org-agent-contrib/org-skill-hyper-graph.org

SKILL: Unified Knowledge Hyper-Graph (Universal Literate Note)

• Overview
• Phase A: Demand (PRD)
  • 1. Purpose
  • 2. User Needs
• Phase D: Build (Implementation)
  • Graph Traversal
• Registration
• Phase B: Blueprint (PROTOCOL)
• Phase B: Blueprint (PROTOCOL)
  • 1. Architectural Intent

Overview

The Unified Knowledge Hyper-Graph extends the agent's memory beyond text. It maps relationships between Code Blocks, Documents, Media Assets, and Research PDFs, enabling cross-modal context retrieval.

Phase A: Demand (PRD)

1. Purpose

Unify the system's diverse information silos into a single, navigable graph.

2. User Needs

• Cross-Modal Linking: Connect a Lisp function to a research PDF and an Org PRD.
• Traceability: Follow the chain of reasoning from requirement to implementation.
• Deep Retrieval: Pull related media assets during plan synthesis.

Phase D: Build (Implementation)

Graph Traversal

(defun hyper-graph-trace-lineage (object-id)
  "Recursively follows #+ID and [[file:]] links to find related cross-modal nodes."
  (let* ((obj (opencortex:lookup-object object-id))
         (links (extract-all-org-links (opencortex:org-object-content obj))))
    (kernel-log "MEMORY [Hyper-Graph] - Tracing lineage for ~a..." object-id)
    (loop for link in links collect (resolve-hyper-link link))))

Registration

(defskill :skill-hyper-graph
  :priority 70
  :trigger (lambda (context) (eq (getf (getf context :payload) :sensor) :deep-trace))
  :neuro (lambda (context) "Synthesize a lineage report for the target ID.")
  :symbolic (lambda (action context) action))

Phase B: Blueprint (PROTOCOL)

Phase B: Blueprint (PROTOCOL)

1. Architectural Intent

• Graph Database: Utilize an in-memory or persistent graph database (e.g., `neo4cl`). Abstract away the underlying implementation via a generic interface.
• Unified ID Space: Every