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Cases - Hunk Classification: Categorizes every conflicted hunk as disjoint-intent, same-question-different-answer, or superseded, with per-hunk resolution rules. - Impartiality Contract: Enforces neutral arbitration — no favoring the spawning agent, no drive-by edits, and every design decision surfaced in the hand-back summary. - Kanban-Native Workflow: Integrates with hermes kanban cards so a third-party reconciler profile automatically receives both sides' completion summaries via parent links. - Use Case: During a parallel-PR campaign, two worker agents modify the same module. Spawn a neutral reconciler subagent with both branch names and intent summaries; it classifies each conflict, merges both intents, runs the build, and reports every decision for human veto. ## Quick Start Ask the agent to act as a neutral merge reconciler for the halted merge in this repository, using the completion summaries from both conflicting kanban tasks to classify and resolve each conflicted hunk.
