Instructions for Azure/gpt-rag-ingestion, a project described as: The GPT-RAG Data Ingestion service automates processing of diverse documents—PDFs, images, spreadsheets, transcripts, and SharePoint—readying them for Azure AI Search. It applies smart chunking, generates text and image embeddings, and enables rich…
Conducts and records a verifiable ingestion architectural decision. Use when a choice alters pipeline boundaries, chunk/index contracts, identity, data, source integration, deployment, or operation with meaningful reversal cost.
Keeps ingestion repository and published GPT-RAG documentation aligned with shipped formats, configuration, indexing, deployment, audit, and operator behavior.
Ingestion architecture and implementation principles. Use for design, review, meaningful refactoring, Azure integration, document security, testing, or operational changes.
Selects and runs evidence-based validation for Python ingestion, chunking, jobs, Azure AI Search contracts, deployment assets, and the operator frontend. Use whenever repository behavior or engineering assets change.
Prepare and reconcile repository releases, including version selection, SemVer checks, release branches, changelog updates, release notes, tags, GitHub releases, and publication approval gates. Use when asked to prepare, version, tag, publish, roll back, or repair a release.
Instructions for Azure/gpt-rag-ingestion, covering gpt-rag ingestion engineering-agent contract, priority, what this repository is, repository boundaries and data, security, and configuration.
Release workflow for containerization-assist (CA). Use when: cutting a new release, bumping patch/minor/major version, updating CHANGELOG.md for a release, preparing a release branch, syncing version across package.json and server.json, releasing CA, tagging a version, publishing a new version of…
Instructions for Azure/containerization-assist, covering agent instructions, build verification before pushing, common pitfalls, running tests and code style.
Detect languages, frameworks, build systems, dependencies, databases, and environment variables in a repository for the purpose of containerization or cloud deployment. Use BEFORE generating a Dockerfile, fixing a Dockerfile, or generating Kubernetes manifests. Triggers require a containerization/deployment intent…
End-to-end orchestrator that takes a source repository through analysis → Dockerfile → image build → security scan → AKS cluster prep → ACR push → Kubernetes manifests → deploy → verify on a real Azure AKS cluster. Trigger ONLY when the user explicitly names Azure, AKS, or ACR — e.g. "deploy to AKS", "deploy to…
Validate and remediate an existing Dockerfile against security, performance, and best-practice rules. Use AFTER a Dockerfile exists (either user-authored or produced by generate-dockerfile) and BEFORE building or pushing the image. Triggers include "fix my Dockerfile", "is this Dockerfile secure", "validate…
Generate or enhance a Dockerfile for a containerized application using curated base-image recommendations and security best practices. Use AFTER analyze-repo (or after the user has told you the language/framework). Triggers include "generate a Dockerfile", "containerize this", "write Dockerfile for X", or when running…
Generate production-ready Kubernetes manifests (Deployment, Service, ConfigMap, Secret, ServiceAccount, optional HPA) for a containerized application. Use AFTER a Dockerfile exists and has been validated by fix-dockerfile. Triggers include "generate kubernetes manifests", "deploy this to k8s", "write k8s yaml"…
TypeScript MCP server for AI-powered containerization workflows with Docker and Kubernetes support. Runs locally from the containerization-assist-mcp npm package. Needs 2 environment variables to run.
Analyzes GPT-RAG MCP boundaries, protocol contracts, security, deployment, and trade-offs. Use for structural or hard-to-reverse changes; do not use for local implementation with settled requirements.
Prepares and validates GPT-RAG MCP component releases. Use for versions, changelog entries, release branches, tags, and release notes; do not use for feature implementation or publish without explicit human approval.