Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Unified entrypoint for orchestrating the current `volc-flink` CLI for Volcano Serverless Flink tasks. Use for concrete Flink intents such as auth/profile setup, project/resource discovery, catalog inspection, draft creation, SQL/JAR/CDC workflows, job operations, savepoints, sessions, monitoring, diagnostics, and performance investigation.
Combines capital flows for individual stocks, industries, concepts, the broader market, major investors, and large orders to identify flow-driven movements, divergences, and crowding risks. Use when users ask about capital flows, major-investor net inflows, industry or concept flows, unusual capital movements, or need a capital flow monitoring dashboard.
An in-depth analyzer for the Dragon-Tiger List. Identifies active-trader seats, assesses the contest between institutions and active traders, and compares lists in the same sector to find standout leaders. Use when the user asks “Who is buying this stock?”, “What’s happening with the recent Dragon-Tiger List?”, “Did X active trader make the list?”, or “Is this X’s stock?”
Use kalodata data to query TikTok e-commerce product rankings and retrieve details for a specific product. Browse top-ranked and best-selling products by region, currency, language, and date range, and use productId to get the price range, sales volume, revenue, commission rate, listing and delisting times, and associated store. Trigger this skill when the user mentions TikTok product rankings, TikTok bestseller charts, TikTok top products, kalodata product rankings, TikTok product details, kalodata product details, product prices, product sales, TikTok product ranking, TikTok bestseller chart, TikTok top products, kalodata product rank, TikTok product detail, kalodata product detail, or product analytics. Even if the user does not explicitly mention “kalodata,” trigger this skill whenever they want to view TikTok product rankings or detailed data for a TikTok product.
Translates beliefs (probabilities) into optimal actions (bet/pass/hedge) using quantitative frameworks including edge calculation, Kelly Criterion bet sizing, forecast extremizing, and Brier score optimization. Use when converting probabilities into decisions, calculating edge against market odds, sizing bets optimally, extremizing aggregated forecasts, improving Brier scores, or when the user mentions betting strategy, Kelly Criterion, edge calculation, Brier score, extremizing, or translating belief into action.
Extract structured fields, sections, figures and tables, source locations, missing items, and supportable conclusions from paper PDFs and supplementary materials. Can also create a Paper Case with a hash and a phased in-depth reading report. Use when the user asks to “extract this paper,” “extract information from papers in bulk,” “make a paper card,” “read a PDF in depth,” “extract figures and tables,” or create a “phased in-depth reading report.” Runs without a private local workspace or preset research lab; use user-provided material and bundled public-source methods.
Audit the health of a PostHog project's data warehouse sources and syncs — find every broken or degraded source connection, sync schema, and webhook channel. Use when the user asks "why are my imports failing?", "what's broken with my sources?", "why is my warehouse data stale?", or wants a one-shot triage of source/sync health before deciding where to dig in. Produces a prioritized report grouped by severity, with recommended next steps. For materialized-view health use `auditing-warehouse-view-health`; for a single failing sync use `diagnosing-failed-warehouse-syncs`.
Audit the health of a PostHog project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views that cost storage and compute. Use when the user asks "which of my views are broken?", "why is this materialized view failing?", "are any of my views wasting compute?", or wants a one-shot triage of view health. For source/sync health use `auditing-warehouse-source-health`.
Use when adding/modifying database columns, encountering "FOREIGN KEY constraint failed", "no such column", "cannot add NOT NULL column" errors, or creating schema migrations for SQLite/GRDB/SQLiteData - prevents data loss with safe migration patterns and testing workflows for iOS/macOS apps
D3.js data visualization skill based on Edward Tufte principles. Selects the right chart type from a large catalogue by analyzing the data question, then generates single-file HTML with D3 v7, dark theme, responsive layout, direct labels, and annotations.
Create custom data visualizations with D3.js: bar, line and scatter charts, chord diagrams, heatmaps, force-directed networks and geographic maps, with proper data binding, scales, axes, transitions and interactivity. Works in React, Vue, Svelte or vanilla JavaScript.
