Structured Consensus
Converge multiple independent perspectives into shared agreement through iterative structured dialogue. This campaign orchestrates Delphi variants, Nominal Group Technique, RAND/UCLA Appropriateness Method, and Consensus Conference protocols to systematically reduce disagreement while preserving legitimate dissent.
Strategy Routing
| Signal |
Strategy |
| Iterative convergence to single answer / establish guidelines / determine threshold |
convergence-distillation |
| Map disagreement structure / wicked problems / value conflicts |
disagreement-cartography |
| Aggregate probability judgments / technology timeline / market forecast |
futures-calibration |
| Establish acceptability standards / medical guidelines / regulatory standards |
appropriateness-bounding |
| Distill strongest arguments / policy deliberation / interdisciplinary dispute |
argument-crystallization |
Manifest
Strategies
| Strategy |
Method Family |
Purpose |
| convergence-distillation |
Classic Delphi, Modified Delphi, NGT |
Iterative convergence to single answer |
| disagreement-cartography |
Policy Delphi, Argument Delphi, SAST |
Map disagreement structure |
| futures-calibration |
Real-Time Delphi, Prediction Markets |
Aggregate probability judgments |
| appropriateness-bounding |
RAND/UCLA Appropriateness, Consensus Conference |
Establish acceptability standards |
| argument-crystallization |
Argument Delphi, Dialectical Delphi |
Distill strongest arguments |
Tactics
| Tactic |
Purpose |
SOPs |
| iterative-convergence-round |
Collect → feedback → revise → check → decide |
judgment-collection, feedback-distribution, consensus-measurement, round-decision |
| disagreement-mapping |
Collect → cluster → extract arguments → visualize |
judgment-collection, cluster-analysis, argument-extraction, disagreement-visualization |
| threshold-calibration |
Adjust thresholds → observe consensus changes |
threshold-sweep, consensus-classification, consensus-measurement |
SOPs
| SOP |
Input |
Output |
| judgment-collection |
question, perspectives[] |
judgments[] |
| feedback-distribution |
judgments[], round_n |
feedback_report |
| consensus-measurement |
judgments[] |
consensus_score, method_used |
| round-decision |
consensus_score, round_n, stability |
continue/stop |
| cluster-analysis |
judgments[] |
clusters[], cluster_characterization[] |
| argument-extraction |
cluster, judgments[] |
arguments[] |
| disagreement-visualization |
clusters[], arguments[] |
disagreement_map |
| threshold-sweep |
judgments[], threshold_range |
threshold_curve |
| consensus-classification |
judgments[], threshold |
consensus_items[], dissensus_items[] |
| consensus-synthesis |
rounds_history, final_judgments |
consensus_report |
Budget Table (M Tier)
| Parameter |
Constraint |
| Perspectives/experts |
>=4 independent perspectives |
| Iteration rounds |
2-4 rounds (until consensus threshold or stability) |
| Consensus threshold |
>=70% agreement or IQR <= 1 |
| Dissent documentation |
All non-consensus items must document reasons |
MCP Tools
mcp__semantic-scholar__relevanceSearch — find methodological referencesmcp__wiki-vault__vault_search — retrieve prior consensus results from vault
Context Management
- Each round's judgments are stored in state and passed forward
- Feedback reports summarize prior round without exposing individual identities
- Final synthesis aggregates all rounds into a single consensus report
- Non-consensus items are explicitly documented with dissent rationale
Available Strategies
Optional, no fixed order; the final leaf is always a sop.
| Strategy |
When to use |
| appropriateness-bounding |
Establish acceptability standards through RAND/UCLA Appropriateness Method or Consensus Conference protocols. |
| argument-crystallization |
Distill the strongest arguments from each perspective through Argument Delphi or Dialectical Delphi methods. |
| convergence-distillation |
Iterative convergence to a single answer through Classic Delphi, Modified Delphi, or Nominal Group Technique rounds. |
| disagreement-cartography |
Map the structure of disagreement across perspectives using Policy Delphi, Argument Delphi, or SAST methods. |
| futures-calibration |
Aggregate probability judgments across perspectives using Real-Time Delphi or prediction market mechanisms. |
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP |
When to use |
| context-checkpoint |
Append research process and results to the current Phase's context file. Covers both process and results with genuine substance. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. |
| context-init |
Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. |
| convergence-multi-stakeholder-simulation |
Simulates diverse stakeholder perspectives and their strongest objections/support arguments. Shared across steel-manning and consensus campaigns. |
| convergence-saturation-detection |
Determines when to stop iterating — coverage threshold met or marginal returns diminishing. Shared across all campaigns. |
Available Campaigns
Optional, no fixed order; the final leaf is always a sop.
