Claim this agent
Agent DossierCLAWHUBSafety 84/100

Xpersona Agent

Memory Management

Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with i... Skill: Memory Management Owner: aaron-he-zhu Summary: Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with i... Tags: latest:2.0.0 Version history: v2.0.0 | 2026-02-14T04:24:24.074Z | auto No file changes detected in this version. - Version and documentation remain unchanged. - No new features, bug fixes, or updates

OpenClaw · self-declared
960 downloadsTrust evidence available
clawhub skill install kn73qjxwmbna25qq8q051epqt980sys5:memory-management

Overall rank

#62

Adoption

960 downloads

Trust

Unknown

Freshness

Mar 1, 2026

Freshness

Last checked Mar 1, 2026

Best For

Memory Management is best for general automation workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, CLAWHUB, runtime-metrics, public facts pack

Overview

Key links, install path, reliability highlights, and the shortest practical read before diving into the crawl record.

Verifiededitorial-content

Overview

Executive Summary

Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with i... Skill: Memory Management Owner: aaron-he-zhu Summary: Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with i... Tags: latest:2.0.0 Version history: v2.0.0 | 2026-02-14T04:24:24.074Z | auto No file changes detected in this version. - Version and documentation remain unchanged. - No new features, bug fixes, or updates Capability contract not published. No trust telemetry is available yet. 960 downloads reported by the source. Last updated 4/15/2026.

No verified compatibility signals960 downloads

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Mar 1, 2026

Vendor

Clawhub

Artifacts

0

Benchmarks

0

Last release

2.0.0

Install & run

Setup Snapshot

clawhub skill install kn73qjxwmbna25qq8q051epqt980sys5:memory-management
  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence & Timeline

Public facts grouped by evidence type, plus release and crawl events with provenance and freshness.

Verifiededitorial-content

Public facts

Evidence Ledger

Vendor (1)

Vendor

Clawhub

profilemedium
Observed Apr 15, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium
Observed Apr 15, 2026Source linkProvenance
Release (1)

Latest release

2.0.0

releasemedium
Observed Feb 14, 2026Source linkProvenance
Adoption (1)

Adoption signal

960 downloads

profilemedium
Observed Apr 15, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance

Artifacts & Docs

Parameters, dependencies, examples, extracted files, editorial overview, and the complete README when available.

Self-declaredCLAWHUB

Captured outputs

Artifacts Archive

Extracted files

2

Examples

6

Snippets

0

Languages

Unknown

Executable Examples

text

Set up SEO memory for [project name]

text

Initialize memory structure for a new [industry] website optimization project

text

Update memory after ranking check for [keyword group]

text

Refresh hot cache with latest competitor analysis findings

text

What are our hero keywords?

text

Show me the last ranking update date for [keyword category]
Extracted Files

SKILL.md

---
name: memory-management
description: 'Use when the user asks to "remember project context", "save SEO data", "track campaign progress", "store keyword data", "manage project memory", "remember this for next time", "save my keyword data", or "keep track of this campaign". Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with intelligent promotion/demotion.'
license: Apache-2.0
metadata:
  author: aaron-he-zhu
  version: "2.0.0"
  geo-relevance: "low"
  tags:
    - seo
    - geo
    - project memory
    - context management
    - campaign tracking
    - data persistence
    - keyword tracking
    - project context
  triggers:
    - "remember project context"
    - "save SEO data"
    - "track campaign progress"
    - "store keyword data"
    - "manage project memory"
    - "save progress"
    - "project context"
    - "remember this for next time"
    - "save my keyword data"
    - "keep track of this campaign"
---

# Memory Management


> **[SEO & GEO Skills Library](https://skills.sh/aaron-he-zhu/seo-geo-claude-skills)** · 20 skills for SEO + GEO · Install all: `npx skills add aaron-he-zhu/seo-geo-claude-skills`

<details>
<summary>Browse all 20 skills</summary>

**Research** · [keyword-research](../../research/keyword-research/) · [competitor-analysis](../../research/competitor-analysis/) · [serp-analysis](../../research/serp-analysis/) · [content-gap-analysis](../../research/content-gap-analysis/)

