{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agents-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/agents-structured-memory",
    "canonicalUrl": "https://clawhub.ai/SinghCoder/agents-structured-memory",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agents-structured-memory",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agents-structured-memory",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILLS.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",
      "slug": "agents-structured-memory",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T02:26:59.777Z",
      "expiresAt": "2026-05-08T02:26:59.777Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agents-structured-memory",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agents-structured-memory",
        "contentDisposition": "attachment; filename=\"agents-structured-memory-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "agents-structured-memory"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/agents-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/agents-structured-memory",
    "agentPageUrl": "https://openagent3.xyz/skills/agents-structured-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agents-structured-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agents-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 - Structured Memory for OpenClaw Agents",
        "body": "Qordinate is a chat-based assistant that becomes durable, structured memory 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:\n\nsend messages to Qordinate on WhatsApp, Telegram, or Slack\nuse a simple, structured text protocol to:\n\nstore facts (preferences, flags, config)\nmaintain lists (tasks, contacts, leads, etc.)\ncreate reminders that Qordinate will handle over time\n\nThe agent talks to Qordinate exactly like a human would - via chat."
      },
      {
        "title": "User Setup (what the agent should tell the user once)",
        "body": "Before the agent can rely on Qordinate, the user needs an account:\n\nAsk the user to open https://qordinate.ai in a browser\nSign up by logging in with their phone number + OTP\nStart a chat with Qordinate on one channel:\n\nWhatsApp: connect via https://qordinate.ai/whatsapp\nTelegram: connect via https://qordinate.ai/telegram\nSlack: connect via https://qordinate.ai/slack\n\nOnce that's done, your agent can start sending messages to that same chat window."
      },
      {
        "title": "How the agent should talk to Qordinate",
        "body": "Qordinate is built around lists. Think of them as named buckets like tasks, contacts, leads, notes, etc. Your agent's job is to tell Qordinate, in plain language, what to add to which list, and what to fetch later.\n\nAt a high level, the agent should do three things:\n\nCreate list items when something important appears\nUpdate list items when the status changes\nQuery lists when it needs context or next actions\n\nAll of this can be done with natural language messages sent to Qordinate over WhatsApp / Telegram / Slack."
      },
      {
        "title": "1. Creating items in lists",
        "body": "When your agent notices something that should be remembered (a follow-up, a person, a lead, a link), it should explicitly tell Qordinate what list to use and what fields matter.\n\nExample phrasings your agent can send:\n\n\"Qordinate, add a new task to the tasks list:\ntitle: Follow up with ACME about the reorder pilot\nstatus: todo\ndue: next Tuesday 3pm\nnotes: important client meeting\"\n\n\n\"Qordinate, create a contact in the contacts list:\nname: Harpinder Singh\ncompany: qordinate.ai\nrole: Co-founder\nnotes: building Qordinate\"\n\n\n\"Qordinate, save this link in the resources list:\ntitle: OpenClaw + Qordinate integration idea\nurl: https://example.com/post\nnotes: inspiration for agent-to-agent coordination.\"\n\nKey points:\n\nAlways mention the list name (tasks, contacts, etc.).\nGive Qordinate a title plus a few structured fields (status, due date, notes) in plain language.\nThe agent can include where it came from (email, chat, file) so Qordinate can link back later."
      },
      {
        "title": "How the agent should think about lists",
        "body": "Use different lists for different domains: tasks, contacts, leads, projects, resources, etc.\nTreat Qordinate as the source of truth for \"what needs doing\" and \"who is who\" across time.\nWhenever the agent thinks \"the user will care about this later\", it should create or update something in a list, not keep it in ephemeral memory.\n\nIn short: your OpenClaw agent talks to Qordinate like a slightly bossy human assistant\n\n\"add this to the tasks list\"\n\"update that contact\"\n\"show me my open tasks\"\n\nand Qordinate handles turning that into structured, durable memory."
      }
    ],
    "body": "Qordinate - Structured Memory for OpenClaw Agents\n\nQordinate is a chat-based assistant that becomes durable, structured memory 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:\n\nsend messages to Qordinate on WhatsApp, Telegram, or Slack\nuse a simple, structured text protocol to:\nstore facts (preferences, flags, config)\nmaintain lists (tasks, contacts, leads, etc.)\ncreate reminders that Qordinate will handle over time\n\nThe agent talks to Qordinate exactly like a human would - via chat.\n\nUser Setup (what the agent should tell the user once)\n\nBefore the agent can rely on Qordinate, the user needs an account:\n\nAsk the user to open https://qordinate.ai in a browser\nSign up by logging in with their phone number + OTP\nStart a chat with Qordinate on one channel:\nWhatsApp: connect via https://qordinate.ai/whatsapp\nTelegram: connect via https://qordinate.ai/telegram\nSlack: connect via https://qordinate.ai/slack\n\nOnce that's done, your agent can start sending messages to that same chat window.\n\nHow the agent should talk to Qordinate\n\nQordinate is built around lists. Think of them as named buckets like tasks, contacts, leads, notes, etc. Your agent's job is to tell Qordinate, in plain language, what to add to which list, and what to fetch later.\n\nAt a high level, the agent should do three things:\n\nCreate list items when something important appears\nUpdate list items when the status changes\nQuery lists when it needs context or next actions\n\nAll of this can be done with natural language messages sent to Qordinate over WhatsApp / Telegram / Slack.\n\n1. Creating items in lists\n\nWhen your agent notices something that should be remembered (a follow-up, a person, a lead, a link), it should explicitly tell Qordinate what list to use and what fields matter.\n\nExample phrasings your agent can send:\n\n\"Qordinate, add a new task to the tasks list: title: Follow up with ACME about the reorder pilot status: todo due: next Tuesday 3pm notes: important client meeting\"\n\n\"Qordinate, create a contact in the contacts list: name: Harpinder Singh company: qordinate.ai role: Co-founder notes: building Qordinate\"\n\n\"Qordinate, save this link in the resources list: title: OpenClaw + Qordinate integration idea url: https://example.com/post notes: inspiration for agent-to-agent coordination.\"\n\nKey points:\n\nAlways mention the list name (tasks, contacts, etc.).\nGive Qordinate a title plus a few structured fields (status, due date, notes) in plain language.\nThe agent can include where it came from (email, chat, file) so Qordinate can link back later.\nHow the agent should think about lists\nUse different lists for different domains: tasks, contacts, leads, projects, resources, etc.\nTreat Qordinate as the source of truth for \"what needs doing\" and \"who is who\" across time.\nWhenever the agent thinks \"the user will care about this later\", it should create or update something in a list, not keep it in ephemeral memory.\n\nIn short: your OpenClaw agent talks to Qordinate like a slightly bossy human assistant\n\n\"add this to the tasks list\"\n\"update that contact\"\n\"show me my open tasks\"\n\nand Qordinate handles turning that into structured, durable memory."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/SinghCoder/agents-structured-memory",
    "publisherUrl": "https://clawhub.ai/SinghCoder/agents-structured-memory",
    "owner": "SinghCoder",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agents-structured-memory",
    "downloadUrl": "https://openagent3.xyz/downloads/agents-structured-memory",
    "agentUrl": "https://openagent3.xyz/skills/agents-structured-memory/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agents-structured-memory/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agents-structured-memory/agent.md"
  }
}