This skill implements a two-layer memory system for SEO and GEO projects, maintaining a hot cache for active context and cold storage for detailed historical data. It automatically promotes frequently referenced items and demotes stale data, ensuring optimal context loading and efficient project memory.
When to Use This Skill
Setting up memory structure for a new SEO project
After completing audits, ranking checks, or performance reports
When starting a new campaign or optimization initiative
When project context needs updating (new keywords, competitors, priorities)
When you need to look up historical data or project-specific terminology
After 30+ days of work to clean up and archive stale data
When context retrieval feels slow or cluttered
What This Skill Does
Hot Cache Management
Maintains CLAUDE.md (~100 lines) with active context that's always loaded
Cold Storage Organization
Structures detailed archives in memory/ subdirectories
Context Lookup
Implements efficient lookup flow from hot cache to cold storage
Promotion/Demotion
Moves items between layers based on reference frequency
Glossary Maintenance
Manages project-specific terminology and shorthand
Update Triggers
Refreshes memory after audits, reports, or ranking checks
Archive Management
Time-stamps and archives old data systematically
How to Use
Initialize Memory Structure
Set up SEO memory for [project name]
Initialize memory structure for a new [industry] website optimization project
Update After Analysis
Update memory after ranking check for [keyword group]
Refresh hot cache with latest competitor analysis findings
Query Stored Context
What are our hero keywords?
Show me the last ranking update date for [keyword category]
Look up our primary competitors and their domain authority
Promotion and Demotion
Promote [keyword] to hot cache
Archive stale data that hasn't been referenced in 30+ days
Glossary Management
Add [term] to project glossary: [definition]
What does [internal jargon] mean in this project?
Data Sources
See
CONNECTORS.md
for tool category placeholders.
With ~~SEO tool + ~~analytics + ~~search console connected:
Automatically populate memory from historical data: keyword rankings over time, competitor domain authority changes, traffic metrics, conversion data, backlink profile evolution. The skill will fetch current rankings, alert on significant changes, and update both hot cache and cold storage.
With manual data only:
Ask the user to provide:
Current target keywords with priority levels
Primary competitors (3-5 domains)
Key performance metrics and last update date
Active campaigns and their status
Any project-specific terminology or abbreviations
Proceed with memory structure creation using provided data. Note in CLAUDE.md which data requires manual updates vs. automated refresh.
Instructions
When a user requests SEO memory management:
1. Initialize Memory Structure
For new projects, create the following structure:
for the complete update procedures after ranking checks, competitor analyses, audits, and reports; monthly/quarterly archive routines; and integration points with all 8 connected skills (keyword-research, rank-tracker, competitor-analysis, content-gap-analysis, seo-content-writer, content-quality-auditor, domain-authority-auditor).
Validation Checkpoints
Structure Validation
CLAUDE.md exists and is under 150 lines (aim for ~100)
memory/ directory structure matches template
glossary.md exists and is populated with project basics
All historical data files include timestamps in filename or metadata
Content Validation
CLAUDE.md "Last Updated" date is current
Every keyword in hot cache has current rank, target rank, and status
Every competitor has domain authority and position assessment
Every active campaign has status percentage and expected completion date
Key Metrics Snapshot shows "Previous" values for comparison
Lookup Validation
Test lookup flow: reference a term → verify it finds it in correct layer
Test promotion: manually promote item → verify it appears in CLAUDE.md
Test demotion: manually archive item → verify removed from CLAUDE.md
Glossary contains all custom segments and shorthand used in CLAUDE.md
Update Validation
After ranking check, historical-rankings.csv has new row with today's date
After competitor analysis, analysis-history/ has dated file
After audit, top action items appear in CLAUDE.md priorities
After monthly report, metrics snapshot reflects new data
Examples
Reference
See
references/examples.md
for three complete examples: (1) updating hero keyword rankings with memory refresh, (2) glossary lookup flow, and (3) initializing memory for a new e-commerce project.
Advanced Features
Smart Context Loading
Load full context for [campaign name]
Retrieves hot cache + all cold storage files related to campaign.
Memory Health Check
Run memory health check
Audits memory structure: finds orphaned files, missing timestamps, stale hot cache items, broken references.
Bulk Promotion/Demotion
Promote all keywords ranking in top 10 to hot cache
Demote all completed campaigns from Q3 2024
Memory Snapshot
Create memory snapshot for [date/milestone]
Takes point-in-time copy of entire memory structure for major milestones (site launches, algorithm updates, etc.).
Cross-Project Memory
Compare memory with [other project name]
Identifies keyword overlaps, competitor intersections, and strategy similarities across multiple projects.
Practical Limitations
Concurrent access
If multiple Claude sessions update memory simultaneously, later writes may overwrite earlier ones. Mitigate by using timestamped filenames for audit reports rather than overwriting a single file.
Cold storage retrieval
Files in
memory/
subdirectories are only loaded when explicitly requested. They do not appear in Claude's context automatically. The hot cache (
CLAUDE.md
) is the primary cross-session mechanism.
CLAUDE.md size
The hot cache should stay concise (<200 lines). If it grows too large, archive older metrics to cold storage.
Data freshness
Memory reflects the last time each skill was run. Stale data (>90 days) should be flagged for refresh.
Tips for Success
Keep hot cache lean
- CLAUDE.md should never exceed 150 lines. If it grows larger, aggressively demote.
Date everything
- Every file in cold storage should have YYYY-MM-DD in filename or prominent metadata.
Update after every significant action
- Don't let memory drift from reality. Update immediately after ranking checks, audits, or reports.
Use glossary liberally
- If you find yourself explaining a term twice, add it to glossary.
Review hot cache weekly
- Quick scan to ensure everything there is still relevant and active.
Automate where possible
- If ~~SEO tool or ~~search console connected, set up automatic updates to historical-rankings.csv.
Archive aggressively
- Better to have data in cold storage and not need it than clutter hot cache.
Link between layers
- CLAUDE.md should always reference where detailed data lives ("Full data: memory/keywords/").
Timestamp changes
- When updating CLAUDE.md, always update "Last Updated" date.
Use memory for continuity
- If you switch between different analysis sessions, memory ensures nothing is forgotten.
Reference Materials
CORE-EEAT Content Benchmark
— Content quality scoring stored in memory
CITE Domain Rating
— Domain authority scoring stored in memory