What problem does it solve? When an automated bmad-loop run pauses because a dev or review session hit a CRITICAL escalation — a contradiction or gap in the frozen spec it could not safely resolve alone — this Skill provides an interactive session where a human disambiguates the spec so the orchestrator can re-arm the story and resume the run. ## Core Features & Use Cases - Escalation triage: Reads the run's context.json, frozen spec, and escalation details, then presents the ambiguity to the human with 2-4 concrete resolution options and a recommendation. - Frozen spec amendment: Updates the <frozen-after-approval> block and affected acceptance criteria so a fresh dev session has exactly one correct reading, without touching orchestrator state like sprint-status.yaml or spec status fields. - Patch-restore handling: For review-stage intent gaps with a saved patch, supports amending the intent and recording a restore_patch so the orchestrator resumes review on the already-written change instead of re-implementing. - Sentinel and ambiguous-file resolution: Handles stories-mode sentinels (unresolved/ambiguous story files) by clarifying upstream SPEC.md or stories.yaml entries, and resolves duplicate story-file matches by cleanup. - Use Case: A bmad-loop run pauses on story 6-4 because the frozen spec never stated whether the CLI list command should output JSON or plain text. You invoke /bmad-loop-resolve 6-4-cli-list-command, review the escalation with the human, amend the spec to mandate JSON output, and write the resolution marker so the orchestrator re-drives the story. ## Quick Start Run /bmad-loop-resolve <story-key> for the paused story and work with me to resolve the escalation recorded in the run's context file.
