Data & Analytics for Claude Code

Microsoft Fabric graph and geospatial analytics - graph model, graph queryset, map, and exploration workflows with preview guardrails.

Microsoft Fabric Mirroring — source onboarding, CDC replication, latency monitoring, schema drift handling, and reconciliation workflows

Microsoft Fabric mirroring for Azure-native sources - Cosmos DB, PostgreSQL, Databricks catalog, Azure SQL Database, and SQL Managed Instance.

Microsoft Fabric mirroring for external sources - generic databases, BigQuery, Oracle, SAP, Snowflake, and SQL Server with preview caveats where applicable.

Microsoft Fabric OneLake — unified data lake, shortcuts, file explorer, ADLS Gen2 APIs, and cross-workspace data access

Microsoft Fabric Real-Time Analytics — Eventhouse, KQL databases, eventstreams, Real-Time Dashboards, and streaming ingestion

Microsoft Fabric Semantic Models — Direct Lake modeling, DAX governance, calculation groups, XMLA deployment, and semantic link automation

Microsoft Graph Investigator — unified user investigation, mailbox forensics, activity timelines, device correlation, and forensic reporting across all M365 services

KDB.AI vector database — schema design, hybrid search, and integration patterns for AI applications

KDB-X workflows and patterns for the next-generation KX time-series database

Query Langfuse traces for debugging LLM calls, analyzing token usage, and investigating workflow executions

Read and update workbooks, worksheets, ranges, and tables via MCP.

Microsoft Forms — create surveys, add questions, collect responses, and summarize results via Graph API

DAX measures, DAX UDFs, calculation groups, Power Query M, TMDL model-as-code, TOM/XMLA and PowerShell automation, Power BI Embedded, deployment pipelines, PBIP scaffolding, Fabric Lakehouse, Direct Lake, performance optimization

Power BI paginated reports through Fabric — RDL authoring, VB.NET expressions, data source configuration, rendering/export, REST API automation, SSRS-to-Fabric migration, performance tuning, and troubleshooting

Process and task mining from M365, Power Automate, and Azure Monitor logs — extract event logs, discover process models, analyze performance, and check conformance

KDB-X Python (pykx) workflows — using kdb+/q from Python, conversions between Python and q types, and KDB-X Python API guidance

Scan, categorize, deduplicate, and organize SharePoint and OneDrive files at scale using Microsoft Graph.

Collection of AIOps skills for root cause analysis, log analysis, and operational tasks

Analyze Claude Code token usage and costs from local session data. Breaks down spend by project, model, and day. Includes model recommendations showing which sessions didn't need Opus. Analyzes MCP server overhead, tool result sizes, and context bloat. Provides personalized cost savings recommendations with estimated savings.

Neural network interpretability with nnsight - includes skills for tracing, logit lens, activation patching, attribution patching, causal tracing, model steering, and remote execution

Analyzes Power Platform and Copilot Studio solutions, generates interactive HTML architecture dashboards with inline SVG diagrams, ERDs, data flows, and optional shareable PageDrop links.

Conduct Fault Tree Analysis (FTA) for system failure analysis using Boolean logic gates. Identifies minimal cut sets, single points of failure, and failure probabilities.

Conduct FMEA for systematic failure mode identification using AIAG-VDA 7-step methodology. Supports DFMEA, PFMEA, and FMEA-MSR with Action Priority risk assessment.

Semantic search over systems engineering standards (IEEE, INCOSE, ISO) with RAG capabilities for grounding specifications in engineering knowledge.

Conduct Pareto Analysis (80/20 Rule) to identify vital few causes driving majority of problems. Generates Pareto charts and prioritization reports.

Orzecznictwo sądów administracyjnych z CBOSA (orzeczenia.nsa.gov.pl): NSA i 16 WSA, ~2,4 mln orzeczeń od 2004 r. Wyszukiwanie po frazie, sygnaturze, sądzie, symbolu sprawy, sędzim i dacie; pełne sentencje i uzasadnienia, powołane przepisy. CBOSA nie ma API — read-only scraping publicznych stron z throttlingiem.

Prawo miejscowe z API ELI 16 wojewódzkich dzienników urzędowych: uchwały rad gmin/powiatów/sejmików (podatki i opłaty lokalne, plany miejscowe MPZP, statuty), rozporządzenia wojewody. Wyszukiwanie po tytule i roczniku, metadane, pełna treść i urzędowy PDF. Read-only, bez klucza.

Polskie orzecznictwo z publicznego API SAOS (saos.org.pl): wyroki, postanowienia i uchwały SN, TK, sądów powszechnych i KIO. Wyszukiwanie po frazie, sygnaturze, sądzie, sędzim, powołanym przepisie i dacie; pełne uzasadnienia, powołane przepisy i orzeczenia.

Decyzje Prezesa UODO z oficjalnego API Portalu Orzeczeń UODO (orzeczenia.uodo.gov.pl): kary za naruszenia RODO, upomnienia, nakazy. Wyszukiwanie pełnotekstowe i po tytule/dacie; pełna treść decyzji po sygnaturze. Read-only, bez klucza.

Persistent session memory with searchable storage and checkpoints

Systematic trade study using DAU 9-Step Process

Skills and MCP configuration for using arx to inspect, fetch, and search locally cached arXiv papers.

Free / freemium public data feeds — FRED, EDGAR, FIGI, Yahoo Finance, World Bank, plus geopolitical sources (ACLED, GDELT, GDACS, NASA, EIA, WTO, etc.). 129 MCP tools.

Premium market-data plugin — Financial Modeling Prep (180 tools, freemium, requires FMP_API_KEY) plus paid vendor MCPs covering LSEG, S&P Global, FactSet, Morningstar, Moody's, PitchBook (87 tools).

Search pathology cases by diagnosis, organ, age, and stains. Build research cohorts and export WSI data.

Upload a CSV, ask a question, and a team of specialist agents builds a custom analysis you own — regression, clustering, forecasting, A/B tests, churn prediction — delivered as an interactive HTML report with charts and AI insights.

Fetch npm package source code for deep implementation analysis. Use when types/docs aren't enough.

Skills for working with Orchestra data pipelines — diagnose and fix failed runs, triage with a merge gate, author pipeline YAML, set up dbt Slim CI, run Snowflake data-quality tests, and review a workspace against best practices. MCP-first.