{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-structured-memory",
    "name": "Qordinate - Durable lists, facts, and reminders for OpenClaw agents.",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/SinghCoder/openclaw-structured-memory",
    "canonicalUrl": "https://clawhub.ai/SinghCoder/openclaw-structured-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-structured-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-structured-memory",
    "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/openclaw-structured-memory"
    },
    "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/openclaw-structured-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-structured-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-structured-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-structured-memory/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": "Qordinate - AI-Native Memory & Productivity for OpenClaw Agents",
        "body": "Qordinate is an AI agent platform that becomes durable, structured memory and productivity infrastructure for your users and agents.\n\nInstead of your OpenClaw agent trying to keep all state in its own scratchpad or a custom DB, it can connect to Qordinate via MCP (Model Context Protocol) and use the Qordinate AI agent to:\n\nStore and retrieve documents (notes, files, PDFs)\nManage contacts (people, companies, leads)\nMaintain lists and tasks with statuses, due dates, and reminders\nSearch the web for up-to-date information\nInteract with connected apps the user has linked to Qordinate\nCreate and manage forms and collect submissions\nSet up automations that run on schedules or triggers\n\nThe agent talks to Qordinate's AI agent through a single powerful tool — query_agent — using natural language."
      },
      {
        "title": "Connection Details",
        "body": "FieldValueProtocolMCP (Model Context Protocol) — Streamable HTTPMCP Server URLhttps://api.qordinate.ai/mcpAuth MethodBearer token — Authorization: Bearer qk_YOUR_API_KEYAPI Key FormatPrefixed with qk_"
      },
      {
        "title": "User Setup (what the agent should tell the user once)",
        "body": "Before the agent can connect, the user needs a Qordinate account and an API key:\n\nSign up at https://app.qordinate.ai using their phone number + OTP\nGo to Profile → API Keys → New API Key to create an API key\nGive the API key (starts with qk_) to the agent\n\nThe API key is shown only once at creation time. The user can set an expiry (1–365 days) or leave it non-expiring."
      },
      {
        "title": "MCP Tool: query_agent",
        "body": "Qordinate's MCP server exposes one tool — query_agent — which is a natural-language interface to the full Qordinate AI agent. The agent has access to the user's documents, contacts, lists, web search, and all connected apps."
      },
      {
        "title": "Input Schema",
        "body": "ParameterTypeRequiredDescriptionquerystring✅Your question or request for the Qordinate agentsession_idstring❌Optional session ID for multi-turn conversations"
      },
      {
        "title": "How to use session_id",
        "body": "Omit session_id for standalone queries\nTo have a multi-turn conversation, capture the session ID from the first response and pass it in subsequent calls\nThis lets the Qordinate agent maintain context across multiple queries"
      },
      {
        "title": "What the agent can do through query_agent",
        "body": "The query_agent tool invokes the full Qordinate AI agent, which can do everything a user interacting directly with Qordinate can do:"
      },
      {
        "title": "Structured Memory (Lists & Tasks)",
        "body": "Create, update, and query lists (tasks, contacts, leads, projects, resources, etc.)\nSet due dates, statuses, and reminders on list items\nQordinate manages reminders and notifications over time"
      },
      {
        "title": "Documents",
        "body": "Create, read, update, and delete documents\nUpload and retrieve files (PDFs, images, etc.)\nShare documents with other users"
      },
      {
        "title": "Contacts",
        "body": "Store and retrieve contact information\nImport contacts (including VCF format)\nSearch contacts by name, company, role, etc."
      },
      {
        "title": "Web Search",
        "body": "Search the web for current information\nThe agent can ask Qordinate to research topics and return results"
      },
      {
        "title": "Connected Apps",
        "body": "Interact with third-party apps the user has connected to Qordinate\nQuery data from connected services"
      },
      {
        "title": "Forms & Automations",
        "body": "Create forms and collect submissions\nSet up automations that trigger on schedules or events"
      },
      {
        "title": "Example Interactions",
        "body": "Your OpenClaw agent sends these as the query parameter to query_agent:"
      },
      {
        "title": "Managing tasks",
        "body": "Add a new task: Follow up with ACME about the reorder pilot, due next Tuesday 3pm, status todo, notes: important client meeting"
      },
      {
        "title": "Storing contacts",
        "body": "Save a new contact: Harpinder Singh, Co-founder at qordinate.ai, building Qordinate"
      },
      {
        "title": "Querying information",
        "body": "Show me all my open tasks due this week"
      },
      {
        "title": "Searching the web",
        "body": "Search the web for the latest pricing of OpenAI GPT-4o API"
      },
      {
        "title": "Working with documents",
        "body": "Create a new document titled \"Meeting Notes - ACME Q1 Review\" with the following content: ..."
      },
      {
        "title": "Updating items",
        "body": "Mark the task \"Follow up with ACME\" as done"
      },
      {
        "title": "How the agent should think about Qordinate",
        "body": "Treat Qordinate as the source of truth for \"what needs doing\" and \"who is who\" across time\nOffload anything the user will care about later — don't keep it in ephemeral memory\nUse natural language — the query_agent tool understands plain English requests\nUse session_id for related queries — if you're doing a multi-step workflow (e.g., \"list tasks\" then \"mark task X as done\"), use the same session_id\nBe specific — include list names, field values, dates, and context in your queries"
      },
      {
        "title": "User Channels (optional, for the user)",
        "body": "Users can also interact with Qordinate directly on their preferred messaging platform. This is independent of the agent's MCP connection:\n\nWhatsApp: connect via https://qordinate.ai/whatsapp\nTelegram: connect via https://qordinate.ai/telegram\nSlack: connect via https://qordinate.ai/slack\n\nEverything the user does on these channels is reflected in the same account the agent accesses via MCP — they share the same data."
