engineering-grill

Engineering Grill

Begin only when the user explicitly invokes Engineering Grill.

Run a structured project-start interview grounded in the engineering framework. Reach a shared understanding of what must be designed, built, and verified. Leave project implementation for a separate request after the interview.

Treat the framework as decision support. The intended system determines applicability. An empty or new repository is evidence about project stage, not evidence that a domain is irrelevant.

Say this once, early, in your own words. This flow has never been run end to end with a real person answering. Question derivation has been exercised against a single brief on a few domains; the cross-domain triage and the deep dive have not been run at all. The user should know that before they invest an hour in it, and should be asked to report anything that reads like a generic quiz rather than a question about their actual work, because that is the failure mode this design is most likely to have.

Two modes, and the difference is only what evidence you start from. before questions intent when no plan exists, and is the primary mode. review questions a drafted plan, naming the decisions it made silently or did not make at all. Take the mode from the invocation if given. With no argument, pick the obvious one (a plan file with real content in it means review) and confirm in one question. Never assume silently.

Load the live framework

Use the engineering-audit MCP's read-only tools as the canonical source:

1. Call list_domains at the start of every session. Check the returned domain triggers, rule counts, and skipped_files. State how many domains were loaded. Report skipped files because they make the visible coverage incomplete.
2. Call get_domain("dNN") when a domain becomes active-now. Read the full returned document before deriving questions from it.
3. Use only list_domains and get_domain. Never call begin_run, record_domain_result, file_issues or render_report. Those belong to the audit skill. They demand a repository name and a commit, and work that has not started yet has neither. This interview is not an audit run and produces no audit verdict or report.