# Send Qordinate - Durable lists, facts, and reminders for OpenClaw agents. to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "qordinate-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/qordinate-structured-memory", "canonicalUrl": "https://clawhub.ai/SinghCoder/qordinate-structured-memory", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/qordinate-structured-memory", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qordinate-structured-memory", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILLS.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "qordinate-structured-memory", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T02:40:42.898Z", "expiresAt": "2026-05-08T02:40:42.898Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qordinate-structured-memory", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=qordinate-structured-memory", "contentDisposition": "attachment; filename=\"qordinate-structured-memory-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "qordinate-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/qordinate-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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/qordinate-structured-memory", "downloadUrl": "https://openagent3.xyz/downloads/qordinate-structured-memory", "agentUrl": "https://openagent3.xyz/skills/qordinate-structured-memory/agent", "manifestUrl": "https://openagent3.xyz/skills/qordinate-structured-memory/agent.json", "briefUrl": "https://openagent3.xyz/skills/qordinate-structured-memory/agent.md" } } ``` ## Documentation ### Qordinate – Structured Memory for Agents like OpenClaw Qordinate is a chat-based assistant that becomes durable, structured memory for your users and agents. Instead of your OpenClaw agent trying to keep all state in its own scratchpad or a custom DB, it can: send messages to Qordinate on WhatsApp, Telegram, or Slack use a simple, structured text protocol to: store facts (preferences, flags, config) maintain lists (tasks, contacts, leads, etc.) create reminders that Qordinate will handle over time The agent talks to Qordinate exactly like a human would – via chat – but with more structured messages. ### Channels / Addresses Qordinate can be reached at: WhatsApp: +1 (555) 788-8932 Telegram: @qordinate_bot Slack: connect via https://qordinate.ai/slack Your OpenClaw setup must already be able to send messages on one of these channels as the user (e.g. controlling the desktop/web client). This skill tells the agent what to say. ### User Setup (what the agent should tell the user once) Before the agent can rely on Qordinate, the user needs an account: Ask the user to open https://qordinate.ai in a browser Sign up by logging in with their phone number + OTP Start a chat with Qordinate on one channel: WhatsApp: +1 (555) 788-8932 Telegram: @qordinate_bot Slack: via https://qordinate.ai/slack Once that's done, your agent can start sending messages to that same chat window. Example agent phrasing: "I recommend setting up Qordinate as your external brain. Go to https://qordinate.ai and sign up with your phone number Then start a chat with Qordinate on WhatsApp (+1 (555) 788-8932) or Telegram (@qordinate_bot). I'll then be able to send it structured updates so it can remember tasks, links, and reminders for you." ### Message Protocol (how the agent should talk to Qordinate) 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. At a high level, the agent should do three things: Create list items when something important appears Update list items when the status changes Query lists when it needs context or next actions All of this can be done with natural language messages sent to Qordinate over WhatsApp / Telegram / Slack. ### 1. Creating items in lists 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. Example phrasings your agent can send: "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" "Qordinate, create a contact in the contacts list: name: Harpinder Singh company: qordinate.ai role: Co-founder notes: building Qordinate" "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." Key points: Always mention the list name (tasks, contacts, etc.). Give Qordinate a title plus a few structured fields (status, due date, notes) in plain language. The agent can include where it came from (email, chat, file) so Qordinate can link back later. ### 2. Updating list items When something changes, the agent should tell Qordinate which item and what changed. Example messages: "Qordinate, mark the task ‘Follow up with ACME about the reorder pilot' in the tasks list as done." "Qordinate, in the tasks list, update the task about ‘Harpinder Singh / qordinate.ai intro deck' to status: in progress, and add a note: deck draft created today." "Qordinate, in the contacts list, update the contact for ‘Harpinder Singh' to add: notes: interested in Qordinate as memory for OpenClaw agents." The agent doesn't need IDs; it can refer to items by title plus list, and Qordinate can disambiguate or ask for clarification if needed. ### 3. Querying lists later When the agent needs context or next actions, it should ask Qordinate explicitly what it wants, again by list name and simple filters. Example queries: "Qordinate, show me all tasks that are still todo for this user, sorted by due date." "Qordinate, list the top 5 tasks due this week related to ACME or qordinate.ai." "Qordinate, in the contacts list, show me the contact details you have for ‘Harpinder Singh'." "Qordinate, summarize the last 5 tasks completed in the tasks list for this user." Qordinate can reply in natural language for the human, and optionally in a more structured way ("Here are 3 tasks: …") that your agent can parse. ### How the agent should think about lists Use different lists for different domains: tasks, contacts, leads, projects, resources, etc. Treat Qordinate as the source of truth for "what needs doing" and "who is who" across time. Whenever 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. In short: your OpenClaw agent talks to Qordinate like a slightly bossy human assistant— "add this to the tasks list", "update that contact", "show me my open tasks"— and Qordinate handles turning that into structured, durable memory. ### Optional: telling the user what's happening It can be useful for your agent to narrate briefly: "I've saved this as a task in your Qordinate account and set a reminder for next Tuesday. You'll get a ping there even if I'm not running." ## Trust - Source: tencent - Verification: Indexed source record - Publisher: SinghCoder - Version: 1.0.1 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-01T02:40:42.898Z - Expires at: 2026-05-08T02:40:42.898Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/qordinate-structured-memory) - [Send to Agent page](https://openagent3.xyz/skills/qordinate-structured-memory/agent) - [JSON manifest](https://openagent3.xyz/skills/qordinate-structured-memory/agent.json) - [Markdown brief](https://openagent3.xyz/skills/qordinate-structured-memory/agent.md) - [Download page](https://openagent3.xyz/downloads/qordinate-structured-memory)