Feature Models Round Table

Take a feature request from a multi-model consensus on what to build, straight through to an implemented, reviewed, tested change. This skill is intentionally thin: it sequences two existing skills and passes their artifacts. It does not re-implement either — if you need to change how consensus or building works, change models-round-table or implement-and-review, not this skill.

Pipeline: models-round-table (answer → consensus) → implement-and-review (build).

Steps

1. Consensus understanding/plan. Run models-round-table on the feature request — frame the task for it as scoping/approach, e.g. "Determine what this feature requires and the best approach: <request>." Do not pre-analyze the request yourself; that bias-free fan-out is the point of models-round-table. It returns a Consensus answer + Agreements + Open caveats, written to .ai-workflow/roundtable/<id>/report.md.

2. Resolve caveats (gate). If the report has Open caveats (low-confidence or orchestrator-decided points), settle them with the user before any code — unless --auto, then record an assumption per caveat. This satisfies implement-and-review's intake gate.

3. Build. Invoke implement-and-review with the settled consensus as the task (--from-roundtable .ai-workflow/roundtable/<id>/report.md). It takes the Consensus answer as the settled task, breaks it into to-tasks vertical slices, runs the FE/BE cross-reviewed TDD build (independent slices in parallel) per slice acceptance, then the final full-review, leaving tests/build green.

4. Report. Relay implement-and-review's final report, prefaced with the consensus summary and how any caveats were resolved. Return both report paths.

Rules