams build something that informs decisions rather than displaying numbers. Use when requesting a dashboard or formalizing ad-hoc reporting. For the event tracking that feeds the dashboard, use measure-instrumentation-spec instead; instrument first, visualize second.
Designs an A/B test or experiment with variants, success metrics, sample size, and duration for an existing hypothesis. Use when planning an experiment to validate a product change or test an assumption you have already framed. To articulate the hypothesis itself first, use define-hypothesis.
Scrapes tweets matching any keyword, hashtag, phrase, or boolean query using apidojo's Twitter Search scraper on Apify. Triggers when the user asks to: scrape tweets about a topic, fetch tweets containing a keyword or hashtag, export Twitter search results to a dataset, get all tweets mentioning a phrase, pull recent tweets for a search term, or collect tweet data for analysis or research. Returns tweet text, author, likes, retweets, replies, timestamp, and tweet URL per result. Ideal for researchers, data analysts, journalists, and social listening teams.
Monitors Instagram hashtag performance and trends using apidojo's Instagram scraper on Apify. Triggers when the user asks to: track Instagram hashtag performance, monitor trending hashtags in a niche on Instagram, find the best hashtags for a content category, analyze hashtag reach and engagement on Instagram, discover new hashtags gaining traction in an industry, compare hashtag performance for a brand, or build an optimal Instagram hashtag strategy for a post. Returns hashtag volume, avg engagement per post, growth trend, and top-performing posts per tag. Ideal for Instagram content creators, social media managers, and brand content teams.
NFL data via ESPN public endpoints plus an nflverse backend for schedules, weekly rosters, play-by-play, and normalized player/team stat tables. Zero config, no API keys. Use when: user asks about NFL scores, standings, team rosters, schedules, game stats, box scores, play-by-play, injuries, transactions, betting futures, depth charts, team/player statistics, NFL news, or which players are trending in fantasy adds/drops. Don't use when: user asks about football/soccer (use football-data), college football (use cfb-data), or other sports.
Analyzes TikTok hashtag performance, reach, and trending content using apidojo's TikTok scraper on Apify. Triggers when the user asks to: analyze a TikTok hashtag, find trending hashtags on TikTok in a niche, see which hashtags perform best for a content type, compare hashtag reach and total view counts on TikTok, identify viral content under a hashtag, research TikTok hashtag strategy for a campaign, find which hashtags a competitor uses most, or determine the best hashtags to use for a TikTok post. Returns hashtag name, total views, top video stats, top creators, and engagement benchmarks. Ideal for social media managers, content strategists, and TikTok growth consultants.
Export and sync Douban (豆瓣) book/movie/music/game collections to local CSV files via Frodo API. Supports full export (all history) and RSS incremental sync (recent items). Use when the user wants to export Douban reading/watching/listening/gaming history, back up their Douban data, set up incremental sync, or mentions 豆瓣/douban collections. Triggers on: 豆瓣, douban, 读书记录, 观影记录, 书影音, 导出豆瓣.
Implement Syncfusion React Charts component for data visualization. Use this when creating charts, configuring axes and series, or customizing visualization styles. This skill covers chart types, data binding, user interactions, financial indicators, accessibility features, and professional data visualization in React applications.
Discovers restaurant brands, food businesses, and hospitality accounts on Instagram using apidojo's Instagram Scraper on Apify. Triggers when the user asks to: find restaurant brands on Instagram, discover food businesses for outreach on Instagram, build a list of restaurant Instagram accounts, find cafes or food chains active on Instagram, identify local restaurant brands by hashtag or location on Instagram, or prospect food and beverage businesses via their Instagram presence. Returns account handle, follower count, bio, post count, and engagement data. Ideal for food tech SaaS vendors, beverage distributors, and B2B service providers targeting restaurants.
Specifies what analytics events to track, when they fire, and what properties to include, as a contract between product and engineering that prevents undertracked features. Use before engineering builds a feature or when auditing existing tracking for gaps. For the dashboard built on top of these events, use measure-dashboard-requirements instead.
Build and query Kusto graphs from natural language. Covers transient graphs (make-graph), persistent graph models/snapshots, pattern matching (graph-match), shortest paths, connected components, and graph-to-table export. Generates the edges-first thinking: define edges, define node lookups, union, make-graph. WHEN: make-graph, graph-match, graph-shortest-paths, graph-to-table, graph-mark-components, persistent graph, graph model, graph snapshot, build a graph from data, find paths between nodes, pattern matching in graph, connected components, transient graph, Kusto graph, KQL graph.
Compose IRQL (Incident Response Query Language) queries for Kusto cybersecurity investigations. Translates natural language hunting questions into composable IRQL pipelines using Get_*, Extract_*, and Enrich_* functions. WHEN: IRQL query, security hunt, threat hunting KQL, incident response query, compose hunting pipeline, failed logins, phishing investigation, lateral movement, process execution, file creation events.
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.