Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Drive Google Analytics (GA4), Google Tag Manager, Google Search Console, and BigQuery from chat — tracking plans, GA4 reports, key-event (conversion) setup, custom dimensions and metrics, GTM audits, GSC performance, and GA4 BigQuery export queries. Use when the user wants an analytics audit, a GA4 report, a tracking plan, conversion setup, GTM cleanup, search-performance data, or asks "how is the site performing?" or "are my conversions firing?"
Drizzle ORM targeting SQLite (better-sqlite3, libsql/Turso, bun:sqlite, Cloudflare D1, expo-sqlite, op-sqlite). Covers schema definition (column modes, primary keys, foreign keys, indexes), drizzle-kit migrations (generate vs push, renames, custom SQL), the query builder (selects, upserts, returning, EXPLAIN), the relational query builder (relations(), `with`, partial columns), transactions and `db.batch()`, prepared statements with `sql.placeholder()`, connection pragmas (WAL, foreign_keys, busy_timeout), and Drizzle type inference (`$inferSelect`, `$inferInsert`, `$type<>`, drizzle-zod). Use when writing, reviewing, or refactoring Drizzle code for SQLite. Trigger even if the user doesn't say "performance" — schema/migration choices made now are expensive to reverse later, and SQLite-specific traps (single-writer model, no native booleans/dates, ALTER TABLE limits, FK pragma off by default) catch teams who reach for Drizzle without reading the SQLite docs.
Track user metrics and provide data-driven insights for product decisions. Use when measuring product health, analyzing user behavior, conducting cohort analysis, or optimizing key metrics. Covers acquisition, engagement, retention, revenue metrics, and data-driven decision making.
Threshold-based alerting on Scrapfly account metrics. Wire up rules like "alert me when scrape success rate drops below 95% for 10 minutes" and receive notifications via email, webhook, or in-app. Use when the user asks to "set up an alert", "monitor my scrape success rate", "tell me when my scrapes start failing", "alert on unblocker block rate", "alert on ASP block rate", "watch a specific domain", or any task involving the Scrapfly alerting product. Covers the three call paths: REST API, MCP `alert_*` tools, and the `scrapfly alert` CLI subcommand. Enterprise plan feature
Generate self-contained HTML reports that make analyses, comparisons, research findings, progress, and plans easy to use for decision-making. Use for requests such as “make an HTML report”, “summarize this in a report”, “visualize the comparison”, “show it in a chart”, “make a Gantt chart”, “make it look like a dashboard”, or “make this easier to read”. Choose appropriate formats from KPI, tables, bar, line, scatter, heatmap, waterfall, donut, radar, and Gantt based on the data and relationships to convey, and generate a single accessible, responsive, print-ready HTML file.
Ports existing Databricks notebooks and jobs to Fabric, covering dbutils to notebookutils, secret scopes to Key Vault, DBFS to OneLake, Unity Catalog mapping to schema-enabled Lakehouses, Jobs and Delta Live Tables to Spark Job Definitions and Pipelines, and Photon to the Native Execution Engine. Use whenever Databricks code has to be converted. For Fabric notebook code that is not being migrated, use spark-cli.
Engineering Manager skill for Engineering Managers. Use this skill when the user says: 'engineering dashboard', 'engineering leaders', 'show me the dashboard', 'DORA metrics', 'PR health', 'sprint pulse', 'deployment frequency', 'lead time', 'change failure rate', 'MTTR', 'sprint velocity', 'investment allocation', 'engineering report', 'engineering manager report', or 'daily engineering brief'. Gathers real data from GitHub (via gh CLI), Linear (via zen-linear skill), Jira (via zen-jira skill), and Sentry (via zen-sentry skill). Renders a live HTML dashboard in Zenflow's built-in browser. Also runs automated actions: multi-model PR review, dependency audits, and bug triage.
Use when auditing or recalibrating game balance: build a source-driven Monte Carlo balance lab (Rust + rayon) that extracts live game data, simulates human playstyles (AFK→pro), emits win-rate/economy verdicts with confidence intervals, and bruteforce-tunes parameters. Trigger on unfair levels, unreachable shops, farm exploits, interest-curve cliffs, post-content recalibration, or CI balance JSON diffs. Keywords: balance lab, Monte Carlo, win rate, difficulty curve, economy career, playstyle simulation, Resource extraction, GDScript parser, bruteforce tuning.
