{
  "schemaVersion": "1.0",
  "item": {
    "slug": "memory-management",
    "name": "Memory Management",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "canonicalUrl": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/memory-management",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-management",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/examples.md",
      "references/glossary-template.md",
      "references/hot-cache-template.md",
      "references/promotion-demotion-rules.md",
      "references/update-triggers-integration.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/memory-management"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/memory-management",
    "agentPageUrl": "https://openagent3.xyz/skills/memory-management/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-management/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-management/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Memory Management",
        "body": "SEO & GEO Skills Library · 20 skills for SEO + GEO · Install all: npx skills add aaron-he-zhu/seo-geo-claude-skills\n\nResearch · keyword-research · competitor-analysis · serp-analysis · content-gap-analysis\n\nBuild · seo-content-writer · geo-content-optimizer · meta-tags-optimizer · schema-markup-generator\n\nOptimize · on-page-seo-auditor · technical-seo-checker · internal-linking-optimizer · content-refresher\n\nMonitor · rank-tracker · backlink-analyzer · performance-reporter · alert-manager\n\nCross-cutting · content-quality-auditor · domain-authority-auditor · entity-optimizer · memory-management\n\nThis 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."
      },
      {
        "title": "When to Use This Skill",
        "body": "Setting up memory structure for a new SEO project\nAfter completing audits, ranking checks, or performance reports\nWhen starting a new campaign or optimization initiative\nWhen project context needs updating (new keywords, competitors, priorities)\nWhen you need to look up historical data or project-specific terminology\nAfter 30+ days of work to clean up and archive stale data\nWhen context retrieval feels slow or cluttered"
      },
      {
        "title": "What This Skill Does",
        "body": "Hot Cache Management: Maintains CLAUDE.md (~100 lines) with active context that's always loaded\nCold Storage Organization: Structures detailed archives in memory/ subdirectories\nContext Lookup: Implements efficient lookup flow from hot cache to cold storage\nPromotion/Demotion: Moves items between layers based on reference frequency\nGlossary Maintenance: Manages project-specific terminology and shorthand\nUpdate Triggers: Refreshes memory after audits, reports, or ranking checks\nArchive Management: Time-stamps and archives old data systematically"
      },
      {
        "title": "Initialize Memory Structure",
        "body": "Set up SEO memory for [project name]\n\nInitialize memory structure for a new [industry] website optimization project"
      },
      {
        "title": "Update After Analysis",
        "body": "Update memory after ranking check for [keyword group]\n\nRefresh hot cache with latest competitor analysis findings"
      },
      {
        "title": "Query Stored Context",
        "body": "What are our hero keywords?\n\nShow me the last ranking update date for [keyword category]\n\nLook up our primary competitors and their domain authority"
      },
      {
        "title": "Promotion and Demotion",
        "body": "Promote [keyword] to hot cache\n\nArchive stale data that hasn't been referenced in 30+ days"
      },
      {
        "title": "Glossary Management",
        "body": "Add [term] to project glossary: [definition]\n\nWhat does [internal jargon] mean in this project?"
      },
      {
        "title": "Data Sources",
        "body": "See CONNECTORS.md for tool category placeholders.\n\nWith ~~SEO tool + ~~analytics + ~~search console connected:\nAutomatically 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.\n\nWith manual data only:\nAsk the user to provide:\n\nCurrent target keywords with priority levels\nPrimary competitors (3-5 domains)\nKey performance metrics and last update date\nActive campaigns and their status\nAny project-specific terminology or abbreviations\n\nProceed with memory structure creation using provided data. Note in CLAUDE.md which data requires manual updates vs. automated refresh."