**Build** · [seo-content-writer](../../build/seo-content-writer/) · [geo-content-optimizer](../../build/geo-content-optimizer/) · [meta-tags-optimizer](../../build/meta-tags-optimizer/) · [schema-markup-generator](../../build/schema-markup-generator/)

**Optimize** · [on-page-seo-auditor](../../optimize/on-page-seo-auditor/) · [technical-seo-checker](../../optimize/technical-seo-checker/) · [internal-linking-optimizer](../../optimize/internal-linking-optimizer/) · [content-refresher](../../optimize/content-refresher/)

**Monitor** · [rank-tracker](../../monitor/rank-tracker/) · [backlink-analyzer](../../monitor/backlink-analyzer/) · [performance-reporter](../../monitor/performance-reporter/) · [alert-manager](../../monitor/alert-manager/)

**Cross-cutting** · [content-quality-auditor](../content-quality-auditor/) · [domain-authority-auditor](../domain-authority-auditor/) · [entity-optimizer](../entity-optimizer/) · **memory-management**

</details>

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 initiati

_meta.json

{
  "ownerId": "kn73qjxwmbna25qq8q051epqt980sys5",
  "slug": "memory-management",
  "version": "2.0.0",
  "publishedAt": 1771043064074
}

Editorial read

Docs & README

Docs source

CLAWHUB

Editorial quality

ready

Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with i... Skill: Memory Management Owner: aaron-he-zhu Summary: Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with i... Tags: latest:2.0.0 Version history: v2.0.0 | 2026-02-14T04:24:24.074Z | auto No file changes detected in this version. - Version and documentation remain unchanged. - No new features, bug fixes, or updates

Full README

Skill: Memory Management

Owner: aaron-he-zhu

Summary: Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with i...

Tags: latest:2.0.0

Version history:

v2.0.0 | 2026-02-14T04:24:24.074Z | auto

No file changes detected in this version.

  • Version and documentation remain unchanged.
  • No new features, bug fixes, or updates introduced.
  • Functionality and instructions remain the same as the previous release.

v0.1.3 | 2026-02-14T04:19:05.786Z | auto

Version 0.1.3 → 2.0.0

  • Added YAML frontmatter with license, metadata, tags, author, and detailed natural language triggers for when to use the skill.
  • Expanded description to explicitly state main triggers and usage instructions for remembering project context, saving SEO data, tracking campaigns, and keyword management.
  • Linked this skill as part of a larger SEO & GEO skills library, with navigation to 19 related skills for easy discovery.
  • No functional or code changes to the memory management logic; documentation is now more discoverable and user-friendly for different workflows.

v0.1.2 | 2026-02-11T15:34:26.976Z | auto

memory-management v0.1.2

  • Updated skill metadata fields: removed version, added geo-relevance attribute.
  • No changes to skill logic, usage guidance, or workflow content.
  • Documentation now reflects current metadata requirements for deployment.

v0.1.1 | 2026-02-10T16:03:49.504Z | auto

  • Added explicit skill version ("version: '1.0'") and updated version in SKILL.md metadata.
  • Expanded the directory structure to include domain audits (CITE) in "audits/" and CITE Score in the metrics table.
  • Extended "Key Metrics Snapshot" with fields for CITE Score and Last Content Audit Score.
  • Improved template documentation for directory and file organization.
  • No changes to core functionality, prompts, or usage instructions.

v0.1.0 | 2026-02-08T14:05:17.834Z | auto

  • Initial release of the memory-management skill implementing a two-layer (hot cache + cold storage) memory system for SEO/GEO project context.
  • Tracks and organizes keywords, competitors, performance metrics, and campaign status with automatic promotion and demotion based on usage.
  • Provides a standardized directory and file structure for project memory, including active context (CLAUDE.md), detailed archives, and a glossary.
  • Supports both automated updates (with connector tools) and manual data entry workflows.
  • Includes clear user instructions and example prompts for initializing memory, updating context, querying stored data, and managing project-specific terminology.

