Skills

memory-management

Installation
Summary

Two-layer memory system for SEO/GEO projects with hot cache and cold storage.

  • Maintains a lean hot cache (CLAUDE.md, ~100 lines) for active context and structured cold storage directories for keywords, competitors, audits, and historical data
  • Automatically promotes frequently referenced items to hot cache and demotes stale data to archives based on reference frequency and age
  • Implements efficient context lookup flow across hot cache, glossary, and cold storage layers with intelligent retrieval and user fallback
  • Integrates with eight related SEO skills (rank-tracker, competitor-analysis, keyword-research, performance-reporter, content-gap-analysis, seo-content-writer, content-quality-auditor, domain-authority-auditor) to auto-populate memory after analyses and reports
  • Includes project glossary management, timestamped archive routines, memory health checks, and bulk promotion/demotion for campaign-scale updates
SKILL.md

Memory Management

This skill implements a three-tier memory system (HOT/WARM/COLD) for SEO and GEO projects. HOT memory (80 lines max) loads automatically every session via the SessionStart hook. WARM memory loads on demand per skill. COLD memory is archived data queried only when explicitly requested. The skill manages the full lifecycle: capture, promote, demote, and archive.

What This Skill Does

Manages a three-tier memory lifecycle (HOT/WARM/COLD) with automatic promotion, demotion, and archival. Also maintains the wiki index layer, open-loop tracking, and cross-skill aggregation.

Quick Start

Start with one of these prompts. Finish with a hot-cache update plan and a handoff summary using the repository format in Skill Contract.

Initialize Wiki Index

Refresh wiki index

Build wiki index for [project name]
Related skills

More from aaron-he-zhu/seo-geo-claude-skills

Installs
3.3K
Repository
aaron-he-zhu/se…e-skills
GitHub Stars
1.6K
First Seen
Feb 6, 2026
Security Audits
Gen Agent Trust HubPass
SocketPass
SnykWarn