Skip to content
Automation
Skill

/map-disagreement

Represent where perspectives/arguments agree, disagree, and why.

From plugin
de-anthropocentric-research-engine
499200 skills
Install
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill map-disagreement --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/map-disagreement

Context preview

The summary Claude sees to decide when to auto-load this skill.

Represent where perspectives/arguments agree, disagree, and why.

SKILL.md

map-disagreement.SKILL.md
name: map-disagreement
description: "Represent where perspectives/arguments agree, disagree, and why."

map-disagreement

Purpose

Represent where perspectives or arguments agree, disagree, and why.

Input contract

required: [perspectives, claims_or_arguments, comparison_dimensions]
optional: [evidence, clustering_rule, convergence_measure]
constraints: [agreement and disagreement are tied to the same proposition and comparison dimension; preserve minority positions]

Procedure

1. Normalize perspectives, propositions, and evidence. 2. Cluster equivalent positions and separate agreement from disagreement. 3. Attribute each disagreement to evidence, assumptions, scope, values, or definitions. 4. Report convergence trends and unresolved fault lines.

Output contract

produces: [agreement_map, disagreement_register, cluster_arguments, convergence_trends]
delta_fields: [findings, evidence_updates, uncertainties, open_questions]

Quality gates

  • Preserve source thresholds when the divergence mode applies: consensus >70% and disagreement >50%.
  • The map includes reasons and evidence for each fault line; percentages describe the supplied perspective set, not population truth.
  • Collection, clustering, argument extraction, and visualization remain separable outputs.

Parameterization

The caller must provide perspective schema, proposition identity, comparison dimensions, agreement rule, disagreement rule, evidence links, and the population represented by any percentages.

Failure and counterexamples

Reject comparisons across different propositions or scopes, and reject consensus claims when the denominator of perspectives is absent.

Provenance map

  • resolved: convergence/disagreement-mapping
  • resolved: stress-test/divergence-detection

Preserved source criteria ledger

| source | physical line | kind | source criterion | |---|---:|---|---| | stress-test/divergence-detection | 14 | percentage | Consensus is >70%; disagreement is >50%; identify convergence trends. |

Read more
Ships withde-anthropocentric-research-engine

The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.

Get the whole plugin
Stats
499
Stars
41
Forks
Active
Maintenance
Python
Language
Apache-2.0
License
8h ago
Last commit
7mo ago
Created

Repo: yogsoth-ai/de-anthropocentric-research-engine