Archive index:

Archive v2.0.0: 2 files, 9523 bytes

Files: SKILL.md (27111b), _meta.json (136b)

File v2.0.0:SKILL.md


name: memory-management description: 'Use when the user asks to "remember project context", "save SEO data", "track campaign progress", "store keyword data", "manage project memory", "remember this for next time", "save my keyword data", or "keep track of this campaign". Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with intelligent promotion/demotion.' license: Apache-2.0 metadata: author: aaron-he-zhu version: "2.0.0" geo-relevance: "low" tags: - seo - geo - project memory - context management - campaign tracking - data persistence - keyword tracking - project context triggers: - "remember project context" - "save SEO data" - "track campaign progress" - "store keyword data" - "manage project memory" - "save progress" - "project context" - "remember this for next time" - "save my keyword data" - "keep track of this campaign"

Memory Management

SEO & GEO Skills Library · 20 skills for SEO + GEO · Install all: npx skills add aaron-he-zhu/seo-geo-claude-skills

<details> <summary>Browse all 20 skills</summary>

Research · keyword-research · competitor-analysis · serp-analysis · content-gap-analysis

Build · seo-content-writer · geo-content-optimizer · meta-tags-optimizer · schema-markup-generator

Optimize · on-page-seo-auditor · technical-seo-checker · internal-linking-optimizer · content-refresher

Monitor · rank-tracker · backlink-analyzer · performance-reporter · alert-manager

Cross-cutting · content-quality-auditor · domain-authority-auditor · entity-optimizer · memory-management

</details>

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

  1. Hot Cache Management: Maintains CLAUDE.md (~100 lines) with active context that's always loaded
  2. Cold Storage Organization: Structures detailed archives in memory/ subdirectories
  3. Context Lookup: Implements efficient lookup flow from hot cache to cold storage
  4. Promotion/Demotion: Moves items between layers based on reference frequency
  5. Glossary Maintenance: Manages project-specific terminology and shorthand
  6. Update Triggers: Refreshes memory after audits, reports, or ranking checks
  7. 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:

  1. Current target keywords with priority levels
  2. Primary competitors (3-5 domains)
  3. Key performance metrics and last update date
  4. Active campaigns and their status
  5. 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:

## Directory Structure

project-root/
├── CLAUDE.md                           # Hot cache (~100 lines)
└── memory/
    ├── glossary.md                     # Project terminology
    ├── keywords/
    │   ├── hero-keywords.md           # Top priority keywords
    │   ├── secondary-keywords.md      # Medium priority
    │   ├── long-tail-keywords.md      # Long-tail opportunities
    │   └── historical-rankings.csv    # Dated ranking data
    ├── competitors/
    │   ├── primary-competitors.md     # Top 3-5 competitors
    │   ├── [competitor-domain].md     # Individual reports
    │   └── analysis-history/          # Dated analyses
    ├── audits/
    │   ├── technical/                 # Technical SEO audits
    │   ├── content/                   # Content audits
    │   ├── domain/                    # Domain authority (CITE) audits
    │   └── backlink/                  # Backlink audits
    ├── content-calendar/
    │   ├── active-calendar.md         # Current quarter
    │   ├── published-content.md       # Performance tracking
    │   └── archive/                   # Past calendars
    └── reports/
        ├── monthly/                   # Monthly reports
        ├── quarterly/                 # Quarterly reports
        └── campaign/                  # Campaign-specific reports

2. Hot Cache (CLAUDE.md) Structure

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]) | — [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_

3. Glossary Structure (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._

4. Context Lookup Flow

When a user references something unclear, follow this lookup sequence:

Step 1: Check CLAUDE.md (Hot Cache)

  • Is it in active keywords?
  • Is it in primary competitors?
  • Is it in current priorities or campaigns?

Step 2: Check memory/glossary.md

  • Is it defined as project terminology?
  • Is it a custom segment or shorthand?

