Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
GPT-RAG is an Azure solution accelerator for building agentic retrieval-augmented generation systems, where agents use connected organizational sources to ground their answers. It is for organizations deploying secure RAG applications with Microsoft Foundry, Microsoft Agent Framework, and Azure infrastructure. The catalogue add-ons provide agents, skills, and instructions for deploying and working with the accelerator.
This repository also configures its own agents. See what GPT-RAG tells them →
Skill Claude CodeCodex ✓ vendor
Conducts and records a verifiable GPT-RAG architectural decision. Use when a choice alters repositories, boundaries, contracts, identity, data, deployment topology, or operation with meaningful reversal cost.
Skill Claude CodeCodex ✓ vendor
Keeps GPT-RAG user and operator documentation aligned with shipped behavior. Use for features, configuration keys, deployment parameters, defaults, component pins, operations, or breaking changes.
Skill Claude CodeCodex ✓ vendor
GPT-RAG architecture and implementation principles. Use for design, review, meaningful refactoring, Azure integration, security, testing, or operational changes.
Skill Claude CodeCodex ✓ vendor
Prepares and validates GPT-RAG umbrella and multi-repository releases. Use whenever work involves release preparation, semantic versions, release branches, manifest or component pins, changelog release entries, tags, GitHub Release notes, or AI Landing Zone release alignment.
Skill Claude Code ✓ vendor
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
Skill Claude Code ✓ vendor
Generate a custom checklist for the current feature based on user requirements.
Skill Claude Code ✓ vendor
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
Skill Claude Code ✓ vendor
Create or update the project constitution from interactive or provided principle inputs.
Skill Claude Code ✓ vendor
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
Skill Claude Code ✓ vendor
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
Skill Claude Code ✓ vendor
Execute the implementation planning workflow using the plan template to generate design artifacts.
Skill Claude Code ✓ vendor
Create or update the feature specification from a natural language feature description.
Skill Claude Code ✓ vendor
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
Skill Claude Code ✓ vendor
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: