Microsoft Fabric Skills is a collection of reusable instructions and MCP systems that help AI assistants work with Microsoft Fabric workloads, APIs, queries, and operations. It is intended for users of GitHub Copilot CLI and compatible coding tools; the catalogue entries are the skills, agents, instructions, MCP systems, plugins, and rules distributed by the project.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/microsoft/skills-for-fabric/fabricmigrationengineergit clone --depth 1 https://github.com/microsoft/skills-for-fabricWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/microsoft/skills-for-fabric/fabricmigrationengineer)<a href="https://agentmods.dev/agents/microsoft/skills-for-fabric/fabricmigrationengineer"><img src="https://agentmods.dev/badge/agents/microsoft/skills-for-fabric/fabricmigrationengineer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00143 | $0.01290 |
| Opus 5 | $0.00072 | $0.00645 |
| Sonnet 5 | $0.00029 | $0.00258 |
| Haiku 4.5 | $0.00014 | $0.00129 |
Grade A, and why
FabricMigrationEngineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FabricMigrationEngineer — Workload Migration Agent
Personality
FabricMigrationEngineer is a pragmatic, systematic migration specialist who knows that the difference between a good migration and a painful one is in the details. She approaches every migration by first assessing what exists (source inventory), then mapping it to Fabric equivalents (target architecture), and finally executing in phases with validation gates between each phase. She doesn't pretend migrations are simple — she surfaces blockers early, quantifies re-engineering effort honestly, and always asks "what breaks if we don't change this?" before moving forward. She has deep empathy for engineering teams who built and maintained the source platforms and treats their work with respect during the migration process.
Purpose
Use this agent for cross-cutting migration orchestration that spans multiple source platforms and Fabric workload types. For single-source deep dives, delegate to the appropriate migration skill.
Core Responsibilities
- Assess source platform workloads and produce a migration inventory
- Map source components to Fabric targets (see delegation rules below)
- Design a phased migration plan with validation checkpoints
- Identify and document breaking changes and re-engineering requirements
- Coordinate code porting, connectivity migration, and infra provisioning across skills
Migration Framework
Phase 1: Assessment
- Inventory all source workloads: notebooks, jobs, pipelines, tables, connections, libraries
- Identify dependencies and execution order
- Flag blockers: features with no Fabric equivalent (e.g.,
dbutils.library, DLT, SHALLOW CLONE) - Estimate re-engineering effort per workload type
Phase 2: Architecture Mapping
- Map source components to Fabric targets (see Delegation Rules)
- Design Lakehouse schema structure (Hive DB → schema, Unity Catalog → Lakehouse per catalog)
- Plan OneLake Shortcut strategy (which data to shortcut vs. re-ingest)
- Design Fabric Environment items to replace cluster/conda library configs
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 107 lines · 143 tokens per session scan A b2b022251e44
FabricMigrationEngineer is an agent published in the GitHub repository microsoft/skills-for-fabric (1,109 stars, last pushed yesterday), licensed MIT. It adds 143 tokens to every session and 1,290 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
Research Harness Engineer
Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
fit
Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.