Step 3: Check Cold Storage

  • Search memory/keywords/ for historical data
  • Search memory/competitors/ for past analyses
  • Search memory/reports/ for archived mentions

Step 4: Ask User

  • If not found in any layer, ask for clarification
  • Log the new term in glossary if it's project-specific

Example lookup:

User: "Update rankings for our hero KWs"

Step 1: Check CLAUDE.md → 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

5. Promotion Logic

Promote to Hot Cache when:

  1. Keyword promotion triggers:

    • Keyword referenced in 3+ conversations within 7 days
    • Keyword showing significant movement (5+ position change)
    • Keyword targeted in new active campaign
    • Keyword suddenly driving traffic spike
  2. Competitor promotion triggers:

    • Competitor mentioned in 3+ recent analyses
    • Competitor showing aggressive SEO activity
    • Competitor launching competing content
  3. Metric promotion triggers:

    • Metric requested frequently for reporting
    • Metric showing anomalous behavior
    • Metric tied to active priority/campaign

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

6. Demotion Logic

Demote to Cold Storage when:

  1. Keyword demotion triggers:

    • Not referenced in 30+ days
    • Target rank achieved and stable for 60+ days
    • Keyword no longer in active strategy
    • Keyword replaced by higher-priority target
  2. Competitor demotion triggers:

    • No significant activity in 60+ days
    • Fell out of top 5 competitors by relevance
    • No longer targeting same keywords
  3. Campaign demotion triggers:

    • Campaign completed 30+ days ago
    • Campaign cancelled or postponed indefinitely

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

7. Update Triggers

After specific events, update memory systematically:

After Ranking Check:

1. Update CLAUDE.md → 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 ±5 positions, create alert note

After Competitor Analysis:

1. Update CLAUDE.md → 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 → 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 → demote stale items
4. Update campaign statuses
5. Archive completed campaigns

8. Archive Management

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 → archive completed ones

9. Cross-Skill Memory Integration

This skill coordinates with other SEO skills:

When keyword-research runs:

  • Add discovered keywords to memory/keywords/
  • Promote top opportunities to CLAUDE.md if high-value
  • Update glossary if new terminology emerges

When rank-tracker runs:

  • Update historical-rankings.csv
  • Refresh CLAUDE.md Hero Keywords table
  • Flag significant movements for hot cache notes

When competitor-analysis runs:

  • Update competitor files in memory/competitors/
  • Refresh CLAUDE.md Primary Competitors section
  • Add new competitors if they outrank current top 5

When content-gap-analysis runs:

  • Store full findings in memory/audits/content/
  • Promote gap opportunities to CLAUDE.md priorities
  • Update content calendar with recommended topics

When seo-content-writer produces content:

  • Log to memory/content-calendar/published-content.md
  • Track target keyword and publish date
  • Set reminder to check performance in 30 days

When content-quality-auditor runs:

  • Save full report to memory/audits/content/YYYY-MM-DD-core-eeat-[page-slug].md
  • Update CLAUDE.md Key Metrics with latest score
  • If score < 60 (Poor/Low), flag in Active Campaigns section
  • Track dimension scores for trend analysis

When domain-authority-auditor runs:

  • Save full report to memory/audits/domain/YYYY-MM-DD-cite-audit.md
  • Update CITE Score in CLAUDE.md Key Metrics Snapshot
  • Note veto item status and dimension scores
  • Compare against previous CITE audit if available

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

Example

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 | ↑3 | #5 | Improving ⭐ |
| best seo software | #23 | #24 | ↓1 | #10 | Stable |
| free backlink checker | #8 | #6 | ↑2 | #3 | Near target ⭐⭐ |
| content optimization guide | #12 | #11 | ↑1 | #5 | Improving |
| technical seo audit | #18 | #16 | ↑2 | #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 → Hero Keywords table updated with current ranks
2. memory/keywords/historical-rankings.csv → 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 → not found]
[Step 2: Check memory/glossary.md → 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"

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

  1. Keep hot cache lean - CLAUDE.md should never exceed 150 lines. If it grows larger, aggressively demote.

  2. Date everything - Every file in cold storage should have YYYY-MM-DD in filename or prominent metadata.

  3. Update after every significant action - Don't let memory drift from reality. Update immediately after ranking checks, audits, or reports.

