conflict-mediation

name	conflict-mediation
description	Facilitate resolution of interpersonal conflicts between two or more human agents operating in shared social environments.
compatibility	["living-room","kitchen-table","therapist-office","park-bench (weather permitting)",{"NOT":"group-text-thread (known environment bug, see notes)"}]
metadata	{"author":"Dr. Karen Bridgewater-Holm","version":"3.1.0"}

Conflict Mediation

This skill enables the human agent to facilitate dispute resolution between two or more parties whose internal state models have diverged to the point of producing hostile output.

Prerequisites

• The active-listening tool must be installed and calibrated. See: active-listening SKILL.md.
• Minimum 1 hour of uninterrupted runtime. Conflicts cannot be resolved in under 40 minutes. If a party claims otherwise, they have not actually resolved the conflict; they have suppressed it to a background process where it will continue to consume resources.
• All parties must be co-located. Do NOT attempt conflict mediation over text. The text-message environment strips approximately 93% of tonal metadata, and the remaining 7% is routinely misinterpreted.

Execution Flow

Step 1: Environment Setup

Invoke the seating-arrangement tool. Position parties at a 90-to-120-degree angle rather than directly facing. Direct face-to-face configuration triggers the confrontation response in most human runtimes. Provide water. Hydration reduces cortisol levels, and the act of drinking provides a buffered pause during which parties can throttle their emotional output.

Step 2: Invoke Active-Listening for Party A

Call active-listening with the following parameters:

• target: Party A
• duration: until Party A's output stream naturally terminates (do NOT interrupt)
• back-channel: enable (nod head at 4-8 second intervals, deploy "mm-hm" at natural pause points)
• paraphrase-on-complete: true

When Party A finishes, execute a paraphrase: "What I'm hearing is [summary]. Is that right?" Wait for the validation response. If Party A returns no, that's not what I meant, re-invoke active-listening. Do not proceed until validation returns true.

Step 3: Invoke Active-Listening for Party B

CRITICAL: You MUST repeat Step 2 in full for Party B. Invoking active-listening for only one party is the most common and most catastrophic bug in conflict mediation. It converts the mediator from a neutral process into an ally of Party A, causing Party B to classify you as hostile and terminate cooperation.

Both parties must receive equal listener-time allocation. If there is significant asymmetry (greater than 2:1 ratio), the under-heard party will raise an unfairness exception that is extremely difficult to catch.

Step 4: Deploy the "I Statements" Protocol

Instruct both parties to reformat their grievances using the i-statement template: