Total 54,069 skills, Data Processing has 2770 skills
Showing 12 of 2770 skills
A股市场机制数据。涨跌停价格、停复牌信息、新股IPO、交易日历、复权因子。 当用户询问"涨跌停""停复牌""新股IPO""交易日历""复权因子"时触发。
Tableau platform help — Tableau Desktop, Tableau Cloud, Tableau Server, Tableau Prep, Tableau Pulse, Embedding API, REST API (v3.28, PAT/JWT auth, 300+ endpoints), MCP server, and Tableau+. Use when dashboards are slow with large datasets, LOD expressions or calculated fields aren't working, licensing costs are confusing or spiraling, Tableau won't connect to Salesforce or your data warehouse, embedded analytics aren't rendering, Tableau Prep flows keep failing, or you need help choosing Creator vs Explorer vs Viewer licenses. Do NOT use for general CRM config (use /sales-salesforce) or sales forecasting methodology (use /sales-forecast).
mParticle platform help — hybrid CDP with real-time event streaming, identity resolution, audience activation, 300+ integrations. Use when mParticle SDK not sending events, identity resolution merging wrong profiles, audience not syncing to destination, connection setup taking too long, Events API returning errors, data plan validation failing, or comparing mParticle pricing tiers. Do NOT use for choosing between CDPs (use /sales-cdp) or CRM data cleanup (use /sales-data-hygiene).
Monitor and analyze real estate market data, generate visual charts, and provide trend analysis and predictions. Use this skill when users mention the following: - Questions related to housing prices, real estate data, and the real estate market - Collecting real estate market data, transaction volumes, and price trends - Generating charts for housing prices, rental prices, or market analysis - Analyzing real estate market trends or making predictions - Specific requests such as "housing price trends", "second-hand housing transactions", "rental prices", "price-to-rent ratio" This skill handles real estate market data collection, visualization, and analysis, primarily targeting Chinese cities (especially Shenzhen), but can be adapted to other markets.
Patterns for DeFi market analysis, screening, and comparison using DefiLlama MCP tools. Covers valuation ratios (P/S, P/F), growth screening with pct_change columns, multi-metric protocol comparison, category comparison, and cross-entity analysis. Use when users ask to compare protocols, screen for undervalued projects, analyze growth trends, or do sector analysis.
Develops and executes Spark code on Dataproc Clusters and Serverless. Reads and writes data using BigLake Iceberg catalogs, BigQuery and Spanner. Debugs execution failures. Use when: - Writing Spark ETL pipelines on GCP. - Training or running inference with ML models with spark on GCP. - Managing Spark clusters, jobs, batches, and interactive sessions. Don't use when: - Writing generic Python scripts that don't use Spark. - Performing simple SQL queries that can be done directly in BigQuery.
Provides guidance for writing, packaging and executing Apache Beam pipelines on GCP using Cloud Dataflow. Use when: - Creating an Apache Beam Dataflow pipeline. - Creating a Google Flex Template.
Reference documentation for live music data APIs and ID mapping between services. Use when integrating MusicBrainz, Setlist.fm, JamBase, Bandsintown, Ticketmaster, or other concert/artist APIs.
Review Kafka schema changes (Avro, Protobuf, JSON Schema) for compatibility and evolution best practices using the Lenses MCP server. Detects breaking changes, missing defaults, schema drift and naming issues. Use when user says "review schema changes", "check schema compatibility", "will this schema break consumers" or asks about schema evolution. Do NOT use for creating new schemas from scratch or registering them in the cluster.
Record transaction flow in accordance with unified rules. Save records by individual stock in Markdown format, and simultaneously write to SQLite for statistics and quantitative review.
InfluxDB Cloud integration. Manage data, records, and automate workflows. Use when the user wants to interact with InfluxDB Cloud data.
Guide the user through connecting a new data warehouse source — Postgres, MySQL, Stripe, Hubspot, MongoDB, Salesforce, BigQuery, Snowflake, and so on. Use when the user wants to "connect Stripe", "import data from Postgres", "add a new data source", "sync my warehouse tables", or wants to pick sync methods for each table. Walks through source-type discovery, credential validation, table discovery, per-table sync_type selection, and the final create call. Also covers picking a good prefix and what to do right after creation.