agent-merge-conflict-arbiter

Resolves git merge conflicts between two agent branches as a neutral third-party arbiter.

Updated Sep 10, 2026
One-click install
npx skills add https://github.com/loteiron/ZeusAgent --skill agent-merge-conflict-arbiter-loteiron
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-merge-conflict-arbiter
Source: https://github.com/loteiron/ZeusAgent/tree/main/optional-skills/autonomous-ai-agents/agent-merge-conflict-arbiter
Command: npx skills add https://github.com/loteiron/ZeusAgent --skill agent-merge-conflict-arbiter-loteiron

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When two 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 change, 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Cases - Hunk Classification: Categorizes every conflicted hunk as disjoint-intent, same-question-different-answer, or superseded, with per-hunk rationale.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-Native Spawning: Supports delegation via a third neutral profile with both conflicted cards linked as parents so intent summaries flow into context automatically. - Use Case: During a parallel-PR wave, two agent branches collide on a shared module. Spawn a reconciler subagent with both branch names and completion 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 act as a neutral arbiter and resolve the halted merge between branch-a and branch-b in this repo, following the classify-resolve-verify procedure and reporting every hunk decision.

Frequently Asked Questions about agent-merge-conflict-arbiter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I resolve git merge conflicts between two AI agents?▼

Spawn a neutral third agent with the repo path, both branch names, and both sides' intent summaries. It classifies each conflicted hunk as disjoint-intent, same-question-different-answer, or superseded, then merges, stages, verifies with tests, and commits.

Why shouldn't an agent resolve conflicts against a peer's branch itself?▼

Agents lack the peer's context and are biased toward their own change, so they reliably overwrite the peer's work or abandon their own. A neutral arbiter with both stated intents produces a fair merged result.

When should I not use a merge-conflict arbiter?▼

Do not use it for conflicts within a single agent's own work or for trivial lockfile and generated-file conflicts, which should simply be regenerated. It targets genuine collisions between two agents' parallel branches.

Can the arbiter work with kanban-based multi-agent workflows?▼

Yes. Create a reconciliation card assigned to a third profile with both conflicted cards linked as parents via kanban_create. The parent links carry both completion summaries into the reconciler's context automatically.

What happens if both sides' intents genuinely tie on a design decision?▼

The arbiter escalates by blocking the kanban card or reporting back rather than guessing. It never splits the difference into a hybrid neither side designed, and every design pick is surfaced in the hand-back summary for human veto.