The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
npx ecc-install --profile fullFair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
npx n8nAn open-source AI agent that brings the power of Gemini directly into your terminal.
npx @google/gemini-cliMicrosoft Fabric Skills are reusable AI assistant instructions for working with Microsoft Fabric. They help GitHub Copilot CLI and compatible AI coding tools understand Fabric workloads, APIs, query patterns, and operational best practices.
Add the public marketplace:
/plugin marketplace add microsoft/skills-for-fabric
Install the full bundle (except powerbi-authoring):
/plugin install fabric-skills@fabric-collection
Or install a focused bundle:
# Authoring: APIs, automation, notebooks, schemas, ingestion, and deployment
/plugin install fabric-authoring@fabric-collection
# Consumption: interactive querying, discovery, exploration, and monitoring
/plugin install fabric-consumption@fabric-collection
# Operations: diagnostics and performance investigation
/plugin install fabric-operations@fabric-collection
# Power BI authoring: semantic models, Power BI report skills, and PBIP workflows
/plugin install powerbi-authoring@fabric-collection
You can also filter the full bundle by workload:
/plugin install fabric-skills@fabric-collection --filter "sqldw-*"
/plugin install fabric-skills@fabric-collection --filter "spark-*"
/plugin install fabric-skills@fabric-collection --filter "eventhouse-*"
| Bundle | Use it for |
|---|---|
fabric-skills | Complete Microsoft Fabric skill bundle, including authoring, consumption, operations, migration, and end-to-end architecture skills. |
fabric-authoring | Creating and managing Fabric items through REST APIs, CLI automation, notebooks, T-SQL, KQL, Dataflows Gen2, Eventstreams, and semantic models. |
fabric-consumption | Read-only exploration and query workflows across Warehouses, Lakehouses, Power BI semantic models, Eventhouse/KQL databases, Eventstreams, Dataflows Gen2, and catalog search. |
fabric-operations | Performance and health diagnostics, including warehouse query insights and slow-query investigation. |
powerbi-authoring | Authoring Power BI semantic models, reports, and PBIP workflows, including Power BI report planning, design, authoring, and management. |
The full bundle includes skills for SQL data warehouse, Spark and Lakehouse, Power BI semantic models, Eventhouse and KQL, Eventstreams, Dataflows Gen2, catalog search, migration scenarios, and medallion architecture workflows.
See CHANGELOG.md for public release notes.
After installing a bundle, open Copilot CLI in a project folder and ask for the Fabric task you want to perform, for example:
Use Microsoft Fabric skills to design a medallion architecture for NYC taxi data.
Most Fabric operations require Azure authentication. Start with:
az login
az account get-access-token --resource https://api.fabric.microsoft.com
SQL, Spark, Power BI, and KQL workflows may require workload-specific endpoints or token audiences. The installed skills provide the detailed commands and API patterns for each workload.
Skills provide guidance and patterns. MCP servers provide live tool access to data sources and APIs. Some bundles include MCP configuration where supported, and you can register additional Fabric MCP servers if your environment provides them.
See MCP setup.
GitHub Copilot CLI plugin installation is the recommended path. This repository also includes root-level configuration files for compatible AI coding tools — CLAUDE.md for Claude Code, .cursorrules for Cursor, .windsurfrules for Windsurf, and AGENTS.md for Codex / Jules / OpenCode. They are picked up automatically when the repo is cloned.
Gemini CLI also auto-discovers GEMINI.md when the repo is cloned.
Report product issues in the GitHub issue tracker.
For security vulnerabilities, do not open a public issue. See SECURITY.md for the private reporting path.
This project is licensed under the MIT License.