construct-input-spaces

SkillDev tools

Lets your agent break source domains into entities, relations, goals and constraints to prepare conceptual blending.

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 construct-input-spaces skill

About this skill

Define the structured input spaces for conceptual blending: entities, relations, goals, constraints, and salient dynamics in each source.

What this skill tells your AI

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

Purpose

Define the explicit source spaces used by conceptual blending.

Input contract

required: [source_domains, blend_goal]
optional: [entities, relations, constraints, salient_dynamics]
constraints: [each source needs entities, relations, goals, and constraints or an explicit unknown]

Procedure

  1. Partition each source domain into entities, relations, goals, constraints, and dynamics.
  2. Normalize equivalent roles without erasing source-specific structure.
  3. Record the blend goal and the items eligible for projection.

If the input spaces and their correspondences are explicit, consider extract-generic-space as the next tactic.

Output contract

produces: [input_space_set, normalized_roles, projection_candidates]
delta_fields: [findings, hypothesis_updates, uncertainties]

Quality gates

  • Every input space is independently reconstructible and source-specific relations remain visible.

Failure and counterexamples

Reject an input space that is only a keyword list or that merges incompatible roles before blending.

Provenance map

  • conceptual-blending/input-space-construction: resolved.

Signals

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