apply-separation-principle

SkillDev tools

Lets your agent solve design conflicts by separating opposing requirements in time, space, scale, or condition.

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 apply-separation-principle skill

About this skill

Resolve a physical contradiction by separating conflicting requirements in time, space, scale, condition, or system level.

What this skill tells your AI

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

Purpose

Resolve a physical contradiction by separating conflicting requirements in time, space, scale, condition, or system level.

Input contract

required: [contradiction, conflicting_requirements]
optional: [system_boundary, operating_conditions]
constraints: [requirements must be stated as mutually conflicting outcomes]

Procedure

  1. State the useful and harmful effects that cannot coexist (conflicting_requirements).
  2. Test separation in time, space, scale, condition, and system level.
  3. Select the separation that removes the conflict and state its operating condition.

Output contract

produces: [separation_candidates, selected_principle, operating_condition]
delta_fields: [findings, hypothesis_updates, decisions, uncertainties]

Quality gates

  • Each candidate names the separated dimension and preserves the useful effect while removing the harmful one.

Failure and counterexamples

Do not call parameter tuning a separation when both requirements still occur under the same condition.

Provenance map

  • triz/separation-principles: concept (the exact pool entry is singular separation-principle; near-name substitution is forbidden).

Signals

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