reverse-etl-and-operational-data-serving
Guides agents through reverse ETL and operational data serving workflows. Use when sending curated warehouse data to business systems, SaaS tools, APIs,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Data & analytics
17,214 results
spark-and-distributed-processing
Guides agents through batch and distributed data processing design. Use when implementing or reviewing Spark-based pipelines, or managed distributed runtimes…
unity-catalog-and-lakehouse-governance
Guides agents through Unity Catalog governance workflows for Databricks lakehouses. Use when defining catalogs, schemas, external locations, access boundaries,…
using-data-agent-skills
Provides a compatibility alias for the main data engineering entry skill. Use when an existing setup still points at the legacy start-here file.
Coding SOP
Standard operating procedure for research experiments, data analysis, and visualization. Covers Python/R script execution, statistical analysis, data wrangling…
database-schema-designer
SQL and NoSQL schema design with normalization, indexing, and migration patterns. Use when designing database schemas, creating tables, optimizing slow…
embeddings
Text embeddings for semantic search and similarity. Use when converting text to vectors, choosing embedding models, implementing chunking strategies, or…
fermi-estimation
Use for Fermi estimation, or when a rough number is needed fast: "roughly how many...", "ballpark the cost", "estimate capacity or market size", "is this even…
google-analytics
Agent-callable Google Analytics 4 (GA4) tools — run analytics reports, discover the dimensions and metrics a property supports, navigate accounts and…
stock-log-viewer
A tool for browsing Sister Zheng's stock analysis diary. Supports viewing the latest n diary entries, counting the total, querying by date, querying by stock name/code, and full-text keyword search.
data-ingestion-pipeline
Build data ingestion pipelines for batch and streaming data from multiple sources. Covers extraction strategies, format normalization, deduplication,…
redis-patterns
Use Redis effectively for caching, pub/sub messaging, rate limiting, distributed locks, and session storage. Covers data structure selection, expiration…
graphrag
Comprehensive skill for Microsoft GraphRAG - modular graph-based RAG system for reasoning over private datasets
oci-order-detail-query
Query and analyze OCI order detail data from StarRocks via DuckDB. Always exports to CSV before analysis. Supports basic, aggregation, customer, sales,…
web-attack-methods
Web full-stack attacks: SQLi/command injection/SSTI/XSS/SSRF/NoSQL, authentication JWT/OAuth/SAML, LFI/upload, Tomcat/WS/STOMP/XFF/PATH_INFO/CDN502/Wangsu JS challenge bypass. Use when testing Web injection, auth bypass,…
wtpy
Comprehensive guide to quantitative trading development with WonderTrader/wtpy, integrating official documentation, community notes, and practical cases. Covers the full workflow of strategy development, backtesting, simulation, live trading, data management, and monitoring/operations for the wtpy Python framework and the WonderTrader C++ core.
alibabacloud-migration-sdm-sql-trans
SQL syntax conversion skill across big data engines (DML/DDL/stored procedures). Covers rewrite scenarios such as identifiers, data types, functions, query syntax, distribution/partitioning strategies, stored procedures/functions, external tables, etc. Synapse → Hologres is currently implemented, and the framework is for other engine pairs (such as SQL Server → MaxCompute, Hive →…
imaging-data
Use when preparing a medical-imaging dataset (DICOM/NIfTI) for modelling. Profiles spacing, orientation, intensity, label integrity, foreground fraction and…
aegis-db-server-hardening
Audits database server hardening for PostgreSQL, MySQL/MariaDB, Redis, and MongoDB — network placement and binding, transport encryption, authentication…
external-mindstudio-ascend-profiler-db-explorer
SQL analysis skill for Ascend PyTorch Profiler / msprof DB (such as ascend_pytorch_profiler*.db, msprof_*.db). Converts natural language questions (operator duration, communication, dispatch, scheduling, schema/table queries) into safe, executable SQL, and extracts table structure details from official documentation as needed.
external-mindstudio-cluster-fast-slow-rank-detector
Expert skill dedicated to diagnosing "fast/slow cards" from Ascend cluster Profiling performance data. When the user provides a [cluster performance data directory/path] and requests analysis of [fast/slow cards], [slow nodes], [load imbalance], or [cluster bottlenecks], this skill must be triggered. This skill automatically receives the cluster path and dispatches relevant tools to output the macroscopic qualitative assessment and microscopic root causes of fast/slow cards (such as Host dispatch bottlenecks or operator computation degradation).
external-mindstudio-mindstudio_profiler_data_check
When the user provides performance data collected by the MindStudio profiler (framework profiler, msprof command line), validate data completeness, collection status, and key configurations to ensure that subsequent analysis tools can run properly.
dataviz
Use this skill whenever you are about to create ANY chart, graph, plot, dashboard, or data visualization, in ANY output medium — an HTML or React artifact,…
detect-anomalies
Detect anomalies in Axiom datasets using statistical analysis. Use when looking for unusual patterns, volume spikes, outliers, or new error types in…