Ingestion Validation Agent Skill
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.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/Azure/gpt-rag-ingestion --skill ingestion-validationThe instruction itself
5 sections, as written by the authorIngestion validation
Start with the narrowest existing command that covers the change.
Engineering-agent assets
python -m pip install --requirement .github/scripts/requirements.txt
python .github/scripts/validate-agentic-assets.py
Python
Run focused tests first:
python -m pytest tests/<affected_test>.py
Then run the maintained suite when risk or repository policy requires it:
python -m pytest
Do not require live Azure credentials for unit tests. Reuse existing fakes,
stubs, and golden fixtures.
Frontend
From frontend/, use the scripts defined in package.json:
npm test
npm run lint
npm run build
Runtime integration
For changes to formats, sources, jobs, embedding, Search payloads, or
deployment:
- Build and run the existing container or use the applicable
scripts/deploy.ps1 or scripts/deploy.sh path.
- Exercise a representative source and document.
- Verify the terminal job result and expected Azure AI Search documents,
fields, ACL metadata, and deletion behavior.
- Inspect logs and correlated audit events without copying document content,
credentials, or private environment names into public artifacts.
If a command is unavailable or live validation is unsafe, report the missing
dependency and residual risk. Do not substitute an unrelated passing check.
Other skills for the same job
different authors, same section of the catalogue
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
Google Cloud Platform CLI - manage GCP resources including Compute Engine, Cloud Run, GKE, Cloud Functions, Storage, BigQuery, and more.
Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and observability. Use PROACTIVELY when creating new backend services or APIs.
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
Aspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev Containers, GitHub Codespaces, templates, dashboard, and deployment. Use when the user asks to create, run, debug, configure, deploy, or troubleshoot an Aspire distributed application.
Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness. Returns a structured report with exact patch locations.
Microsoft Store Developer CLI (msstore) for publishing Windows applications to the Microsoft Store. Use when asked to configure Store credentials, list Store apps, check submission status, publish submissions, manage package flights, set up CI/CD for Store publishing, or integrate with Partner Center. Supports Windows App SDK/WinUI, UWP, .NET MAUI, Flutter, Electron, React Native, and PWA applications.
How to use it
Take azure/ingestion-validation from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.