Fabric Analytics Projects — Data skill for Claude Code
End-to-end Fabric projects built with Claude Code and MCP — covering medallion lakehouses, real-time KQL pipelines, ML workflows, and Power BI semantic models.
How to install Fabric Analytics Projects
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open alisaghilutfi/Fabric-Analytics-Projects and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Fabric Analytics Projects does
End-to-end Fabric projects built with Claude Code and MCP — covering medallion lakehouses, real-time KQL pipelines, ML workflows, and Power BI semantic models. Developed using a two-harness agentic workflow.
Alternatives in Data
- Claude Code Usage Monitor — by Maciek-roboblog - A real-time terminal-based tool for monitoring Claude Code token usage 7k ★
- Azure Event Hub Java — Real-time high-throughput streaming for Java 1.8k ★
- Data Pipelines Pack — Data pipeline development skills 1.6k ★
README
Fabric Analytics Projects
End-to-end Microsoft Fabric analytics projects built by [Ali Saghi](https://www.linkedin.com/in/ali-saghi-fabric/), DP-600 certified Microsoft Fabric Analytics Engineer and founder of [Lotusoftware](https://lotusoftware.hashnode.dev) — a data analytics consultancy in Vantaa, Finland.
Each project demonstrates a full analytics workload on Microsoft Fabric: from raw data ingestion through medallion architecture to semantic models, Power BI reports, and real-time dashboards. All projects are built using a two-harness agentic workflow — no manual Fabric UI work.
How This Works
This repo is the **execution harness** of a two-harness agentic system. The planning harness (claude.ai) reads business context and writes session instructions. The execution harness (Claude Code in VS Code) reads those instructions, executes against Fabric and Power BI via MCP servers, and files a recap at session end.
flowchart LR
A([ProjectPlanner\nclaude.ai]) -->|writes instructions| B[CONTEXT.md]
B -->|read at session start| C([FabricEngineer\nClaude Code])
C -->|executes via MCP| D[(Microsoft Fabric\nPower BI)]
D -->|results| C
C -->|files recap| B
B -->|updates| E[PROJECTS.md]
style A fill:#E1F5EE,stroke:#0F6E56,color:#085041
style C fill:#E1F5EE,stroke:#0F6E56,color:#085041
style B fill:#EEEDFE,stroke:#534AB7,color:#26215C
style E fill:#EEEDFE,stroke:#534AB7,color:#26215C
style D fill:#E6F1FB,stroke:#185FA5,color:#0C447C
The loop runs every session. `CONTEXT.md` per workspace is the handoff document — it holds current state, known blockers, and the exact next step. `PROJECTS.md` is the portfolio-wide registry updated after every session.
Projects
ws_Finance_Analysis — Finance Analytics Platform
**Type:** Business Intelligence + CI/CD **Stack:** Medallion architecture · DirectLake semantic model · Power BI report (4 pages) · Three-environment CI/CD (Dev/Test/Prod) · GitHub
Related Skills
Product Jobs Search Agent
A file-based agentic system that runs a senior PM job search end to end. Built with Claude Code. No external s
Anomaly Hunter
Multi-agent anomaly detection with real-time investigation. Built with 8 AI/ML sponsors for autonomous data qu
Edgespark Template
AI-agent-native, one-command EdgeSpark templates. Hatch: static-site host + built-in backend. Perch: link-in-b
Copilot Scope
Observability for AI copilot sessions; OpenTelemetry collector, Postgres store, and Blazor dashboard with real
Building Online RAG Pipelines For Semantic Search
Build a production retrieval-augmented generation pipeline in plain JavaScript: ingest, chunk, embed, store in
Docwise Agentic
Full agentic RAG pipeline: adaptive chunking → Qdrant hybrid search (semantic + BM25 + RRF) → LangGraph ReAct
Related Agents
AI Data Engineer
Data Engineer who designs and builds data pipelines, warehouses, lakehouses, and data infrastructure to power
Powerbi Analyst
Power BI + DAX for the Seshat BI repo — PBIP semantic models, measures, gold-only data models, performance. Us
Data Eng Sa Orchestrator
Use as the implementer counterpart to data-eng-sa-reviewer. Drafts and builds data engineering, analytics engi