# Hierarchy Construction

> Tactic for building is-a and part-of hierarchies — establish parent-child relationships, verify transitivity, detect cycles.

- Skill: `yogsoth-ai/hierarchy-construction-2` (Agent Skill)
- Install (CLI): `npx get-skill add yogsoth-ai/hierarchy-construction-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/hierarchy-construction-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: yogsoth-ai (https://skillmd.com/u/yogsoth-ai)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/yogsoth-ai/hierarchy-construction-2

---


# Hierarchy Construction

Build taxonomic hierarchies using component_of and instance_of edges. Ensure hierarchies are acyclic, transitive, and complete.

## Available SOPs

- edge-batch-creation — create hierarchy edges in bulk
- hierarchy-visualization — inspect current hierarchy structure
- gap-detection — find missing intermediate levels
- consistency-checking (tactic, peer) — verify no cycles

## Guiding Principles

- **Acyclic always.** A cycle in a hierarchy is a logical error. Detect and break immediately.
- **Intermediate levels matter.** Jumping from "machine learning" directly to "Adam optimizer" skips useful structure.
- **Multiple inheritance is fine.** A concept can belong to multiple parents (component_of multiple things).
- **Depth ≤ 5.** Hierarchies deeper than 5 levels are usually over-specified.

## Minimum Yield

<HARD-GATE>
≥3 hierarchy edges created per invocation.
If the hierarchy is already complete for the current scope, report and exit.
</HARD-GATE>