  4. Use glossary liberally - If you find yourself explaining a term twice, add it to glossary.

  5. Review hot cache weekly - Quick scan to ensure everything there is still relevant and active.

  6. Automate where possible - If ~~SEO tool or ~~search console connected, set up automatic updates to historical-rankings.csv.

  7. Archive aggressively - Better to have data in cold storage and not need it than clutter hot cache.

  8. Link between layers - CLAUDE.md should always reference where detailed data lives ("Full data: memory/keywords/").

  9. Timestamp changes - When updating CLAUDE.md, always update "Last Updated" date.

  10. Use memory for continuity - If you switch between different analysis sessions, memory ensures nothing is forgotten.

Reference Materials

Related Skills

File v2.0.0:_meta.json

{ "ownerId": "kn73qjxwmbna25qq8q051epqt980sys5", "slug": "memory-management", "version": "2.0.0", "publishedAt": 1771043064074 }

Archive v0.1.3: 2 files, 9523 bytes

Files: SKILL.md (27111b), _meta.json (136b)

File v0.1.3:SKILL.md


name: memory-management description: 'Use when the user asks to "remember project context", "save SEO data", "track campaign progress", "store keyword data", "manage project memory", "remember this for next time", "save my keyword data", or "keep track of this campaign". Manages a two-layer memory system (hot cache + cold storage) for SEO/GEO project context, tracking keywords, competitors, metrics, and campaign status with intelligent promotion/demotion.' license: Apache-2.0 metadata: author: aaron-he-zhu version: "2.0.0" geo-relevance: "low" tags: - seo - geo - project memory - context management - campaign tracking - data persistence - keyword tracking - project context triggers: - "remember project context" - "save SEO data" - "track campaign progress" - "store keyword data" - "manage project memory" - "save progress" - "project context" - "remember this for next time" - "save my keyword data" - "keep track of this campaign"

Memory Management

SEO & GEO Skills Library · 20 skills for SEO + GEO · Install all: npx skills add aaron-he-zhu/seo-geo-claude-skills

<details> <summary>Browse all 20 skills</summary>

Research · keyword-research · competitor-analysis · serp-analysis · content-gap-analysis

Build · seo-content-writer · geo-content-optimizer · meta-tags-optimizer · schema-markup-generator

Optimize · on-page-seo-auditor · technical-seo-checker · internal-linking-optimizer · content-refresher

Monitor · rank-tracker · backlink-analyzer · performance-reporter · alert-manager

Cross-cutting · content-quality-auditor · domain-authority-auditor · entity-optimizer · memory-management

</details>

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

  1. Hot Cache Management: Maintains CLAUDE.md (~100 lines) with active context that's always loaded
  2. Cold Storage Organization: Structures detailed archives in memory/ subdirectories
  3. Context Lookup: Implements efficient lookup flow from hot cache to cold storage
  4. Promotion/Demotion: Moves items between layers based on reference frequency
  5. Glossary Maintenance: Manages project-specific terminology and shorthand
  6. Update Triggers: Refreshes memory after audits, reports, or ranking checks
  7. 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:

  1. Current target keywords with priority levels
  2. Primary competitors (3-5 domains)
  3. Key performance metrics and last update date
  4. Active campaigns and their status
  5. 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:

## Directory Structure

project-root/
├── CLAUDE.md                           # Hot cache (~100 lines)
└── memory/
    ├── glossary.md                     # Project terminology
    ├── keywords/
    │   ├── hero-keywords.md           # Top priority keywords
    │   ├── secondary-keywords.md      # Medium priority
    │   ├── long-tail-keywords.md      # Long-tail opportunities
    │   └── historical-rankings.csv    # Dated ranking data
    ├── competitors/
    │   ├── primary-competitors.md     # Top 3-5 competitors
    │   ├── [competitor-domain].md     # Individual reports
    │   └── analysis-history/          # Dated analyses
    ├── audits/
    │   ├── technical/                 # Technical SEO audits
    │   ├── content/                   # Content audits
    │   ├── domain/                    # Domain authority (CITE) audits
    │   └── backlink/                  # Backlink audits
    ├── content-calendar/
    │   ├── active-calendar.md         # Current quarter
    │   ├── published-content.md       # Performance tracking
    │   └── archive/                   # Past calendars
    └── reports/
        ├── monthly/                   # Monthly reports
        ├── quarterly/                 # Quarterly reports
        └── campaign/                  # Campaign-specific reports

