hatch3r-board-groom

## §0 Detect Ambiguity (P8 B1) Before any action, scan the user's request and provided context for unresolved questions in scope, acceptance criteria, irreversibility, or constraint conflicts (contradictory inputs, missing target, unknown convention). If any are found, ask the user via the platform-native question tool per `agents/shared/user-question-protocol.md` — do not proceed under silent assumption. This is the default path, not an exception. Acceptable to proceed without asking ONLY when scope is single-target, single-concern, and the brief alone is testable. Any residual ambiguity discovered mid-workflow invokes the same protocol. ## Invoked by Run directly for backlog refinement, or dispatched from `skills/hatch3r-cleanup/SKILL.md` (Step 2) scoped to stale-item archival (Step 4e) after that skill's consolidated cleanup ASK — this skill's own per-issue ASK checkpoints still apply on dispatch. ## Integration with Platform Agentic Workflows hatch3r's board commands are the **implementation orchestration layer** above platform agentic workflows (GitHub Agentic Workflows, Azure DevOps automations, GitLab Auto DevOps): the platform workflows run continuous background automation (triage, testing, docs) while the board commands orchestrate the delivery pipeline. `board-groom` is the refinement stage — it re-prioritizes, reclassifies, re-scopes, archives, decomposes, merges, and remediates dependency/health issues on existing work items as priorities and scope evolve. C...