self-critique

To validate code quality before a code review, run an automated self-evaluation loop to score implementations against project specs, doctrine, and rubric criteria. It surfaces blockers and checks architecture compliance to ensure feature readiness.

Rubric-driven self-evaluation is an automated process that reviews a feature implementation against project specifications and quality criteria. It enforces checks for spec alignment, architecture compliance, and contract stability across iterations.

Check architecture compliance and contract stability by running an iterative evaluation loop against the project doctrine. This ensures alignment with interfaces and data contracts, validating that the implementation meets runnable state criteria.

Yes, you can use automated spec alignment to find blockers during iterations. The evaluation repeats scoring against a rubric to drive improvements and enforce conventions until the implementation passes readiness checks.

No, the self-critique evaluation requires no external dependencies to run. It operates independently to compare implementations against the plan, specs, and rubric to validate conformance and readiness for review.

Run an automated code review loop after implementing a feature and before task completion. It applies during feature development and prior to formal code review to validate spec conformance and enforce quality criteria.