      },
      {
        "title": "Instructions",
        "body": "When a user requests SEO memory management:"
      },
      {
        "title": "1. Initialize Memory Structure",
        "body": "For new projects, create the following structure:\n\n## Directory Structure\n\nproject-root/\n├── CLAUDE.md                           # Hot cache (~100 lines)\n└── memory/\n    ├── glossary.md                     # Project terminology\n    ├── keywords/\n    │   ├── hero-keywords.md           # Top priority keywords\n    │   ├── secondary-keywords.md      # Medium priority\n    │   ├── long-tail-keywords.md      # Long-tail opportunities\n    │   └── historical-rankings.csv    # Dated ranking data\n    ├── competitors/\n    │   ├── primary-competitors.md     # Top 3-5 competitors\n    │   ├── [competitor-domain].md     # Individual reports\n    │   └── analysis-history/          # Dated analyses\n    ├── audits/\n    │   ├── technical/                 # Technical SEO audits\n    │   ├── content/                   # Content audits\n    │   ├── domain/                    # Domain authority (CITE) audits\n    │   └── backlink/                  # Backlink audits\n    ├── content-calendar/\n    │   ├── active-calendar.md         # Current quarter\n    │   ├── published-content.md       # Performance tracking\n    │   └── archive/                   # Past calendars\n    └── reports/\n        ├── monthly/                   # Monthly reports\n        ├── quarterly/                 # Quarterly reports\n        └── campaign/                  # Campaign-specific reports\n\nTemplates: See references/hot-cache-template.md for the complete CLAUDE.md hot cache template and references/glossary-template.md for the project glossary template."
      },
      {
        "title": "4. Context Lookup Flow",
        "body": "When a user references something unclear, follow this lookup sequence:\n\nStep 1: Check CLAUDE.md (Hot Cache)\n\nIs it in active keywords?\nIs it in primary competitors?\nIs it in current priorities or campaigns?\n\nStep 2: Check memory/glossary.md\n\nIs it defined as project terminology?\nIs it a custom segment or shorthand?\n\nStep 3: Check Cold Storage\n\nSearch memory/keywords/ for historical data\nSearch memory/competitors/ for past analyses\nSearch memory/reports/ for archived mentions\n\nStep 4: Ask User\n\nIf not found in any layer, ask for clarification\nLog the new term in glossary if it's project-specific\n\nExample lookup:\n\nUser: \"Update rankings for our hero KWs\"\n\nStep 1: Check CLAUDE.md → Found \"Hero Keywords (Priority 1)\" section\nStep 2: Extract keyword list from hot cache\nStep 3: Execute ranking check\nStep 4: Update both CLAUDE.md and memory/keywords/historical-rankings.csv"
      },
      {
        "title": "5. Promotion & Demotion Logic",
        "body": "Reference: See references/promotion-demotion-rules.md for detailed promotion/demotion triggers (keywords, competitors, metrics, campaigns) and the action procedures for each."
      },
      {
        "title": "6. Update Triggers, Archive Management & Cross-Skill Integration",
        "body": "Reference: See references/update-triggers-integration.md 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)."
      },
      {
        "title": "Structure Validation",
        "body": "CLAUDE.md exists and is under 150 lines (aim for ~100)\n memory/ directory structure matches template\n glossary.md exists and is populated with project basics\n All historical data files include timestamps in filename or metadata"
      },
      {
        "title": "Content Validation",
        "body": "CLAUDE.md \"Last Updated\" date is current\n Every keyword in hot cache has current rank, target rank, and status\n Every competitor has domain authority and position assessment\n Every active campaign has status percentage and expected completion date\n Key Metrics Snapshot shows \"Previous\" values for comparison"
      },
      {
        "title": "Lookup Validation",
        "body": "Test lookup flow: reference a term → verify it finds it in correct layer\n Test promotion: manually promote item → verify it appears in CLAUDE.md\n Test demotion: manually archive item → verify removed from CLAUDE.md\n Glossary contains all custom segments and shorthand used in CLAUDE.md"
      },
      {
        "title": "Update Validation",
        "body": "After ranking check, historical-rankings.csv has new row with today's date\n After competitor analysis, analysis-history/ has dated file\n After audit, top action items appear in CLAUDE.md priorities\n After monthly report, metrics snapshot reflects new data"
      },
      {
        "title": "Examples",
        "body": "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."
      },
      {
        "title": "Smart Context Loading",
        "body": "Load full context for [campaign name]\n\nRetrieves hot cache + all cold storage files related to campaign."
      },
      {
        "title": "Memory Health Check",
        "body": "Run memory health check\n\nAudits memory structure: finds orphaned files, missing timestamps, stale hot cache items, broken references."