| Campaign |
When to use |
| convergence-multi-criteria-scoring |
Multi-Criteria Scoring Campaign — evaluate and rank candidates against multiple weighted criteria using AHP, BWM, TOPSIS, VIKOR, ELECTRE, PROMETHEE, MAUT methods. |
1---2name: structured-consensus3description: Structured Consensus Campaign — converge multiple perspectives into shared agreement through iterative structured dialogue using Delphi variants, NGT, RAND/UCLA, Consensus Conference methods.4---56# Structured Consensus78Converge multiple independent perspectives into shared agreement through iterative structured dialogue. This campaign orchestrates Delphi variants, Nominal Group Technique, RAND/UCLA Appropriateness Method, and Consensus Conference protocols to systematically reduce disagreement while preserving legitimate dissent.910## Strategy Routing1112| Signal | Strategy |13|--------|----------|14| Iterative convergence to single answer / establish guidelines / determine threshold | convergence-distillation |15| Map disagreement structure / wicked problems / value conflicts | disagreement-cartography |16| Aggregate probability judgments / technology timeline / market forecast | futures-calibration |17| Establish acceptability standards / medical guidelines / regulatory standards | appropriateness-bounding |18| Distill strongest arguments / policy deliberation / interdisciplinary dispute | argument-crystallization |1920## Manifest2122### Strategies2324| Strategy | Method Family | Purpose |25|----------|--------------|---------|26| convergence-distillation | Classic Delphi, Modified Delphi, NGT | Iterative convergence to single answer |27| disagreement-cartography | Policy Delphi, Argument Delphi, SAST | Map disagreement structure |28| futures-calibration | Real-Time Delphi, Prediction Markets | Aggregate probability judgments |29| appropriateness-bounding | RAND/UCLA Appropriateness, Consensus Conference | Establish acceptability standards |30| argument-crystallization | Argument Delphi, Dialectical Delphi | Distill strongest arguments |3132### Tactics3334| Tactic | Purpose | SOPs |35|--------|---------|------|36| iterative-convergence-round | Collect → feedback → revise → check → decide | judgment-collection, feedback-distribution, consensus-measurement, round-decision |37| disagreement-mapping | Collect → cluster → extract arguments → visualize | judgment-collection, cluster-analysis, argument-extraction, disagreement-visualization |38| threshold-calibration | Adjust thresholds → observe consensus changes | threshold-sweep, consensus-classification, consensus-measurement |3940### SOPs4142| SOP | Input | Output |43|-----|-------|--------|44| judgment-collection | question, perspectives[] | judgments[] |45| feedback-distribution | judgments[], round_n | feedback_report |46| consensus-measurement | judgments[] | consensus_score, method_used |47| round-decision | consensus_score, round_n, stability | continue/stop |48| cluster-analysis | judgments[] | clusters[], cluster_characterization[] |49| argument-extraction | cluster, judgments[] | arguments[] |50| disagreement-visualization | clusters[], arguments[] | disagreement_map |51| threshold-sweep | judgments[], threshold_range | threshold_curve |52| consensus-classification | judgments[], threshold | consensus_items[], dissensus_items[] |53| consensus-synthesis | rounds_history, final_judgments | consensus_report |5455## Budget Table (M Tier)5657| Parameter | Constraint |58|-----------|-----------|59| Perspectives/experts | >=4 independent perspectives |60| Iteration rounds | 2-4 rounds (until consensus threshold or stability) |61| Consensus threshold | >=70% agreement or IQR <= 1 |62| Dissent documentation | All non-consensus items must document reasons |6364## MCP Tools6566- `mcp__semantic-scholar__relevanceSearch` — find methodological references67- `mcp__wiki-vault__vault_search` — retrieve prior consensus results from vault6869## Context Management7071- Each round's judgments are stored in state and passed forward72- Feedback reports summarize prior round without exposing individual identities73- Final synthesis aggregates all rounds into a single consensus report74- Non-consensus items are explicitly documented with dissent rationale7576<!-- BEGIN available-tables (generated) -->7778## Available Strategies7980Optional, no fixed order; the final leaf is always a sop.8182| Strategy | When to use |83| --- | --- |84| appropriateness-bounding | Establish acceptability standards through RAND/UCLA Appropriateness Method or Consensus Conference protocols. |85| argument-crystallization | Distill the strongest arguments from each perspective through Argument Delphi or Dialectical Delphi methods. |86| convergence-distillation | Iterative convergence to a single answer through Classic Delphi, Modified Delphi, or Nominal Group Technique rounds. |87| disagreement-cartography | Map the structure of disagreement across perspectives using Policy Delphi, Argument Delphi, or SAST methods. |88| futures-calibration | Aggregate probability judgments across perspectives using Real-Time Delphi or prediction market mechanisms. |8990## Available SOPs9192Optional, no fixed order; the final leaf is always a sop.9394| SOP | When to use |95| --- | --- |96| context-checkpoint | Append research process and results to the current Phase's context file. Covers both process and results with genuine substance. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase. |97| context-init | Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed. |98| convergence-multi-stakeholder-simulation | Simulates diverse stakeholder perspectives and their strongest objections/support arguments. Shared across steel-manning and consensus campaigns. |99| convergence-saturation-detection | Determines when to stop iterating — coverage threshold met or marginal returns diminishing. Shared across all campaigns. |100101## Available Campaigns102103Optional, no fixed order; the final leaf is always a sop.104105| Campaign | When to use |106| --- | --- |107| convergence-multi-criteria-scoring | Multi-Criteria Scoring Campaign — evaluate and rank candidates against multiple weighted criteria using AHP, BWM, TOPSIS, VIKOR, ELECTRE, PROMETHEE, MAUT methods. |108109<!-- END available-tables (generated) -->
yogsoth-ai