2. Hot Cache (CLAUDE.md) Structure

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]) | — [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_

3. Glossary Structure (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._

4. Context Lookup Flow

When a user references something unclear, follow this lookup sequence:

Step 1: Check CLAUDE.md (Hot Cache)

  • Is it in active keywords?
  • Is it in primary competitors?
  • Is it in current priorities or campaigns?

Step 2: Check memory/glossary.md

  • Is it defined as project terminology?
  • Is it a custom segment or shorthand?

Step 3: Check Cold Storage

  • Search memory/keywords/ for historical data
  • Search memory/competitors/ for past analyses
  • Search memory/reports/ for archived mentions

Step 4: Ask User

  • If not found in any layer, ask for clarification
  • Log the new term in glossary if it's project-specific

Example lookup:

User: "Update rankings for our hero KWs"

Step 1: Check CLAUDE.md → 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

5. Promotion Logic

Promote to Hot Cache when:

  1. Keyword promotion triggers:

    • Keyword referenced in 3+ conversations within 7 days
    • Keyword showing significant movement (5+ position change)
    • Keyword targeted in new active campaign
    • Keyword suddenly driving traffic spike
  2. Competitor promotion triggers:

    • Competitor mentioned in 3+ recent analyses
    • Competitor showing aggressive SEO activity
    • Competitor launching competing content
  3. Metric promotion triggers:

    • Metric requested frequently for reporting
    • Metric showing anomalous behavior
    • Metric tied to active priority/campaign

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

6. Demotion Logic

Demote to Cold Storage when:

  1. Keyword demotion triggers:

    • Not referenced in 30+ days
    • Target rank achieved and stable for 60+ days
    • Keyword no longer in active strategy
    • Keyword replaced by higher-priority target
  2. Competitor demotion triggers:

    • No significant activity in 60+ days
    • Fell out of top 5 competitors by relevance
    • No longer targeting same keywords
  3. Campaign demotion triggers:

    • Campaign completed 30+ days ago
    • Campaign cancelled or postponed indefinitely

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

7. Update Triggers

After specific events, update memory systematically:

After Ranking Check:

1. Update CLAUDE.md → 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 ±5 positions, create alert note

After Competitor Analysis:

1. Update CLAUDE.md → 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 → 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 → demote stale items
4. Update campaign statuses
5. Archive completed campaigns

8. Archive Management

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 → archive completed ones

9. Cross-Skill Memory Integration

This skill coordinates with other SEO skills:

When keyword-research runs:

  • Add discovered keywords to memory/keywords/
  • Promote top opportunities to CLAUDE.md if high-value
  • Update glossary if new terminology emerges

When rank-tracker runs:

  • Update historical-rankings.csv
  • Refresh CLAUDE.md Hero Keywords table
  • Flag significant movements for hot cache notes

When competitor-analysis runs:

  • Update competitor files in memory/competitors/
  • Refresh CLAUDE.md Primary Competitors section
  • Add new competitors if they outrank current top 5

When content-gap-analysis runs:

  • Store full findings in memory/audits/content/
  • Promote gap opportunities to CLAUDE.md priorities
  • Update content calendar with recommended topics

When seo-content-writer produces content:

  • Log to memory/content-calendar/published-content.md
  • Track target keyword and publish date
  • Set reminder to check performance in 30 days

When content-quality-auditor runs:

  • Save full report to memory/audits/content/YYYY-MM-DD-core-eeat-[page-slug].md
  • Update CLAUDE.md Key Metrics with latest score
  • If score < 60 (Poor/Low), flag in Active Campaigns section
  • Track dimension scores for trend analysis

When domain-authority-auditor runs:

  • Save full report to memory/audits/domain/YYYY-MM-DD-cite-audit.md
  • Update CITE Score in CLAUDE.md Key Metrics Snapshot
  • Note veto item status and dimension scores
  • Compare against previous CITE audit if available

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

Example

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 | ↑3 | #5 | Improving ⭐ |
| best seo software | #23 | #24 | ↓1 | #10 | Stable |
| free backlink checker | #8 | #6 | ↑2 | #3 | Near target ⭐⭐ |
| content optimization guide | #12 | #11 | ↑1 | #5 | Improving |
| technical seo audit | #18 | #16 | ↑2 | #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 → Hero Keywords table updated with current ranks
2. memory/keywords/historical-rankings.csv → 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 → not found]
[Step 2: Check memory/glossary.md → 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"

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

  1. Keep hot cache lean - CLAUDE.md should never exceed 150 lines. If it grows larger, aggressively demote.

  2. Date everything - Every file in cold storage should have YYYY-MM-DD in filename or prominent metadata.

  3. Update after every significant action - Don't let memory drift from reality. Update immediately after ranking checks, audits, or reports.

  4. Use glossary liberally - If you find yourself explaining a term twice, add it to glossary.

  5. Review hot cache weekly - Quick scan to ensure everything there is still relevant and active.

  6. Automate where possible - If ~~SEO tool or ~~search console connected, set up automatic updates to historical-rankings.csv.

  7. Archive aggressively - Better to have data in cold storage and not need it than clutter hot cache.

  8. Link between layers - CLAUDE.md should always reference where detailed data lives ("Full data: memory/keywords/").

  9. Timestamp changes - When updating CLAUDE.md, always update "Last Updated" date.

  10. Use memory for continuity - If you switch between different analysis sessions, memory ensures nothing is forgotten.

Reference Materials

Related Skills

File v0.1.3:_meta.json

{ "ownerId": "kn73qjxwmbna25qq8q051epqt980sys5", "slug": "memory-management", "version": "0.1.3", "publishedAt": 1771042745786 }

API & Reliability

Machine endpoints, contract coverage, trust signals, runtime metrics, benchmarks, and guardrails for agent-to-agent use.

MissingCLAWHUB

Machine interfaces

Contract & API

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/snapshot"
curl -s "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/contract"
curl -s "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/trust"

Operational fit

Reliability & Benchmarks

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
No benchmark suites or observed failure patterns are available.

Machine Appendix

Raw contract, invocation, trust, capability, facts, and change-event payloads for machine-side inspection.

MissingCLAWHUB

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "CLAWHUB",
      "generatedAt": "2026-04-17T06:13:29.392Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile"
}

Facts JSON

[
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Clawhub",
    "href": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "sourceUrl": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T00:45:39.800Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-04-15T00:45:39.800Z",
    "isPublic": true
  },
  {
    "factKey": "traction",
    "category": "adoption",
    "label": "Adoption signal",
    "value": "960 downloads",
    "href": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "sourceUrl": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-04-15T00:45:39.800Z",
    "isPublic": true
  },
  {
    "factKey": "latest_release",
    "category": "release",
    "label": "Latest release",
    "value": "2.0.0",
    "href": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "sourceUrl": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "sourceType": "release",
    "confidence": "medium",
    "observedAt": "2026-02-14T04:24:24.074Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-memory-management/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "release",
    "title": "Release 2.0.0",
    "description": "No file changes detected in this version. - Version and documentation remain unchanged. - No new features, bug fixes, or updates introduced. - Functionality and instructions remain the same as the previous release.",
    "href": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "sourceUrl": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "sourceType": "release",
    "confidence": "medium",
    "observedAt": "2026-02-14T04:24:24.074Z",
    "isPublic": true
  }
]

Sponsored

Ads related to Memory Management and adjacent AI workflows.