      },
      {
        "title": "Bulk Promotion/Demotion",
        "body": "Promote all keywords ranking in top 10 to hot cache\n\nDemote all completed campaigns from Q3 2024"
      },
      {
        "title": "Memory Snapshot",
        "body": "Create memory snapshot for [date/milestone]\n\nTakes point-in-time copy of entire memory structure for major milestones (site launches, algorithm updates, etc.)."
      },
      {
        "title": "Cross-Project Memory",
        "body": "Compare memory with [other project name]\n\nIdentifies keyword overlaps, competitor intersections, and strategy similarities across multiple projects."
      },
      {
        "title": "Practical Limitations",
        "body": "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.\nCold 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.\nCLAUDE.md size: The hot cache should stay concise (<200 lines). If it grows too large, archive older metrics to cold storage.\nData freshness: Memory reflects the last time each skill was run. Stale data (>90 days) should be flagged for refresh."
      },
      {
        "title": "Tips for Success",
        "body": "Keep hot cache lean - CLAUDE.md should never exceed 150 lines. If it grows larger, aggressively demote.\nDate everything - Every file in cold storage should have YYYY-MM-DD in filename or prominent metadata.\nUpdate after every significant action - Don't let memory drift from reality. Update immediately after ranking checks, audits, or reports.\nUse glossary liberally - If you find yourself explaining a term twice, add it to glossary.\nReview hot cache weekly - Quick scan to ensure everything there is still relevant and active.\nAutomate where possible - If ~~SEO tool or ~~search console connected, set up automatic updates to historical-rankings.csv.\nArchive aggressively - Better to have data in cold storage and not need it than clutter hot cache.\nLink between layers - CLAUDE.md should always reference where detailed data lives (\"Full data: memory/keywords/\").\nTimestamp changes - When updating CLAUDE.md, always update \"Last Updated\" date.\nUse memory for continuity - If you switch between different analysis sessions, memory ensures nothing is forgotten."
      },
      {
        "title": "Reference Materials",
        "body": "CORE-EEAT Content Benchmark — Content quality scoring stored in memory\nCITE Domain Rating — Domain authority scoring stored in memory"
      },
      {
        "title": "Related Skills",
        "body": "rank-tracker — Provides ranking data to update memory\ncompetitor-analysis — Generates competitor reports for storage\nkeyword-research — Discovers keywords to add to memory\nperformance-reporter — Creates reports that trigger memory updates\ncontent-gap-analysis — Identifies optimization priorities for hot cache\nseo-content-writer — Logs published content to memory calendar\ncontent-quality-auditor — Content audit results stored in memory for tracking\ndomain-authority-auditor — CITE domain audit results stored in memory for tracking\nentity-optimizer — Store entity audit results for tracking over time"
      }
    ],
    "body": "Memory Management\n\nSEO & GEO Skills Library · 20 skills for SEO + GEO · Install all: npx skills add aaron-he-zhu/seo-geo-claude-skills\n\n<details> <summary>Browse all 20 skills</summary>\n\nResearch · keyword-research · competitor-analysis · serp-analysis · content-gap-analysis\n\nBuild · seo-content-writer · geo-content-optimizer · meta-tags-optimizer · schema-markup-generator\n\nOptimize · on-page-seo-auditor · technical-seo-checker · internal-linking-optimizer · content-refresher\n\nMonitor · rank-tracker · backlink-analyzer · performance-reporter · alert-manager\n\nCross-cutting · content-quality-auditor · domain-authority-auditor · entity-optimizer · memory-management\n\n</details>\n\nThis 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.\n\nWhen to Use This Skill\nSetting up memory structure for a new SEO project\nAfter completing audits, ranking checks, or performance reports\nWhen starting a new campaign or optimization initiative\nWhen project context needs updating (new keywords, competitors, priorities)\nWhen you need to look up historical data or project-specific terminology\nAfter 30+ days of work to clean up and archive stale data\nWhen context retrieval feels slow or cluttered\nWhat This Skill Does\nHot Cache Management: Maintains CLAUDE.md (~100 lines) with active context that's always loaded\nCold Storage Organization: Structures detailed archives in memory/ subdirectories\nContext Lookup: Implements efficient lookup flow from hot cache to cold storage\nPromotion/Demotion: Moves items between layers based on reference frequency\nGlossary Maintenance: Manages project-specific terminology and shorthand\nUpdate Triggers: Refreshes memory after audits, reports, or ranking checks\nArchive Management: Time-stamps and archives old data systematically\nHow to Use\nInitialize Memory Structure\nSet up SEO memory for [project name]\n\nInitialize memory structure for a new [industry] website optimization project\n\nUpdate After Analysis\nUpdate memory after ranking check for [keyword group]\n\nRefresh hot cache with latest competitor analysis findings\n\nQuery Stored Context\nWhat are our hero keywords?