# Library Taxonomy Retrieval

> Dual retrieval: embedding similarity PLUS taxonomic adjacency in task ontology. Use when related concepts use different wording. Scope boundary: triangulation for facts → `survey-triangulation`.

- Skill: `catcorner22/library-taxonomy-retrieval` (Agent Skill)
- Install (CLI): `npx skillmds@latest add catcorner22/library-taxonomy-retrieval`
- Raw SKILL.md: https://api.skillmd.com/api/skills/catcorner22/library-taxonomy-retrieval/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: CatCorner22 (https://skillmd.com/u/catcorner22)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/catcorner22/library-taxonomy-retrieval

---

# Library taxonomy retrieval

**#24** · **Domain:** Library science · **Category:** memory · **Difficulty:** 🟡 Medium

## Core principle

Classification maps relationships — not just keyword proximity.

## AI problem addressed

Embedding-only misses structurally related but differently worded concepts.

## Implementation

1. Semantic search (embeddings)
2. Taxonomic browse (adjacent ontology nodes)
Merge results; dedupe; rank by task relevance.

## Boundaries

- Prototype as prompt scaffold (🟢) before full pipeline middleware (🟡/🔴)
- Category router: **`ai-transfer-memory`**
- Catalog: **`ai-transfer-ecosystem-primer`**
- Runtime plugin id: `catalog_retrieval`
- Also implements: `memory_palace`
- Merge notes: Also absorbs `memory_palace`: spatial room-walk as one retrieval mode.