memory-managementManages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with i...
Install via ClawdBot CLI:
clawdbot install aaron-he-zhu/memory-managementSEO & GEO Skills Library ยท 20 skills for SEO + GEO ยท Install all: npx skills add aaron-he-zhu/seo-geo-claude-skills
Research ยท keyword-research ยท competitor-analysis ยท serp-analysis ยท content-gap-analysis
Build ยท seo-content-writer ยท geo-content-optimizer ยท meta-tags-optimizer ยท schema-markup-generator
Optimize ยท on-page-seo-auditor ยท technical-seo-checker ยท internal-linking-optimizer ยท content-refresher
Monitor ยท rank-tracker ยท backlink-analyzer ยท performance-reporter ยท alert-manager
Cross-cutting ยท content-quality-auditor ยท domain-authority-auditor ยท entity-optimizer ยท memory-management
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.
Set up SEO memory for [project name]
Initialize memory structure for a new [industry] website optimization project
Update memory after ranking check for [keyword group]
Refresh hot cache with latest competitor analysis findings
What are our hero keywords?
Show me the last ranking update date for [keyword category]
Look up our primary competitors and their domain authority
Promote [keyword] to hot cache
Archive stale data that hasn't been referenced in 30+ days
Add [term] to project glossary: [definition]
What does [internal jargon] mean in this project?
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:
Proceed with memory structure creation using provided data. Note in CLAUDE.md which data requires manual updates vs. automated refresh.
When a user requests SEO memory management:
For new projects, create the following structure:
## Directory Structure
project-root/
โโโ CLAUDE.md # Hot cache (~100 lines)
โโโ memory/
โโโ glossary.md # Project terminology
โโโ keywords/
โ โโโ hero-keywords.md # Top priority keywords
โ โโโ secondary-keywords.md # Medium priority
โ โโโ long-tail-keywords.md # Long-tail opportunities
โ โโโ historical-rankings.csv # Dated ranking data
โโโ competitors/
โ โโโ primary-competitors.md # Top 3-5 competitors
โ โโโ [competitor-domain].md # Individual reports
โ โโโ analysis-history/ # Dated analyses
โโโ audits/
โ โโโ technical/ # Technical SEO audits
โ โโโ content/ # Content audits
โ โโโ domain/ # Domain authority (CITE) audits
โ โโโ backlink/ # Backlink audits
โโโ content-calendar/
โ โโโ active-calendar.md # Current quarter
โ โโโ published-content.md # Performance tracking
โ โโโ archive/ # Past calendars
โโโ reports/
โโโ monthly/ # Monthly reports
โโโ quarterly/ # Quarterly reports
โโโ campaign/ # Campaign-specific reports
Create or update CLAUDE.md with this template:
# [Project Name] - SEO Memory (Hot Cache)
**Last Updated**: [Date]
**Project Status**: [Active/Maintenance/Growth]
## Active Target Keywords (Top 10-20)
### Hero Keywords (Priority 1)
| Keyword | Current Rank | Target Rank | Volume | Status |
|---------|--------------|-------------|--------|--------|
| [keyword 1] | #[X] | #[Y] | [vol] | [tracking/optimizing/achieved] |
| [keyword 2] | #[X] | #[Y] | [vol] | [tracking/optimizing/achieved] |
### Secondary Keywords (Priority 2)
| Keyword | Current Rank | Target Rank | Volume | Status |
|---------|--------------|-------------|--------|--------|
| [keyword 1] | #[X] | #[Y] | [vol] | [tracking/optimizing/achieved] |
_Full keyword database: memory/keywords/_
## Primary Competitors (Top 3-5)
1. **[Competitor 1]** (DA: [X])
- Main strengths: [brief]
- Our position vs. them: [ahead/behind/competitive]
2. **[Competitor 2]** (DA: [X])
- Main strengths: [brief]
- Our position vs. them: [ahead/behind/competitive]
_Detailed analyses: memory/competitors/_
## Current Optimization Priorities
1. **[Priority 1]** - [Brief description]
- Status: [not started/in progress/completed]
- Expected impact: [high/medium/low]
- Deadline: [date]
2. **[Priority 2]** - [Brief description]
- Status: [not started/in progress/completed]
- Expected impact: [high/medium/low]
- Deadline: [date]
## Key Metrics Snapshot
**Last Metrics Update**: [Date]
| Metric | Current | Previous | Change | Target |
|--------|---------|----------|--------|--------|
| Organic Traffic | [X] | [X] | [+/-X%] | [target] |
| Avg. Position | [X] | [X] | [+/-X] | [target] |
| Total Keywords Ranking | [X] | [X] | [+/-X] | [target] |
| Page 1 Rankings | [X] | [X] | [+/-X] | [target] |
| Domain Authority | [X] | [X] | [+/-X] | [target] |
| CITE Score | [X] | [X] | [+/-X] | [target] |
| Last Content Audit Score | [score]/100 | ([rating]) | โ [date] | [page audited] |
| Total Backlinks | [X] | [X] | [+/-X%] | [target] |
_Historical data: memory/reports/_
## Active Campaigns
### [Campaign Name 1]
- **Duration**: [Start date] - [End date]
- **Goal**: [Specific goal]
- **Status**: [planning/active/completed]
- **Progress**: [X]%
- **Key activities**: [brief list]
### [Campaign Name 2]
- **Duration**: [Start date] - [End date]
- **Goal**: [Specific goal]
- **Status**: [planning/active/completed]
- **Progress**: [X]%
- **Key activities**: [brief list]
_Campaign archives: memory/reports/campaign/_
## Quick Reference Notes
- [Important note 1]
- [Important note 2]
- [Important note 3]
_For project terminology, see: memory/glossary.md_
# [Project Name] - SEO Glossary
**Purpose**: Project-specific terminology, brand terms, internal jargon, and abbreviations.
**Last Updated**: [Date]
## Brand Terms
| Term | Full Name | Context |
|------|-----------|---------|
| [abbreviation] | [full name] | [when/how it's used] |
## Product Names
| Internal Name | Public Name | Category |
|---------------|-------------|----------|
| [code name] | [market name] | [product type] |
## Custom Segments
| Segment Name | Definition | Keyword Count |
|--------------|------------|---------------|
| Hero KWs | Top 10 revenue-driving keywords | 10 |
| Quick Wins | Low-difficulty, high-value targets | 25 |
| Brand Defense | Brand + modifier combinations | 15 |
## Competitor Shorthand
| Shorthand | Full Domain | Notes |
|-----------|-------------|-------|
| Comp A | competitor-a.com | Main competitor, [industry] |
| Comp B | competitor-b.com | Niche competitor, [specialty] |
## Project Acronyms
| Acronym | Full Term | Definition |
|---------|-----------|------------|
| [ABC] | [Full term] | [What it means in this project] |
## Internal Jargon
| Phrase | Meaning | Example Usage |
|--------|---------|---------------|
| [phrase] | [definition] | "Check rankings for [phrase]" |
## Historical Context
- **Project started**: [Date]
- **Major algorithm updates affecting us**: [List with dates]
- **Site migrations/redesigns**: [List with dates]
- **Key milestones**: [List with dates]
---
_This glossary helps decode project shorthand and maintain consistency across reports and communications._
When a user references something unclear, follow this lookup sequence:
Step 1: Check CLAUDE.md (Hot Cache)
Step 2: Check memory/glossary.md
Step 3: Check Cold Storage
Step 4: Ask User
Example lookup:
User: "Update rankings for our hero KWs"
Step 1: Check CLAUDE.md โ Found "Hero Keywords (Priority 1)" section
Step 2: Extract keyword list from hot cache
Step 3: Execute ranking check
Step 4: Update both CLAUDE.md and memory/keywords/historical-rankings.csv
Promote to Hot Cache when:
Promotion action:
1. Add item to relevant section in CLAUDE.md
2. Add note: "Promoted [date] - [reason]"
3. Keep detailed data in cold storage
4. Set reminder to review in 30 days
Demote to Cold Storage when:
Demotion action:
1. Remove from CLAUDE.md
2. Archive full data in memory/[category]/archive/
3. Add line to CLAUDE.md: "Last reviewed [category]: [date]"
4. Keep 1-line summary if historically significant
After specific events, update memory systematically:
After Ranking Check:
1. Update CLAUDE.md โ Hero Keywords table (current ranks)
2. Append to memory/keywords/historical-rankings.csv
3. Note any keywords with significant movement
4. Update "Last Metrics Update" date in CLAUDE.md
5. If hero keyword moves ยฑ5 positions, create alert note
After Competitor Analysis:
1. Update CLAUDE.md โ Primary Competitors section (DA, position vs. them)
2. Save full report to memory/competitors/analysis-history/YYYY-MM-DD-analysis.md
3. Update individual competitor files if detailed findings
4. Note new competitor strategies in hot cache
After Audit (Technical/Content/Backlink):
1. Save full report to memory/audits/[type]/YYYY-MM-DD-[audit-name].md
2. Extract top 3-5 action items โ CLAUDE.md Current Optimization Priorities
3. Update Key Metrics Snapshot if audit includes metrics
4. Create campaign entry if audit spawns new initiative
After Monthly/Quarterly Report:
1. Save report to memory/reports/[period]/YYYY-MM-report.md
2. Update all metrics in CLAUDE.md Key Metrics Snapshot
3. Review hot cache โ demote stale items
4. Update campaign statuses
5. Archive completed campaigns
Monthly Archive Routine:
1. Review CLAUDE.md for items not referenced in 30 days
2. Move stale items to appropriate cold storage
3. Create monthly snapshot: memory/snapshots/YYYY-MM-CLAUDE.md
4. Compress old historical-rankings.csv (keep only last 90 days in main file)
5. Update glossary with new terms from the month
Quarterly Archive Routine:
1. Review entire cold storage structure
2. Compress files older than 6 months
3. Create quarterly summary report
4. Update project timeline in glossary
5. Audit all active campaigns โ archive completed ones
This skill coordinates with other SEO skills:
When keyword-research runs:
When rank-tracker runs:
When competitor-analysis runs:
When content-gap-analysis runs:
When seo-content-writer produces content:
When content-quality-auditor runs:
memory/audits/content/YYYY-MM-DD-core-eeat-[page-slug].mdWhen domain-authority-auditor runs:
User: "Update rankings for our hero keywords"
Assistant:
I'll update rankings for your hero keywords. Let me check the hot cache for the list.
[Reads CLAUDE.md, finds Hero Keywords section:]
- keyword research tools (currently #15, target #5)
- best seo software (currently #23, target #10)
- free backlink checker (currently #8, target #3)
- content optimization guide (currently #12, target #5)
- technical seo audit (currently #18, target #8)
[If ~~SEO tool connected: runs automated ranking check]
[If manual: asks user for current rankings]
---
## Ranking Update - December 15, 2024
| Keyword | Previous | Current | Change | Target | Status |
|---------|----------|---------|--------|--------|--------|
| keyword research tools | #15 | #12 | โ3 | #5 | Improving โญ |
| best seo software | #23 | #24 | โ1 | #10 | Stable |
| free backlink checker | #8 | #6 | โ2 | #3 | Near target โญโญ |
| content optimization guide | #12 | #11 | โ1 | #5 | Improving |
| technical seo audit | #18 | #16 | โ2 | #8 | Improving |
### Notable Changes
- **free backlink checker** moved to #6 (only 3 positions from target!)
- **keyword research tools** gained 3 positions (strong movement)
- All other keywords showing stable or positive movement
### Updated Files
1. CLAUDE.md โ Hero Keywords table updated with current ranks
2. memory/keywords/historical-rankings.csv โ New row added:
`2024-12-15,keyword research tools,12,best seo software,24,free backlink checker,6,...`
### Recommendations
1. Push additional content/backlinks to "free backlink checker" pages to hit #3 target
2. Investigate why "keyword research tools" suddenly gained 3 positions (replicate success)
3. Monitor "best seo software" for any negative trends
Hot cache refreshed. Next ranking check recommended: December 22, 2024.
User: "What does 'quick wins' mean in our project?"
Assistant:
Let me look that up in the project memory.
[Step 1: Check CLAUDE.md โ not found]
[Step 2: Check memory/glossary.md โ found!]
From your project glossary:
**Quick Wins**
- **Definition**: Low-difficulty, high-value target keywords
- **Keyword Count**: 25 keywords
- **Context**: This segment includes keywords where you can achieve page 1 rankings within 30-60 days due to low competition, despite having decent search volume
According to your memory files, your current quick wins are stored in:
`memory/keywords/long-tail-keywords.md` (tagged with "quick-win" label)
Would you like me to show you the current list of quick win keywords?
User: "Set up memory for a new e-commerce site selling outdoor gear"
Assistant:
I'll set up the two-layer memory system for your outdoor gear e-commerce site.
## Creating Directory Structure
[Creates: memory/glossary.md, memory/keywords/, memory/competitors/, etc.]
## CLAUDE.md (Hot Cache) - Initial Setup
I'll need some information to populate the hot cache:
1. **Target Keywords**: What are your top 10 hero keywords?
(e.g., "hiking backpacks", "camping tents", "outdoor clothing")
2. **Primary Competitors**: Who are your top 3-5 competitors?
(e.g., rei.com, backcountry.com, moosejaw.com)
3. **Current Metrics** (if available):
- Domain authority?
- Current organic traffic?
- Any existing rankings?
4. **Active Initiatives**:
- Are you launching a new category?
- Running a content campaign?
- Focusing on any specific product line?
5. **Project Terminology**:
- Any internal product names or abbreviations?
- How do you segment your keyword strategy?
Please provide what you have, and I'll create your initial CLAUDE.md and glossary. We can start with basics and enrich as we gather more data.
---
Once you provide this information, I'll generate:
- CLAUDE.md with your initial hot cache
- memory/glossary.md with project terminology
- memory/keywords/ structure with placeholder files
- memory/competitors/ with initial competitor list
- memory/content-calendar/active-calendar.md for Q1 2025
After setup, you can use commands like:
- "Update rankings for hero keywords"
- "Add new competitor [domain]"
- "Promote [keyword] to hot cache"
- "Archive campaigns from Q3 2024"
Load full context for [campaign name]
Retrieves hot cache + all cold storage files related to campaign.
Run memory health check
Audits memory structure: finds orphaned files, missing timestamps, stale hot cache items, broken references.
Promote all keywords ranking in top 10 to hot cache
Demote all completed campaigns from Q3 2024
Create memory snapshot for [date/milestone]
Takes point-in-time copy of entire memory structure for major milestones (site launches, algorithm updates, etc.).
Compare memory with [other project name]
Identifies keyword overlaps, competitor intersections, and strategy similarities across multiple projects.
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.Generated Mar 1, 2026
A digital marketing agency starts a new SEO campaign for a client in the e-commerce sector. They use this skill to initialize memory structure, storing target keywords, competitor domains, and performance metrics in the hot cache and cold storage, ensuring all team members have consistent project context from day one.
An in-house SEO team at a SaaS company tracks an ongoing content optimization campaign. They update memory after monthly ranking checks, promoting frequently referenced keywords to the hot cache and archiving stale data to maintain efficient context retrieval and monitor progress over time.
A freelance SEO consultant revisits a past project for a local business client after six months. They query stored context to recall hero keywords, competitor analysis findings, and campaign status from cold storage, enabling quick resumption without re-researching.
A large enterprise with multiple SEO teams uses this skill to manage project-specific terminology and abbreviations. They add new terms to the glossary as campaigns evolve, ensuring all members understand internal jargon and reducing miscommunication during audits and reports.
An SEO agency conducts a quarterly review for a long-term client in the travel industry. They archive data not referenced in over 30 days from the hot cache to cold storage, optimizing memory performance and keeping the active context focused on current priorities.
Agencies managing multiple client SEO campaigns use this skill to maintain separate memory structures per project, tracking keywords, competitors, and metrics. It enhances efficiency by reducing context-switching and ensuring data persistence across team handoffs, supporting retainer-based or project-based revenue models.
Companies with dedicated SEO teams integrate this skill to streamline internal project management, storing campaign progress and historical data. It improves collaboration by providing a centralized memory system, aiding in reporting and strategy adjustments, typically funded through departmental budgets.
Independent consultants leverage this skill to manage memory for diverse clients across industries, from setup to ongoing tracking. It helps organize project contexts efficiently, enabling quick recalls and professional updates, often charging hourly rates or fixed project fees.
๐ฌ Integration Tip
Connect this skill with SEO tools like rank trackers or analytics platforms to automate data population; for manual setups, prompt users to provide keywords, competitors, and metrics during initialization.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection