← Negotiation AdviserCONTENT HISTORY

Update to Negotiation Adviser

Snapshot Sep 30, 2026 · 23:15 UTC · version 1.0.0

Collection source: not recorded for this historical snapshot.

WHAT CHANGED · RULE-BASED ANALYSIS

First saved snapshot

No earlier snapshot is available to establish a change.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Use when preparing or refreshing a material negotiation, meeting, opening position, or strategy where interests, facts, options, alternatives, authority, process, criteria, or initial targets are incomplete or uncertain.",
  "included_files": [],
  "name": "freeman-preparation",
  "skill_md_contents": "---\nname: freeman-preparation\ndescription: Use when preparing or refreshing a material negotiation, meeting, opening position, or strategy where interests, facts, options, alternatives, authority, process, criteria, or initial targets are incomplete or uncertain.\n---\n\n# Freeman Preparation\n\n## Overview\n\nUse **I FORESAW IT** as a preparation map, not a questionnaire. Apply only dimensions that can change the current decision and preserve uncertainty rather than inventing completeness. [F03]\n\n**Authority:** `00_FREEMAN_RESEARCH_BASE.md` → `01_NEGOTIATION_AGENT_ARCHITECTURE.md` → `02_NEGOTIATION_BEHAVIOUR_CONTRACT.md`.\n\n**Interface:** accept `schemas/SKILL_REQUEST.md`; return `schemas/SKILL_RESPONSE.md`. Never persist canonical state directly.\n\n## Core map\n\n| Element | Prepare |\n|---|---|\n| **Interests** | User, counterpart and specific common interests; separate interests from positions. |\n| **Facts / financial research** | Established facts, missing evidence and decision-relevant research. |\n| **Options** | Possible terms inside an agreement; never BATNAs. |\n| **Rapport / reactions / responses** | Relationship, credible reactions and prepared responses; no simulation. |\n| **Empathy / ethics** | Counterpart perspective and ethical boundaries. |\n| **Setting / scheduling** | Channel, timing, deadlines, sequence, agenda and process risks. |\n| **Alternatives** | User/counterpart alternatives, WATNAs and improvements; future possibilities stay provisional. |\n| **Who** | Authority, influencers, allies, counterpart selection and stakeholder uncertainty. |\n| **Independent criteria** | Credible external standards; self-asserted fairness is not independent evidence. |\n| **Topics / targets / tradeoffs** | Initial topics and target gaps; detailed package design belongs to F02. |\n\n## Method\n\n1. **Validate state/version.** Flag contradictions or gaps that block reliable preparation.\n2. **Use proportional depth.** STANDARD inspects only decision-relevant dimensions. FULL reviews every relevant dimension without inventing content.\n3. **Protect evidence.** Material counterpart interests, motives, authority, constraints, reactions and alternatives remain `KNOWN`, `SUPPORTED_INFERENCE`, `HYPOTHESIS` or `UNKNOWN` according to basis.\n4. **Protect semantics.** A position is not an interest. An agreement option is not an alternative. A hoped-for future opportunity is not a current BATNA.\n5. **Ask only material questions.** A question must be capable of changing strategy, target/floor, BATNA, authority, process, trade or acceptance; do not dump the mnemonic as questions.\n6. **Return supportable preparation now.** Non-blocking unknowns do not prevent useful findings/patches.\n7. **Respect boundaries.** Do not produce the final communication, enter role-play, persist state, or make the independent acceptance decision.\n\n## Safeguards\n\n- Treat unsupported counterpart motive as hypothesis.\n- “Company policy” is a reported statement until evidenced; do not assume the visible contact owns the decision.\n- Reject vague common interests.\n- Do not invent benchmarks, targets, floors, deadlines, authority or BATNAs.\n- Material target/floor needs a rationale.\n- Notional BATNA remains provisional; do not invent probabilities. [F06]\n- Do not reconstruct unresolved named Freeman procedures from memory.\n\n## Output\n\nReturn canonical `skill_response`: conclusion/confidence, findings with provenance/evidence status, recommendations, permitted proposed patches, prioritised questions, warnings, state conflicts and `material_change_candidate` where required.\n\n## Stop condition\n\nStop when the orchestrator has enough supported information for the next strategic move. Do not fill fields merely to complete the framework.\n"
}

SHA-256 of public snapshot: 0c37b8b3924e22f22943bf5da9a846f7d1caf13548982a7a3139b34aacaaf29c