build-noncircularity-matrix

SkillDev tools

Lets your agent build a claude skill-style matrix that checks whether a theory's validation is circular.

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

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the build-noncircularity-matrix skill

About this skill

Cross-tabulate target theory claims/assumptions against validator assumptions and mark independent, shared, derived-from-target, or unknown dependencies.

What this skill tells your AI

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

Purpose

Cross-tabulate target claims/assumptions against validator assumptions and expose circularity.

Input contract

required: [target_claims, target_assumptions, validator_assumptions]
optional: [evidence_channels]
constraints: [each cell is independent/shared/derived-from-target/unknown]

Procedure

  1. Enumerate both assumption sets.
  2. Populate dependency cells with evidence.
  3. Identify copied assumptions and independent failure channels.

If the matrix exposes shared premises or dependent validation paths, consider detect-pass-by-construction as the next tactic.

Output contract

produces: [noncircularity_matrix, dependency_summary, independent_channels]
delta_fields: [findings, evidence_updates, uncertainties, decisions]

Quality gates

  • Unknown dependencies remain unknown; they are not counted independent.
  • At least one non-circular channel is required for validation.

Failure and counterexamples

A validator that embeds the target claim cannot corroborate it by construction.

Provenance map

  • resolved: circular-validation-audit

Signals

GitHub stars
501
Forks
41
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
build-noncircularity-matrix
Source
github.com/yogsoth-ai/de-anthropocentric-research-engine