Use Exa Agent for multi-step web research, list-building, enrichment, structured output, run continuation, and coverage validation. Exa Agent can access additional data providers: fiber, financial_datasets, similarweb, baselayer, affiliate, particle, and jinko.
Identify, measure, and exclude bot / crawler / AI-agent traffic in PostHog web and product analytics using the traffic classification surface (the isLikelyBot / getTrafficType HogQL functions and the $virt_* virtual properties). Use when the user asks to "exclude bots", "filter out crawlers", "remove bot traffic from my numbers", "how much of my traffic is bots / AI crawlers", "is GPTBot / ChatGPT / Claude hitting my site", "break down traffic by human vs bot", or wants clean human-only counts in an insight or dashboard. For the real-time Live tab bot tiles, use exploring-live-traffic instead.
Database patterns for Go services: database/sql, connection management, transactions, migrations, query builders, and ORM usage (sqlc, GORM, ent). Use when: "database access", "SQL query", "connection pool", "transactions", "database migration", "sqlc", "GORM", "ent", "prepared statement", "repository pattern". Not for: in-memory structures (go-data-structures), SQL security (go-security-audit), query profiling (go-performance-review)
Search and analyze TikTok Shop store (seller) data. Filter stores by region, category, GMV over the past 30 days, sales trends, listing time, and local or cross-border status. Returns metrics including sales volume, revenue (GMV), followers, rating, review count, positive review rate, delivery rate, response rate, affiliate creators, promotional videos, livestreams, and products in the store, across 16 TikTok Shop sites. Trigger on mentions of TikTok store search, seller analytics, TikTok Shop store rankings, store sales, store GMV, stores promoting products, EchoTik store data, TikTok Shop seller search, TikTok shop list, TikTok seller analytics, EchoTik seller, or TikTok store data. Trigger even without explicit mention of “EchoTik” or “TikTok” if the request involves filtering or analyzing TikTok Shop store/seller performance metrics.
Query the list of products currently for sale in a TikTok Shop store (seller). Use sellerId to retrieve all products and return metrics including product title, price, sales volume and revenue (GMV) across multiple periods (1/7/15/30/60/90 days and total), rating, review count, commission rate, listing time, sales method, and category. Trigger on mentions of TikTok store products, products for sale, seller product lists, product selection, what a store sells, store product analysis, EchoTik store products, TikTok Shop seller products, TikTok store products, TikTok seller product list, or EchoTik store product list. Trigger even without explicit mention of “EchoTik” or “TikTok” if the request involves viewing products for sale in a known TikTok Shop store (known sellerId) and their sales, pricing, or commission performance.
Search and analyze TikTok video data. Filter videos by region, creator, product, category, views, duration, posting time, and whether they feature product promotion, paid promotion, or AI video. Returns metrics such as views, likes, comments, shares, saves, video sales, and GMV across 16 TikTok Shop sites. Trigger on mentions of TikTok video search, video lists, promotional videos, video data, views, sales, analytics, EchoTik videos, TikTok video search, TikTok video list, TikTok video analytics, TikTok promotional videos, TikTok video views, or TikTok video engagement. Trigger even without explicit mention of “EchoTik” or “TikTok” if the request involves searching or analyzing TikTok video performance metrics by criteria.
Discover popular new products in 16 TikTok Shop regional markets using EchoTik new product ranking data. Trigger this skill when users mention TikTok new product rankings, TikTok best-selling products, TikTok Shop hits, short-video e-commerce product selection, TikTok new product discovery, cross-border TikTok product selection, TikTok new product rankings, TikTok bestsellers, short-video product selection, TikTok viral products, new product ranking, or TikTok product trends. Trigger it even if the user does not explicitly mention “EchoTik” or “new product rankings”, as long as their request involves finding hot new products or emerging product trends on TikTok Shop.
