classify-simplicity-evidence

SkillDev tools

Lets your agent judge whether an explanation's simplicity is genuinely informative or just a relabeling.

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 classify-simplicity-evidence skill

About this skill

Classify simplicity/compression as earned, weak, or decorative based on whether it forbids alternatives, compresses independent facts, or merely renames/repackages them.

What this skill tells your AI

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

Purpose

Classify explanatory compression as earned, weak, or decorative.

Input contract

required: [explanation, covered_facts, alternatives, predictions]
optional: [evidence]
constraints: [facts and alternatives must be independently listed]

Procedure

  1. Check whether independent facts are compressed.
  2. Check whether alternatives are forbidden and predictions constrained.
  3. Classify earned, weak, or decorative and preserve rationale.

If simplicity provides discriminating support only through a vulnerable consequence, consider test-risky-prediction as the next tactic.

Output contract

produces: [simplicity_class, compression_evidence, missing_constraints]
delta_fields: [findings, evidence_updates, uncertainties, decisions]

Quality gates

  • Decorative simplicity is a relabeling with no independent compression or risky prediction.

Failure and counterexamples

Do not classify by description length or elegance alone.

Provenance map

  • resolved: elegance-trap-probe

Signals

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