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 you and the AI disambiguate the spec so the orchestrator can re-arm the story and resume the run. ## Core Features & Use Cases - Structured escalation intake: Reads a context.json containing the story key, frozen spec path, baseline commit, and the list of CRITICAL escalations to resolve. - Interactive disambiguation: Presents the ambiguity plainly with 2–4 concrete resolution options, a recommendation, and trade-offs, then records the human's decision. - Frozen spec correction: Amends the spec's frozen-after-approval block and affected acceptance criteria so a fresh dev session has exactly one correct reading, then writes a resolution.json marker the orchestrator uses to resume. - Use Case: A review session escalates because the spec never states whether a CLI list command should output JSON or plain text; you invoke this Skill, decide JSON with the human, patch the spec, and the paused run resumes cleanly. ## Quick Start Invoke /bmad-loop-resolve with the escalated story key to review the escalation, decide a resolution with me, and update the frozen spec.