      }
    ],
    "body": "Qordinate - AI-Native Memory & Productivity for OpenClaw Agents\n\nQordinate is an AI agent platform that becomes durable, structured memory and productivity infrastructure for your users and agents.\n\nInstead of your OpenClaw agent trying to keep all state in its own scratchpad or a custom DB, it can connect to Qordinate via MCP (Model Context Protocol) and use the Qordinate AI agent to:\n\nStore and retrieve documents (notes, files, PDFs)\nManage contacts (people, companies, leads)\nMaintain lists and tasks with statuses, due dates, and reminders\nSearch the web for up-to-date information\nInteract with connected apps the user has linked to Qordinate\nCreate and manage forms and collect submissions\nSet up automations that run on schedules or triggers\n\nThe agent talks to Qordinate's AI agent through a single powerful tool — query_agent — using natural language.\n\nConnection Details\nField\tValue\nProtocol\tMCP (Model Context Protocol) — Streamable HTTP\nMCP Server URL\thttps://api.qordinate.ai/mcp\nAuth Method\tBearer token — Authorization: Bearer qk_YOUR_API_KEY\nAPI Key Format\tPrefixed with qk_\nUser Setup (what the agent should tell the user once)\n\nBefore the agent can connect, the user needs a Qordinate account and an API key:\n\nSign up at https://app.qordinate.ai using their phone number + OTP\nGo to Profile → API Keys → New API Key to create an API key\nGive the API key (starts with qk_) to the agent\n\nThe API key is shown only once at creation time. The user can set an expiry (1–365 days) or leave it non-expiring.\n\nMCP Tool: query_agent\n\nQordinate's MCP server exposes one tool — query_agent — which is a natural-language interface to the full Qordinate AI agent. The agent has access to the user's documents, contacts, lists, web search, and all connected apps.\n\nInput Schema\nParameter\tType\tRequired\tDescription\nquery\tstring\t✅\tYour question or request for the Qordinate agent\nsession_id\tstring\t❌\tOptional session ID for multi-turn conversations\nHow to use session_id\nOmit session_id for standalone queries\nTo have a multi-turn conversation, capture the session ID from the first response and pass it in subsequent calls\nThis lets the Qordinate agent maintain context across multiple queries\nWhat the agent can do through query_agent\n\nThe query_agent tool invokes the full Qordinate AI agent, which can do everything a user interacting directly with Qordinate can do:\n\nStructured Memory (Lists & Tasks)\nCreate, update, and query lists (tasks, contacts, leads, projects, resources, etc.)\nSet due dates, statuses, and reminders on list items\nQordinate manages reminders and notifications over time\nDocuments\nCreate, read, update, and delete documents\nUpload and retrieve files (PDFs, images, etc.)\nShare documents with other users\nContacts\nStore and retrieve contact information\nImport contacts (including VCF format)\nSearch contacts by name, company, role, etc.\nWeb Search\nSearch the web for current information\nThe agent can ask Qordinate to research topics and return results\nConnected Apps\nInteract with third-party apps the user has connected to Qordinate\nQuery data from connected services\nForms & Automations\nCreate forms and collect submissions\nSet up automations that trigger on schedules or events\nExample Interactions\n\nYour OpenClaw agent sends these as the query parameter to query_agent:\n\nManaging tasks\nAdd a new task: Follow up with ACME about the reorder pilot, due next Tuesday 3pm, status todo, notes: important client meeting\n\nStoring contacts\nSave a new contact: Harpinder Singh, Co-founder at qordinate.ai, building Qordinate\n\nQuerying information\nShow me all my open tasks due this week\n\nSearching the web\nSearch the web for the latest pricing of OpenAI GPT-4o API\n\nWorking with documents\nCreate a new document titled \"Meeting Notes - ACME Q1 Review\" with the following content: ...\n\nUpdating items\nMark the task \"Follow up with ACME\" as done\n\nHow the agent should think about Qordinate\nTreat Qordinate as the source of truth for \"what needs doing\" and \"who is who\" across time\nOffload anything the user will care about later — don't keep it in ephemeral memory\nUse natural language — the query_agent tool understands plain English requests\nUse session_id for related queries — if you're doing a multi-step workflow (e.g., \"list tasks\" then \"mark task X as done\"), use the same session_id\nBe specific — include list names, field values, dates, and context in your queries\nUser Channels (optional, for the user)\n\nUsers can also interact with Qordinate directly on their preferred messaging platform. This is independent of the agent's MCP connection:\n\nWhatsApp: connect via https://qordinate.ai/whatsapp\nTelegram: connect via https://qordinate.ai/telegram\nSlack: connect via https://qordinate.ai/slack\n\nEverything the user does on these channels is reflected in the same account the agent accesses via MCP — they share the same data."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/SinghCoder/openclaw-structured-memory",
    "publisherUrl": "https://clawhub.ai/SinghCoder/openclaw-structured-memory",
    "owner": "SinghCoder",
    "version": "2.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-structured-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-structured-memory",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-structured-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-structured-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-structured-memory/agent.md"
  }
}