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. This Skill provides an impartial reconciliation procedure that merges both sides' work based on their stated intents. ## Core Features & Use Cases - Hunk Classification: Categorizes every conflicted hunk as disjoint-intent, same-question-different-answer, or superseded, then applies the matching resolution strategy. - Impartiality Contract: Enforces rules against self-favoring, drive-by edits, and splitting the difference on design decisions, with escalation when intents genuinely tie. - Kanban Integration: Supports spawning a neutral third-profile reconciler agent via kanban cards that carry both sides' completion summaries as parent links. - Use Case: During a parallel multi-agent refactor, two agents' branches collide on the same module. Spawn a reconciler agent with both branch names and intent summaries; it classifies each hunk, merges disjoint changes, picks one answer per design collision, verifies with the build, and hands back a summary listing every decision. ## Quick Start Ask the agent to reconcile the halted merge in this repository between branch-a and branch-b using both sides' kanban completion summaries, following the merge-reconciler procedure.
