{
  "schemaVersion": "1.0",
  "item": {
    "slug": "memory-hygiene",
    "name": "Memory Hygiene",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/dylanbaker24/memory-hygiene",
    "canonicalUrl": "https://clawhub.ai/dylanbaker24/memory-hygiene",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/memory-hygiene",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-hygiene",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.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-hygiene"
    },
    "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-hygiene",
    "agentPageUrl": "https://openagent3.xyz/skills/memory-hygiene/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-hygiene/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-hygiene/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 Hygiene",
        "body": "Keep vector memory lean. Prevent token waste from junk memories."
      },
      {
        "title": "Quick Commands",
        "body": "Audit: Check what's in memory\n\nmemory_recall query=\"*\" limit=50\n\nWipe: Clear all vector memory\n\nrm -rf ~/.clawdbot/memory/lancedb/\n\nThen restart gateway: clawdbot gateway restart\n\nReseed: After wipe, store key facts from MEMORY.md\n\nmemory_store text=\"<fact>\" category=\"preference|fact|decision\" importance=0.9"
      },
      {
        "title": "Config: Disable Auto-Capture",
        "body": "The main source of junk is autoCapture: true. Disable it:\n\n{\n  \"plugins\": {\n    \"entries\": {\n      \"memory-lancedb\": {\n        \"config\": {\n          \"autoCapture\": false,\n          \"autoRecall\": true\n        }\n      }\n    }\n  }\n}\n\nUse gateway action=config.patch to apply."
      },
      {
        "title": "What to Store (Intentionally)",
        "body": "✅ Store:\n\nUser preferences (tools, workflows, communication style)\nKey decisions (project choices, architecture)\nImportant facts (accounts, credentials locations, contacts)\nLessons learned\n\n❌ Never store:\n\nHeartbeat status (\"HEARTBEAT_OK\", \"No new messages\")\nTransient info (current time, temp states)\nRaw message logs (already in files)\nOAuth URLs or tokens"
      },
      {
        "title": "Monthly Maintenance Cron",
        "body": "Set up a monthly wipe + reseed:\n\ncron action=add job={\n  \"name\": \"memory-maintenance\",\n  \"schedule\": \"0 4 1 * *\",\n  \"text\": \"Monthly memory maintenance: 1) Wipe ~/.clawdbot/memory/lancedb/ 2) Parse MEMORY.md 3) Store key facts to fresh LanceDB 4) Report completion\"\n}"
      },
      {
        "title": "Storage Guidelines",
        "body": "When using memory_store:\n\nKeep text concise (<100 words)\nUse appropriate category\nSet importance 0.7-1.0 for valuable info\nOne concept per memory entry"
      }
    ],
    "body": "Memory Hygiene\n\nKeep vector memory lean. Prevent token waste from junk memories.\n\nQuick Commands\n\nAudit: Check what's in memory\n\nmemory_recall query=\"*\" limit=50\n\n\nWipe: Clear all vector memory\n\nrm -rf ~/.clawdbot/memory/lancedb/\n\n\nThen restart gateway: clawdbot gateway restart\n\nReseed: After wipe, store key facts from MEMORY.md\n\nmemory_store text=\"<fact>\" category=\"preference|fact|decision\" importance=0.9\n\nConfig: Disable Auto-Capture\n\nThe main source of junk is autoCapture: true. Disable it:\n\n{\n  \"plugins\": {\n    \"entries\": {\n      \"memory-lancedb\": {\n        \"config\": {\n          \"autoCapture\": false,\n          \"autoRecall\": true\n        }\n      }\n    }\n  }\n}\n\n\nUse gateway action=config.patch to apply.\n\nWhat to Store (Intentionally)\n\n✅ Store:\n\nUser preferences (tools, workflows, communication style)\nKey decisions (project choices, architecture)\nImportant facts (accounts, credentials locations, contacts)\nLessons learned\n\n❌ Never store:\n\nHeartbeat status (\"HEARTBEAT_OK\", \"No new messages\")\nTransient info (current time, temp states)\nRaw message logs (already in files)\nOAuth URLs or tokens\nMonthly Maintenance Cron\n\nSet up a monthly wipe + reseed:\n\ncron action=add job={\n  \"name\": \"memory-maintenance\",\n  \"schedule\": \"0 4 1 * *\",\n  \"text\": \"Monthly memory maintenance: 1) Wipe ~/.clawdbot/memory/lancedb/ 2) Parse MEMORY.md 3) Store key facts to fresh LanceDB 4) Report completion\"\n}\n\nStorage Guidelines\n\nWhen using memory_store:\n\nKeep text concise (<100 words)\nUse appropriate category\nSet importance 0.7-1.0 for valuable info\nOne concept per memory entry"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/dylanbaker24/memory-hygiene",
    "publisherUrl": "https://clawhub.ai/dylanbaker24/memory-hygiene",
    "owner": "dylanbaker24",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/memory-hygiene",
    "downloadUrl": "https://openagent3.xyz/downloads/memory-hygiene",
    "agentUrl": "https://openagent3.xyz/skills/memory-hygiene/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-hygiene/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-hygiene/agent.md"
  }
}