Search and recommendation system planning for a two-sided trust marketplace built on OpenSearch — user-intent framing, product-surface architecture, index design, query understanding, retrieval strategy, ranking, search-plus-recs blending, measurement, and a dashboard-and-alerting layer for ongoing decision making. Triggers on tasks involving marketplace search, homefeeds, ranking, relevance tuning, OpenSearch query DSL, analyzers, synonyms, golden sets, NDCG, A/B testing, or diagnosing an existing retrieval system. Use this skill BEFORE marketplace-personalisation when planning new work; hand off when the diagnosed bottleneck is personalisation-specific.
Knowledge base for the 28 ScraperAPI MCP tools. Covers scrape, Google (search, news, jobs, shopping, maps), Amazon (product, search, offers), Walmart (search, product, category, review), eBay (search, product), Redfin (for_sale, for_rent, search, agent), crawler tools, and the AI Parser (create, get_details, parse_url, list, update, delete) for reusable custom extraction. Provides tool selection, parameter optimization, credit cost guidance, and error recovery. Requires the ScraperAPI MCP server and a valid SCRAPERAPI_API_KEY. Trigger on: web scraping, scraping a URL, reading a webpage behind bot protection, Google search queries, current events and news lookup, job listings, product price comparison, shopping research, Amazon/Walmart/eBay product lookup or search, e-commerce data extraction, Redfin real estate listings, property search, rental search, site crawling, custom structured extraction, building a reusable parser, extracting fields from any site, SERP monitoring, SEO tracking, competitive intelligence, or market research. Note: Transmits user-supplied queries, URLs, and content to ScraperAPI.
Universal Strava API integration for fitness data management. Use when working with Strava activities, athlete profiles, segments, routes, clubs, or any fitness tracking data. Triggers on requests to get, create, or update activities, analyze training stats, export routes, explore segments, or interact with Strava data programmatically
Use when you need to add or review Mongock MongoDB data migrations in a Spring Boot application — including Maven coordinates, Spring Data MongoDB drivers, migration scan packages, @ChangeUnit classes, lock/transaction settings, and optional policy-approved MongoDB integration verification. This should trigger for requests such as Add Mongock migrations in Spring Boot; Review Spring MongoDB data migrations; Configure Mongock change units for Spring Data MongoDB; Create Mongock change units for Spring Boot MongoDB; Review Mongock migration ordering in a Spring service. Part of Plinth Toolkit
Expert knowledge for Azure Machine Learning development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using AutoML, Prompt Flow, online/batch endpoints, vector stores/RAG, or Model Catalog in Azure ML, and other Azure Machine Learning related development tasks. Not for Azure Databricks (use azure-databricks), Azure Synapse Analytics (use azure-synapse-analytics), Azure Data Science Virtual Machines (use azure-data-science-vm), Azure HDInsight (use azure-hdinsight).
Trace on-chain money flow via the Etherscan API V2 and write a single Etherscan Flow Case JSON file (nodes + edges). Input: a tx hash, a wallet/contract address, a business/entity scope (“show ENS DAO as a business”), pasted notes/draft, or a user-typed link (gist, tweet/X, article) with addresses and flow claims verified live. Two modes: strict trace for tx/address investigation, and business/entity profile for income/spending/treasury questions. Use when the user says “trace this tx”, “visualize this transaction”, “follow the money”, “build a case for this scam”, “show this DAO's income and spending”, or pastes a 0x hash/address. Output is JSON only; every address, amount and txhash comes from a live API response, never invented. Ethereum by default, other EVM chains supported. Security cases also reconstruct an evidence-backed incident mechanism, confidence, losses, and alternatives. Transport priority: official etherscan CLI, Etherscan MCP, inline apikey=, then other HTTP key sources
Use this skill whenever a question should be answered from documents stored in a LlamaCloud Index v2 knowledge base — retrieving passages, locating indexed files, or searching indexed content through the LlamaParse Platform REST API with curl. Teaches agentic retrieval — navigating an index like a file system instead of one-shot RAG.
Personalisation and recommendation systems for a two-sided trust marketplace built on AWS Personalize — event tracking, dataset and schema design, two-sided matching, cold start, feedback loops, bias control, recipe selection, serving-time re-ranking, observability, and a diagnostic playbook for existing systems. Trigger when designing, building, debugging, reviewing, or improving such a system — and even when the user does not explicitly mention "AWS Personalize" but is working on recommendations, ranking, search, homepage personalisation, or anything that matches seekers and providers across a trust-based catalog.
Expert product analytics strategist for SaaS and digital products. Use when designing product metrics frameworks, funnel analysis, cohort retention, feature adoption tracking, A/B testing, experimentation design, data instrumentation, or product dashboards. Covers AARRR, HEART, behavioral analytics, and impact measurement.
