{
  "schemaVersion": "1.0",
  "item": {
    "slug": "memory-search",
    "name": "Memory Search",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/aigentic-net/memory-search",
    "canonicalUrl": "https://clawhub.ai/aigentic-net/memory-search",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/memory-search",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-search",
    "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-search"
    },
    "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-search",
    "agentPageUrl": "https://openagent3.xyz/skills/memory-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-search/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 Search",
        "body": "You have two tools for recalling information from your memory files. Use them."
      },
      {
        "title": "memory_search",
        "body": "Semantic vector search across your indexed memory files (MEMORY.md, memory/*.md, and session transcripts).\n\nParameters:\n\nParamTypeRequiredDescriptionquerystringyesNatural language question or topic to search formaxResultsnumbernoMax results to return (default: 6)minScorenumbernoMinimum relevance score threshold (0-1)\n\nExample calls:\n\n{ \"query\": \"what projects is the human working on\" }\n{ \"query\": \"preferences about code style\", \"maxResults\": 3 }\n{ \"query\": \"important dates birthdays deadlines\", \"maxResults\": 10, \"minScore\": 0.3 }\n\nReturns: Array of results, each with:\n\nsnippet — the matching text chunk\npath — relative file path (e.g. MEMORY.md, memory/2026-02-07.md)\nstartLine / endLine — line range in the source file\nscore — relevance score\ncitation — formatted source reference (in direct chats)"
      },
      {
        "title": "memory_get",
        "body": "Read a specific section of a memory file by path and line range. Use this after memory_search to pull more context around a result.\n\nParameters:\n\nParamTypeRequiredDescriptionpathstringyesRelative path from workspace (e.g. MEMORY.md, memory/2026-02-07.md)fromnumbernoStarting line numberlinesnumbernoNumber of lines to read\n\nExample calls:\n\n{ \"path\": \"MEMORY.md\" }\n{ \"path\": \"memory/2026-02-07.md\", \"from\": 15, \"lines\": 30 }"
      },
      {
        "title": "When to Use Memory Search",
        "body": "Always search before answering about:\n\nPrior conversations or decisions\nThe human's preferences, habits, or opinions\nDates, deadlines, birthdays, events\nProject status or history\nAnything the human said \"remember this\" about\nTodos, action items, or commitments\nPeople, names, relationships\n\nThe pattern is:\n\nReceive a question that might involve past context\nCall memory_search with a relevant query\nReview the results\nIf a snippet looks promising but needs more context, call memory_get with the path and line range\nAnswer using what you found (cite sources in direct chats)"
      },
      {
        "title": "When NOT to Use",
        "body": "Purely factual questions with no personal context (\"what is Python?\")\nThe human explicitly gives you all the context you need in the message\nYou just searched and the results are still in your context"
      },
      {
        "title": "Tips",
        "body": "Be specific in queries. \"birthday\" works better than \"important information about the human.\"\nSearch multiple angles. If one query returns nothing useful, try rephrasing. \"project deadlines\" and \"what's due soon\" might return different results.\nDon't over-fetch. Start with default maxResults. Only increase if you need more coverage.\nUse memory_get sparingly. The search snippets are usually enough. Only pull full sections when you need surrounding context.\nSay when you checked. If you searched and found nothing, tell the human: \"I checked my memory and didn't find anything about that.\" Don't silently guess."
      },
      {
        "title": "What Gets Indexed",
        "body": "Your memory search covers:\n\nMEMORY.md — your curated long-term memory\nmemory/*.md — daily notes and raw logs\nSession transcripts (if enabled)\n\nThese files are automatically indexed. You don't need to trigger indexing — just write to the files and the system handles the rest."
      },
      {
        "title": "Do NOT",
        "body": "Do NOT try to run shell commands like cat or ls to read memory files. Use memory_search and memory_get.\nDo NOT try to configure or debug the search system. That's operator config, not your job.\nDo NOT assume memory is empty without searching first. The index may have content even if the memory/ directory looks sparse."