\n\nShow me the last ranking update date for [keyword category]\n\nLook up our primary competitors and their domain authority\n\nPromotion and Demotion\nPromote [keyword] to hot cache\n\nArchive stale data that hasn't been referenced in 30+ days\n\nGlossary Management\nAdd [term] to project glossary: [definition]\n\nWhat does [internal jargon] mean in this project?\n\nData Sources\n\nSee CONNECTORS.md for tool category placeholders.\n\nWith ~~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.\n\nWith manual data only: Ask the user to provide:\n\nCurrent target keywords with priority levels\nPrimary competitors (3-5 domains)\nKey performance metrics and last update date\nActive campaigns and their status\nAny project-specific terminology or abbreviations\n\nProceed with memory structure creation using provided data. Note in CLAUDE.md which data requires manual updates vs. automated refresh.\n\nInstructions\n\nWhen a user requests SEO memory management:\n\n1. Initialize Memory Structure\n\nFor new projects, create the following structure:\n\n## Directory Structure\n\nproject-root/\n├── CLAUDE.md                           # Hot cache (~100 lines)\n└── memory/\n    ├── glossary.md                     # Project terminology\n    ├── keywords/\n    │   ├── hero-keywords.md           # Top priority keywords\n    │   ├── secondary-keywords.md      # Medium priority\n    │   ├── long-tail-keywords.md      # Long-tail opportunities\n    │   └── historical-rankings.csv    # Dated ranking data\n    ├── competitors/\n    │   ├── primary-competitors.md     # Top 3-5 competitors\n    │   ├── [competitor-domain].md     # Individual reports\n    │   └── analysis-history/          # Dated analyses\n    ├── audits/\n    │   ├── technical/                 # Technical SEO audits\n    │   ├── content/                   # Content audits\n    │   ├── domain/                    # Domain authority (CITE) audits\n    │   └── backlink/                  # Backlink audits\n    ├── content-calendar/\n    │   ├── active-calendar.md         # Current quarter\n    │   ├── published-content.md       # Performance tracking\n    │   └── archive/                   # Past calendars\n    └── reports/\n        ├── monthly/                   # Monthly reports\n        ├── quarterly/                 # Quarterly reports\n        └── campaign/                  # Campaign-specific reports\n\n\nTemplates: See references/hot-cache-template.md for the complete CLAUDE.md hot cache template and references/glossary-template.md for the project glossary template.\n\n4. Context Lookup Flow\n\nWhen a user references something unclear, follow this lookup sequence:\n\nStep 1: Check CLAUDE.md (Hot Cache)\n\nIs it in active keywords?\nIs it in primary competitors?\nIs it in current priorities or campaigns?\n\nStep 2: Check memory/glossary.md\n\nIs it defined as project terminology?\nIs it a custom segment or shorthand?\n\nStep 3: Check Cold Storage\n\nSearch memory/keywords/ for historical data\nSearch memory/competitors/ for past analyses\nSearch memory/reports/ for archived mentions\n\nStep 4: Ask User\n\nIf not found in any layer, ask for clarification\nLog the new term in glossary if it's project-specific\n\nExample lookup:\n\nUser: \"Update rankings for our hero KWs\"\n\nStep 1: Check CLAUDE.md → Found \"Hero Keywords (Priority 1)\" section\nStep 2: Extract keyword list from hot cache\nStep 3: Execute ranking check\nStep 4: Update both CLAUDE.md and memory/keywords/historical-rankings.csv\n\n5. Promotion & Demotion Logic\n\nReference: See references/promotion-demotion-rules.md for detailed promotion/demotion triggers (keywords, competitors, metrics, campaigns) and the action procedures for each.\n\n6. Update Triggers, Archive Management & Cross-Skill Integration\n\nReference: See references/update-triggers-integration.md 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).\n\nValidation Checkpoints\nStructure Validation\n CLAUDE.md exists and is under 150 lines (aim for ~100)\n memory/ directory structure matches template\n glossary.md exists and is populated with project basics\n All historical data files include timestamps in filename or metadata\nContent Validation\n CLAUDE.md \"Last Updated\" date is current\n Every keyword in hot cache has current rank, target rank, and status\n Every competitor has domain authority and position assessment\n Every active campaign has status percentage and expected completion date\n Key Metrics Snapshot shows \"Previous\" values for comparison\nLookup Validation\n Test lookup flow: reference a term → verify it finds it in correct layer\n Test promotion: manually promote item → verify it appears in CLAUDE.md\n Test demotion: manually archive item → verify removed from CLAUDE.md\n Glossary contains all custom segments and shorthand used in CLAUDE.md\nUpdate Validation\n After ranking check, historical-rankings.csv has new row with today's date\n After competitor analysis, analysis-history/ has dated file\n After audit, top action items appear in CLAUDE.md priorities\n After monthly report, metrics snapshot reflects new data\nExamples\n\nReference: 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.\n\nAdvanced Features\nSmart Context Loading\nLoad full context for [campaign name]\n\n\nRetrieves hot cache + all cold storage files related to campaign.\n\nMemory Health Check\nRun memory health check\n\n\nAudits memory structure: finds orphaned files, missing timestamps, stale hot cache items, broken references.\n\nBulk Promotion/Demotion\nPromote all keywords ranking in top 10 to hot cache\n\nDemote all completed campaigns from Q3 2024\n\nMemory Snapshot\nCreate memory snapshot for [date/milestone]\n\n\nTakes point-in-time copy of entire memory structure for major milestones (site launches, algorithm updates, etc.).\n\nCross-Project Memory\nCompare memory with [other project name]\n\n\nIdentifies keyword overlaps, competitor intersections, and strategy similarities across multiple projects.\n\nPractical Limitations\nConcurrent 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.\nCold 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.\nCLAUDE.md size: The hot cache should stay concise (<200 lines). If it grows too large, archive older metrics to cold storage.\nData freshness: Memory reflects the last time each skill was run. Stale data (>90 days) should be flagged for refresh.\nTips for Success\nKeep hot cache lean - CLAUDE.md should never exceed 150 lines. If it grows larger, aggressively demote.\nDate everything - Every file in cold storage should have YYYY-MM-DD in filename or prominent metadata.\nUpdate after every significant action - Don't let memory drift from reality. Update immediately after ranking checks, audits, or reports.\nUse glossary liberally - If you find yourself explaining a term twice, add it to glossary.\nReview hot cache weekly - Quick scan to ensure everything there is still relevant and active.\nAutomate where possible - If ~~SEO tool or ~~search console connected, set up automatic updates to historical-rankings.csv.\nArchive aggressively - Better to have data in cold storage and not need it than clutter hot cache.\nLink between layers - CLAUDE.md should always reference where detailed data lives (\"Full data: memory/keywords/\").\nTimestamp changes - When updating CLAUDE.md, always update \"Last Updated\" date.\nUse memory for continuity - If you switch between different analysis sessions, memory ensures nothing is forgotten.\nReference Materials\nCORE-EEAT Content Benchmark — Content quality scoring stored in memory\nCITE Domain Rating — Domain authority scoring stored in memory\nRelated Skills\nrank-tracker — Provides ranking data to update memory\ncompetitor-analysis — Generates competitor reports for storage\nkeyword-research — Discovers keywords to add to memory\nperformance-reporter — Creates reports that trigger memory updates\ncontent-gap-analysis — Identifies optimization priorities for hot cache\nseo-content-writer — Logs published content to memory calendar\ncontent-quality-auditor — Content audit results stored in memory for tracking\ndomain-authority-auditor — CITE domain audit results stored in memory for tracking\nentity-optimizer — Store entity audit results for tracking over time"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "publisherUrl": "https://clawhub.ai/aaron-he-zhu/memory-management",
    "owner": "aaron-he-zhu",
    "version": "3.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/memory-management",
    "downloadUrl": "https://openagent3.xyz/downloads/memory-management",
    "agentUrl": "https://openagent3.xyz/skills/memory-management/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-management/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-management/agent.md"
  }
}