Query TikTok Shop store (seller) details. Use sellerId to retrieve a complete profile for one store, including total sales; sales volume and revenue (GMV) across multiple periods (1, 7, 30, and 90 days); follower count, rating, review count, positive review rate, delivery rate, response rate, number of products in the store, creator count, shoppable video count, livestream count, price range, product categories, estimated listing time, and other metrics. Trigger this skill when the user mentions TikTok store details, TikTok seller details, TikTok store analysis, TikTok store data, TikTok store profile, TikTok Shop store detail, TikTok seller detail, or EchoTik store profile. Even if the user does not explicitly mention “EchoTik” or “TikTok,” trigger this skill whenever they want the complete details or profile of a TikTok Shop store and know its sellerId.
Search TikTok e-commerce store rankings using kalodata data and retrieve details for a specified store. Browse top-ranked, high-sales TikTok Shop stores by region, currency, language, and date range. Use shopId to retrieve revenue, sales volume, products for sale, revenue from self-operated, distribution, and marketplace channels, and creator collaborations. Trigger on mentions of TikTok store rankings, top-selling TikTok stores, TikTok Shop leaderboards, kalodata store searches or rankings, TikTok store details, store revenue or sales, TikTok shop ranking, TikTok shop leaderboard, TikTok top shops, TikTok store ranking, TikTok shop detail, TikTok store detail, or kalodata shop search/detail. Trigger even without explicit mention of “kalodata” if the request involves viewing TikTok store rankings or detailed data for a TikTok store.
Check the evidence, biases, alternative explanations, and reporting limits required by research conclusions before execution or submission. Use when the user asks “审我的研究设计”, “当严格审稿人”, “攻击这个结论”, or requests the rw-research-referee workflow. Runs without a private local workspace or preset research lab; use user-provided material and bundled public-source methods
Use right after a Keboola semantic-context tool returns, when building an app, query, report, or transformation from a semantic model. Ground the SQL in the model's own physical mapping (dataset `tableId`/`fqn`, metric SQL) and confirm the real columns before writing any query — do not build SQL from the business-facing display names.
Clarify how to visualize change over a time range before building a trend. Use whenever the user asks how much something changed, grew, dropped, improved, or regressed between two points or periods — "how much did X change from A to B", "before vs after", "start vs end", "week over week", "compare this month to last", "change over time" — or mentions a "slope chart" / "slopegraph". Two readings of "change" need different charts: the whole trend (a line, every interval) versus just the two endpoints (a slope, start vs end). Ask which they want, then render it. Not for choosing a saved insight ChartDisplayType in the insight editor.
Data discovery and analysis specialist focused on extracting actionable insights from complex datasets, identifying patterns and anomalies, and transforming raw data into strategic intelligence. Excels at multi-source data integration, advanced analytics, and data-driven decision support.
Guides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, drilling into individual recordings, and turning real, corroborated issues into PostHog tasks, insights, or an investigating-replay hand-off.\nTRIGGER when: user wants to pull/read/triage Replay Vision observations, asks \"what has my scanner found\", wants to act on or summarize scanner findings, turn observations into tasks/work, or points at a /replay-vision/<scanner-id> URL.\nDO NOT TRIGGER when: creating or sizing a scanner (use creating-replay-vision-scanners), running a one-off scan you don't then analyse, or authoring a signals scout.
Query blockchain data across 40+ chains using Flipside's AI agents. Use when working with blockchain data, crypto wallets, DeFi protocols, NFTs, token transfers, or on-chain analytics. Requires the Flipside CLI (https://docs.flipsidecrypto.xyz/get-started/cli)
Deeply analyzes Amazon niches by product ASIN, covering monopoly level, brand concentration, new product success rate, and market opportunity score. Trigger this skill when users mention niche analysis by ASIN, ASIN market research, finding the niche for an ASIN, monopoly assessment, brand concentration analysis, new product success rate, market demand score, competitive landscape, Amazon submarket exploration, ASIN niche analysis, niche by ASIN, monopoly level, brand concentration, new product success rate, market opportunity score, competitive landscape, or Jiimore data. Even if the user does not explicitly mention “niche” or “ASIN,” trigger this skill whenever their request involves assessing the competitive landscape, brand density, or opportunity potential of the niche associated with a product ASIN.
