extract-structural-mapping

SkillDev tools

Lets your agent build an explicit element-by-element mapping between two structures to check a claimed equivalence.

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 extract-structural-mapping skill

About this skill

Construct an explicit source↔target mapping over objects, relations, operations, constraints, and invariants for a claimed structural equivalence.

What this skill tells your AI

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

Purpose

Construct an explicit source-to-target mapping over objects, relations, operations, constraints, and invariants.

Input contract

required: [source_structure, target_structure, mapping_claim]
optional: [required_objects, required_relations, invariants]
constraints: [mapping must preserve identity and provenance of mapped elements]

Procedure

  1. Enumerate source and target elements.
  2. Map objects, relations, operations, constraints, and invariants.
  3. Mark unmatched, ambiguous, and many-to-one mappings.

If source-target correspondences are explicit, consider test-structure-preservation as the next tactic.

Output contract

produces: [structural_mapping, unmatched_elements, ambiguity_report, invariant_inventory]
delta_fields: [findings, evidence_updates, uncertainties]

Quality gates

  • Every claimed preserved element has an explicit mapping or is marked absent.

Failure and counterexamples

Do not infer mapping from labels or surface resemblance.

Provenance map

  • resolved: isomorphism-falsification

Signals

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