What problem does it solve? When two AI agents working in parallel produce conflicting git branches, neither agent can fairly resolve the conflict — each lacks the peer's context and is biased toward its own changes, leading to overwritten work or abandoned features. This Skill provides an impartial reconciliation procedure that merges both sides based on their stated intents. ## Core Features & Use Cases - Hunk Classification: Categorizes every conflicted hunk as disjoint-intent, same-question-different-answer, or superseded, with per-hunk rationale. - Impartiality Contract: Enforces rules against self-favoring, drive-by edits, and splitting the difference on design decisions. - Kanban Integration: Supports spawning a neutral reconciler agent via delegate_task or a third-profile kanban card with both conflicted cards linked as parents. - Use Case: During a parallel-PR wave, two agent branches collide on a shared module. Spawn a reconciler subagent with both branch names and intent summaries; it classifies each hunk, merges disjoint changes, picks one answer per design collision, runs the build, and hands back a summary listing every decision for human veto. ## Quick Start Resolve the halted merge in this repository between branch-a and branch-b as a neutral reconciler, using both sides' kanban completion summaries as intent sources.