Fetch recent posts from one or more X/Twitter accounts through twitterapi.io, output structured JSON/CSV records, optionally sync records to Feishu/Lark Bitable through feishu-cli, and optionally guide recurring execution through OpenClaw, Codex automations, cron, or launchd. Use when the user wants to monitor X bloggers, collect recent tweets, export tweet metrics, append tweets to Feishu Bitable, or set up a scheduled Twitter/X account tracking workflow.
Use when you need to add or review Mongock MongoDB data migrations in a Micronaut application — including Mongock runner/driver selection, Micronaut bean wiring, migration scan packages, @ChangeUnit classes, lock/transaction settings, and Testcontainers verification. This should trigger for requests such as Add Mongock migrations in Micronaut; Review Micronaut MongoDB data migrations; Configure Mongock change units with Micronaut Data MongoDB; Create Mongock change units for Micronaut MongoDB; Review Mongock migration ordering in a Micronaut service. Part of Plinth Toolkit
Use when reviewing, designing, or modifying Java enterprise systems that process personal data and need GDPR-aware engineering controls. This should trigger for requests such as Review a Java service for GDPR privacy controls; Design data-subject rights workflows; Add retention, deletion, pseudonymization, or privacy-safe logging; Assess data transfer, DPIA, breach evidence, or processor/controller boundary concerns before production release. Part of Plinth Toolkit
Use when reviewing, designing, or modifying Java enterprise systems that may support EU Digital Markets Act gatekeeper-platform concerns, core platform services, interoperability, business-user data access, consent-dependent data combination, ranking, self-preferencing, advertising transparency, or anti-circumvention controls. This should trigger for requests such as Review a Java platform for DMA controls; Design interoperability and business-user data access evidence; Add ranking, consent, preference, or anti-circumvention audit controls; Assess gatekeeper-platform engineering evidence before production release. Part of Plinth Toolkit
A ByteHouse cluster load analysis and performance monitoring tool for analyzing cluster load, monitoring resource usage, analyzing query throughput, and identifying performance bottlenecks. Use this Skill when users need to analyze ByteHouse cluster load, monitor resource usage, analyze query throughput, or identify performance bottlenecks.
A professional A-share market analyst assistant providing daily stock price analysis, stock selection strategies, and investment recommendations. Use for: (1) accessing real-time A-share quotes and historical data; (2) technical analysis (candlestick patterns, MACD, KDJ, RSI, Bollinger Bands, etc.); (3) fundamental analysis (financial metrics, valuation analysis); (4) tracking sector trends; (5) screening stock selection strategies; (6) quantitative factor analysis; and (7) generating daily stock market analysis reports. Trigger when users ask related questions such as “analyze this stock,” “pick stocks today,” “A-share market analysis,” “technical analysis,” “fundamental analysis,” or “quantitative stock selection.”
Build a RAG (retrieval-augmented generation) pipeline or a custom search engine on top of Bright Data's Discover API, using intent-ranked web results and parsed page content as the retrieval/ingestion layer for an LLM or vector store. Use when the user wants to “build a RAG pipeline,” “add web search to my LLM/agent,” “ground my model in live web data,” “build a search engine over the web,” “ingest web content into a vector DB / knowledge base,” or “give my chatbot retrieval.” Covers both live retrieval (Discover at query time as a web-grounded retriever) and ingestion (Discover → chunk → embed → vector store → retrieve). Built on the `discover-api` skill. For a one-off written report use `live-research`; for raw markdown of specific known URLs use `scrape`.
Use Univer (spreadsheet engine) in Node.js backend environments for headless data processing, batch report generation, server-side formula calculation, and automated workbook manipulation. Use when the user needs to create, read, or modify spreadsheets on the server without a browser, run Univer in Node.js, use createUniverOnNode, UniverRPCNodeMainPlugin, child_process fork for formula workers, server-side XLSX/JSON processing, or batch cell operations via Facade API in a backend context. Triggers include “Node.js,” “server side,” “backend,” “headless,” “batch generate,” “automated report,” “createUniverOnNode,” “rpc-node,” “formula worker,” or “Univer in Node”
Use when you need to add or review Mongock MongoDB data migrations in a Quarkus application — including the Quarkiverse Mongock extension, Quarkus MongoDB client configuration, migrate-at-start, @ChangeUnit classes, lock/transaction settings, and Quarkus test verification. This should trigger for requests such as Add Mongock migrations in Quarkus; Configure quarkus-mongock; Review Quarkus MongoDB data migrations; Create Mongock change units for Quarkus MongoDB; Review Mongock migration ordering in a Quarkus service. Part of Plinth Toolkit
Use when reviewing, designing, or modifying Java enterprise systems that expose, exchange, store, process, export, or port data across users, businesses, connected products, cloud providers, APIs, event streams, AI data pipelines, data spaces, or SaaS platforms and need EU Data Act engineering controls. This should trigger for requests such as Review a Java platform for EU Data Act controls; Design data access and portability evidence; Add data-sharing request workflows, export formats, interoperability, metadata, audit logs, cloud-switching support, non-personal data safeguards, or trade-secret handoffs; Assess Data Act engineering readiness before production release. Part of Plinth Toolkit
Use when the user has tabular data (pandas DataFrame, parquet, csv, Arrow, json) and wants to filter, group, aggregate, join, or speed up slow pandas. Provides chDB DataStore — same pandas API, ClickHouse engine underneath. Also handles reading from S3, MySQL, PostgreSQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake as DataFrames and joining across sources. TRIGGER when: user mentions DataFrame, parquet, csv, "fast pandas", "speed up pandas", or cross-source DataFrame joins; user imports `chdb.datastore` or `from datastore import DataStore`. SKIP this skill for raw SQL syntax (use chdb-sql instead), ClickHouse server administration, or non-Python DataStore API work.
Lightweight scanner tracking Smart Money market concentration across all Hyperliquid assets. Flags assets accelerating up the ranks before they become crowded top-3 plays. IMMEDIATE_MOVER signal fires on 10+ rank jumps with quality filters (erratic history, velocity gate, trader count floor, max leverage check). One API call per scan, runs every 60 seconds. Use when detecting SM rotations, finding emerging opportunities early, or monitoring rank acceleration patterns
Choose the right y-axis unit when creating or updating an insight via `posthog:insight-create` or `posthog:insight-update`—for both TrendsQuery (`trendsFilter.aggregationAxisFormat`) and SQL insights (`DataVisualizationNode`, `chartSettings.yAxis[].settings.formatting`). Use when the agent is about to add a `formula` purely to convert units (e.g. dividing seconds by 60 to display minutes), when a `math_property` or SQL column is a duration, currency, ratio, or large count, or whenever the user mentions "format the y-axis", "duration", "seconds", "minutes", "hours", "milliseconds", "ms", "percentage", "%%", "currency", "decimals", "axis label", or "axis unit" in the context of a graph insight.
Inspects URL paths and proposes, tests, orders, and applies project-level path cleaning rules so dynamic segments (numeric IDs, UUIDs, slugs, dates) collapse into readable aliases. Use when the user says "clean the paths", "normalize URLs", "group similar pages", "too many distinct paths", "/users/123 and /users/456 are the same page", "set up path cleaning", or asks why a Web analytics or Paths breakdown is fragmented across thousands of nearly-identical URLs. Covers regex syntax (re2), alias placeholder convention, rule ordering, the test workflow, and applying rules via the path-cleaning-rules-update MCP tool.
Feature engineering for marketplace recommenders — what to extract from raw marketplace assets (listing photos, owner-entered listing metadata, sitter wizard responses) to power item-to-item (similar listings), user-to-item (homefeed ranking), or user-to-user (mutual-fit matching) recommenders. Covers asset auditing, first-principles feature decomposition, vision-feature extraction (CLIP, room-type, amenities, aesthetics), listing text and metadata encoding, sitter wizard design, derived-composition patterns for i2i / u2i / u2u (ANN shelves, two-tower, mutual-fit), feature quality governance (training-serving parity, drift, PII), and incremental value proof (ablation A/B, kill reviews, feature-free baseline). Trigger even when the user does not explicitly say "feature engineering" but is asking how to get more signal out of listing photos, listing metadata, or the sitter onboarding wizard, or how to improve i2i / u2i / u2u quality without blindly ingesting a new model.
RQAlpha is an open-source event-driven backtesting framework from 米筐. It supports A-shares and futures, with a modular, extensible architecture. Use it when users need to quickly backtest A-share or futures strategies, use built-in data (download-bundle), develop Mod plugins, or mention rqalpha or 米筐. Compared with backtrader, rqalpha includes built-in A-share daily data and is easier to install, making it suitable for quick validation; backtrader is more flexible and has a larger community. If users only need data retrieval and do not need backtesting, direct them to data Skills such as baostock/akshare/tushare.
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.