      }
    ],
    "body": "Memory Search\n\nYou have two tools for recalling information from your memory files. Use them.\n\nTools\nmemory_search\n\nSemantic vector search across your indexed memory files (MEMORY.md, memory/*.md, and session transcripts).\n\nParameters:\n\nParam\tType\tRequired\tDescription\nquery\tstring\tyes\tNatural language question or topic to search for\nmaxResults\tnumber\tno\tMax results to return (default: 6)\nminScore\tnumber\tno\tMinimum relevance score threshold (0-1)\n\nExample calls:\n\n{ \"query\": \"what projects is the human working on\" }\n{ \"query\": \"preferences about code style\", \"maxResults\": 3 }\n{ \"query\": \"important dates birthdays deadlines\", \"maxResults\": 10, \"minScore\": 0.3 }\n\n\nReturns: Array of results, each with:\n\nsnippet — the matching text chunk\npath — relative file path (e.g. MEMORY.md, memory/2026-02-07.md)\nstartLine / endLine — line range in the source file\nscore — relevance score\ncitation — formatted source reference (in direct chats)\nmemory_get\n\nRead a specific section of a memory file by path and line range. Use this after memory_search to pull more context around a result.\n\nParameters:\n\nParam\tType\tRequired\tDescription\npath\tstring\tyes\tRelative path from workspace (e.g. MEMORY.md, memory/2026-02-07.md)\nfrom\tnumber\tno\tStarting line number\nlines\tnumber\tno\tNumber of lines to read\n\nExample calls:\n\n{ \"path\": \"MEMORY.md\" }\n{ \"path\": \"memory/2026-02-07.md\", \"from\": 15, \"lines\": 30 }\n\nWhen to Use Memory Search\n\nAlways search before answering about:\n\nPrior conversations or decisions\nThe human's preferences, habits, or opinions\nDates, deadlines, birthdays, events\nProject status or history\nAnything the human said \"remember this\" about\nTodos, action items, or commitments\nPeople, names, relationships\n\nThe pattern is:\n\nReceive a question that might involve past context\nCall memory_search with a relevant query\nReview the results\nIf a snippet looks promising but needs more context, call memory_get with the path and line range\nAnswer using what you found (cite sources in direct chats)\nWhen NOT to Use\nPurely factual questions with no personal context (\"what is Python?\")\nThe human explicitly gives you all the context you need in the message\nYou just searched and the results are still in your context\nTips\nBe specific in queries. \"birthday\" works better than \"important information about the human.\"\nSearch multiple angles. If one query returns nothing useful, try rephrasing. \"project deadlines\" and \"what's due soon\" might return different results.\nDon't over-fetch. Start with default maxResults. Only increase if you need more coverage.\nUse memory_get sparingly. The search snippets are usually enough. Only pull full sections when you need surrounding context.\nSay when you checked. If you searched and found nothing, tell the human: \"I checked my memory and didn't find anything about that.\" Don't silently guess.\nWhat Gets Indexed\n\nYour memory search covers:\n\nMEMORY.md — your curated long-term memory\nmemory/*.md — daily notes and raw logs\nSession transcripts (if enabled)\n\nThese files are automatically indexed. You don't need to trigger indexing — just write to the files and the system handles the rest.\n\nDo NOT\nDo NOT try to run shell commands like cat or ls to read memory files. Use memory_search and memory_get.\nDo NOT try to configure or debug the search system. That's operator config, not your job.\nDo NOT assume memory is empty without searching first. The index may have content even if the memory/ directory looks sparse."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/aigentic-net/memory-search",
    "publisherUrl": "https://clawhub.ai/aigentic-net/memory-search",
    "owner": "aigentic-net",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/memory-search",
    "downloadUrl": "https://openagent3.xyz/downloads/memory-search",
    "agentUrl": "https://openagent3.xyz/skills/memory-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/memory-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/memory-search/agent.md"
  }
}