PostgreSQL 18+ enterprise best practices for database development. USE THIS SKILL WHEN THE USER: - Creates schemas, tables, functions, procedures, or triggers - Writes PL/pgSQL code (naming conventions: l_, in_, io_, co_ prefixes) - Implements Table API (SECURITY DEFINER functions, schema separation) - Manages migrations, indexes, constraints, or query performance - Works with PostgreSQL 18+ features (uuidv7, virtual columns) - Builds Medallion Architecture data warehouses (Bronze/Silver/Gold) - Reviews code for anti-patterns or migrates from Oracle PL/SQL CORE PATTERNS: - Three-schema separation: data (tables) → private (internal) → api (external) - Table API: All access via SECURITY DEFINER with SET search_path - Native PL/pgSQL migration system (no Flyway/Liquibase needed) - Trivadis naming: l_ (local), in_ (input), io_ (inout), co_ (constant)
Manage the full lifecycle of Alibaba Cloud EMR Serverless Spark workspaces—create workspaces, submit jobs, Kyuubi interactive queries, resource queue scaling, and status queries. Use this Skill when users want to create Spark workspaces, submit Spark jobs, view job status and logs, execute SQL via Kyuubi, scale resource queues, or view workspace status. Also applicable when users say "create a Spark workspace", "submit Spark job", "run PySpark", "execute SQL via Kyuubi", "scale resource queue", "view job logs", etc.
Expert knowledge for Azure Analysis Services development, including troubleshooting. Use when resolving server connectivity, firewall/VNet, DNS, client connection, or network error issues, and other Azure Analysis Services development tasks. Not for Azure Synapse Analytics (use azure-synapse-analytics), Azure SQL Database (use azure-sql-database), Azure SQL Managed Instance (use azure-sql-managed-instance), or SQL Server on Azure Virtual Machines (use azure-sql-virtual-machines)
Convex backend specialist. Use this agent for any code inside a `convex/` directory — function definitions, schemas, indexes, queries, mutations, actions, HTTP endpoints, cron jobs, file storage, auth wiring, and component installation. Knows the object-form function syntax, validator patterns, resource limits, and component ecosystem that generic Claude routinely gets wrong.
Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates, plus the tool-centric pivot (capture rate per intent, discovery rate against the advertised catalog, description fit, tool overlaps). Use when the user asks "what are agents trying to do with the MCP?", "group the intents", "which goals fail most?", "what does each cluster route to?", "when agents have this intent do they find my tool?", "which tools get mixed up?", wants to recompute the clustering, or pastes an MCP analytics intent-clustering URL.
Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use when the user asks "what did this MCP session do?", "show me the tool calls for session X", "what was the agent's goal?", "which sessions had errors?", "who is connecting to my MCP?", or pastes an MCP analytics sessions URL.
Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool has the highest error rate?", "what's the slowest tool?", "which tools fail most often?", "how reliable is tool X?", wants a tool-quality matrix, or pastes an MCP analytics tool-quality / dashboard URL and asks what it shows.
On-chain DEX market data queries via Gate: token prices/价格, K-line/OHLC candlestick charts, token rankings, security risk audits, new token discovery, holder analysis, and trading volume stats. Read-only — no transactions. Use when the user asks for 'token price', 'price of ETH', 'check SOL price', '查价格', 'K线', 'candlestick', 'OHLC', 'top gainers', 'trending tokens', 'is this token safe', 'honeypot check', 'new tokens', 'trading volume', or 'liquidity events'. Do NOT use for swap/trade execution (use gate-dex-trade) or wallet balance/account queries (use gate-dex-wallet).
Football data analytics entry point. Use for any task involving football data: xG, match or player stats, scouting, shot maps, scraping FBref, Understat, or Transfermarkt, judging players or teams from stats. Routes to the right nutmeg skill and handles first-time setup.
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.