Skip to content

CONTRIBUTING.md

Latest commit

 

History

History
43 lines (30 loc) · 1.34 KB

CONTRIBUTING.md

File metadata and controls

43 lines (30 loc) · 1.34 KB
Raw

Contributing

Thanks for improving rag-architect.

This repository is meant to stay practical: every addition should help an AI architect produce clearer, more measurable, more implementation-ready work.

Good contributions

  • Production RAG design patterns
  • Better eval and observability checklists
  • ADR templates for AI infrastructure decisions
  • GitHub issue templates for implementation agents
  • LLM-as-judge rubrics and calibration guidance
  • Model routing and unit economics guidance
  • Agent tool design patterns with failure behavior

Contribution standards

Before opening a PR, check:

  • Does this help ship evaluated, observable AI systems?
  • Is it specific enough for a coding agent or engineering team to use?
  • Are tradeoffs, non-goals, and failure modes clear?
  • Does it avoid unverifiable hype?
  • Does it preserve a clean Hermes skill structure?

Validate locally

python3 scripts/validate.py

Style

  • Prefer concise, direct markdown.
  • Use tables for tradeoffs and decision matrices.
  • Include acceptance criteria for implementation work.
  • Include eval and observability expectations for AI behavior changes.
  • Avoid vendor lock-in unless a template is explicitly vendor-specific.

Security and privacy

Do not commit secrets, API keys, profile runtime state, private company data, customer data, or internal-only examples.