Argument Mapping

SkillDev tools

Campaign for mapping argument structures — extract claims, link evidence,

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Argument Mapping skill

What this skill tells your AI

The instructions your AI receives, as published by yogsoth-ai/de-anthropocentric-research-engine in skills/argument-mapping/SKILL.md and read by ahel’s review.

Map argument structures for research domains. Extracts claims from sources, links supporting and opposing evidence, assesses argument strength, and synthesizes coherent positions from complex debates.

Manifest

LevelCountSkills
Strategy3claim-extraction, evidence-linking-arg, argument-synthesis
Tactic2claim-decomposition, strength-assessment
SOP6claim-page-creation, rebuttal-documentation, evidence-attachment, strength-scoring, argument-visualization, synthesis-report

Budget Table

MetricSmallMediumLarge
Claims extracted102550
Evidence links created154080
Rebuttals documented31020
Strength scores assigned102550
Synthesis reports135

Strategy Sequence (Reference, Not Prescription)

  1. claim-extraction — identify and extract claims from source material
  2. evidence-linking-arg — link evidence to claims (supporting, contradicting, qualifying)
  3. argument-synthesis — synthesize positions from the argument graph

MCP Tools Used

  • vault_search — find existing claims and evidence
  • vault_add_edge — create argument edges (supported_by, contradicts, derived_from)
  • vault_query_graph — trace argument chains
  • vault_graph_stats — assess argument coverage
  • vault_lint — validate structural integrity

Context-Management

Guiding Principles

  • Claims are atomic. Each claim page states exactly one proposition. Compound claims must be decomposed.
  • Evidence is typed. Every evidence link specifies its relationship: supports, contradicts, qualifies, or is irrelevant.
  • Strength is earned. A claim's strength comes from the weight and diversity of its evidence, not from authority or repetition.
  • Steel-man first. Before documenting rebuttals, ensure the strongest version of each claim is represented.
  • Synthesis is not averaging. The synthesis report identifies which claims survive scrutiny, not a compromise between all positions.

Available Strategies

Optional, no fixed order; the final leaf is always a sop.

StrategyWhen to use
argument-synthesisStrategy for synthesizing argument positions — aggregate evidence, resolve contradictions, produce synthesis reports identifying which claims survive scrutiny.
claim-extractionStrategy for extracting claims from source material — identify propositions, decompose compound claims, classify claim types, create claim pages in the vault.
evidence-linking-argStrategy for linking evidence to claims — find supporting/contradicting evidence, create typed edges, assess evidence quality, identify gaps in evidential coverage.

Available Tactics

Optional, no fixed order; the final leaf is always a sop.

TacticWhen to use
knowledge-compilationTactic for compiling research findings into vault pages — orchestrates page creation, updates, edge linking, and index maintenance. Minimum yield ≥3 page operations per invocation.

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

SOPWhen to use
context-checkpointAppend 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-initCreate 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.

Signals

GitHub stars
469
Forks
37
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
argument-mapping
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine