{
  "schemaVersion": "1.0",
  "item": {
    "slug": "self-prompt",
    "name": "Self-Prompt",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/eliranwong/self-prompt",
    "canonicalUrl": "https://clawhub.ai/eliranwong/self-prompt",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/self-prompt",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=self-prompt",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/send_agent_task.py",
      "scripts/send_agent_task.sh"
    ],
    "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/self-prompt"
    },
    "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/self-prompt",
    "agentPageUrl": "https://openagent3.xyz/skills/self-prompt/agent",
    "manifestUrl": "https://openagent3.xyz/skills/self-prompt/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/self-prompt/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": "The Problem",
        "body": "When automated scripts (cron, monitoring) send messages via openclaw message send:\n\nMessages appear in chat as \"system messages\"\nAgents may treat them as background info, not tasks\nAgents respond to user messages but ignore automated ones\nAccountability checks, alerts, and tasks go unanswered"
      },
      {
        "title": "The Solution",
        "body": "Use openclaw agent instead of openclaw message send for messages requiring agent response:\n\n# OLD (agent may ignore):\nopenclaw message send --target -GROUP_ID --message \"TASK: Do something\"\n\n# NEW (agent MUST respond):\nRESPONSE=$(openclaw agent \\\n    --agent AGENT_ID \\\n    --session-id \"agent:AGENT_ID:telegram:group:GROUP_ID\" \\\n    --channel telegram \\\n    --message \"TASK: Do something\" \\\n    --timeout 180)\n\n# Send response to chat:\nopenclaw message send --target -GROUP_ID --message \"$RESPONSE\""
      },
      {
        "title": "Why This Works",
        "body": "openclaw message send → Creates chat message → Agent sees as \"notification\"\nopenclaw agent → Triggers actual agent turn → Agent MUST process and respond"
      },
      {
        "title": "For Bash Scripts",
        "body": "Use scripts/send_agent_task.sh:\n\n# Simple usage:\n~/.openclaw/skills/self-prompt/scripts/send_agent_task.sh \\\n    \"AGENT_ID\" \\\n    \"GROUP_ID\" \\\n    \"Your task message here\""
      },
      {
        "title": "For Python Scripts",
        "body": "Use scripts/send_agent_task.py:\n\nfrom send_agent_task import send_and_deliver\n\nsuccess, response = send_and_deliver(\n    agent_id=\"stock-trading\",\n    group_id=\"-5283045656\", \n    message=\"TASK: Analyze current positions\",\n    timeout=180\n)"
      },
      {
        "title": "Pattern: Data + Task Separation",
        "body": "For monitoring scripts, separate data delivery from task requests:\n\n# 1. Send DATA immediately (informational)\nopenclaw message send --target \"$GROUP_ID\" --message \"📊 Position Data:\n$POSITIONS\"\n\n# 2. Send TASK via agent (forces response)\nRESPONSE=$(openclaw agent \\\n    --agent \"$AGENT_ID\" \\\n    --session-id \"agent:$AGENT_ID:telegram:group:$GROUP_ID\" \\\n    --message \"Analyze the data above and report findings\" \\\n    --timeout 180)\n\n# 3. Deliver response\nopenclaw message send --target \"$GROUP_ID\" --message \"📊 Analysis:\n$RESPONSE\""
      },
      {
        "title": "Accountability Checks",
        "body": "# Force agent to respond to accountability check\nsend_agent_task.sh \"my-agent\" \"-123456789\" \\\n    \"ACCOUNTABILITY CHECK: Did you complete the required tasks? Respond with status.\""
      },
      {
        "title": "Monitoring Alerts",
        "body": "# Force agent to investigate and report\nsend_agent_task.sh \"trading-agent\" \"-123456789\" \\\n    \"ALERT: Position down 5%. Investigate and report findings.\""
      },
      {
        "title": "Scheduled Research Tasks",
        "body": "# Force agent to do research\nsend_agent_task.sh \"research-agent\" \"-123456789\" \\\n    \"DAILY TASK: Search for news on $SYMBOLS and summarize findings.\""
      },
      {
        "title": "Session Key Format",
        "body": "The session key follows this pattern:\n\nagent:AGENT_ID:CHANNEL:TYPE:TARGET\n\nExamples:\n\nagent:stock-trading:telegram:group:-5283045656\nagent:main:telegram:direct:123456789\nagent:assistant:discord:channel:987654321"
      },
      {
        "title": "send_agent_task.sh",
        "body": "Location: scripts/send_agent_task.sh\n\nsend_agent_task.sh AGENT_ID GROUP_ID \"message\" [timeout]\n\nSends task via openclaw agent\nCaptures response\nSends response to group via message send\nLogs to ~/agent_task.log"
      },
      {
        "title": "send_agent_task.py",
        "body": "Location: scripts/send_agent_task.py\n\nfrom send_agent_task import send_and_deliver\n\nsuccess, response = send_and_deliver(\n    agent_id=\"agent-name\",\n    group_id=\"-123456789\",\n    message=\"Task message\",\n    timeout=180,\n    channel=\"telegram\"\n)"
      },
      {
        "title": "Agent not responding",
        "body": "Verify agent is running: openclaw gateway status\nCheck session key format matches your agent/group\nIncrease timeout for long-running tasks"
      },
      {
        "title": "Response not appearing in chat",
        "body": "Ensure script sends response via message send after capturing\nCheck GROUP_ID is correct (negative for groups)\nVerify channel is correct (telegram/discord/etc)"
      },
      {
        "title": "Timeout errors",
        "body": "Increase timeout for research/analysis tasks (300-600 seconds)\nCheck if agent is overloaded with concurrent requests"
      }
    ],
    "body": "Self-Prompt: Forcing Agent Responses\nThe Problem\n\nWhen automated scripts (cron, monitoring) send messages via openclaw message send:\n\nMessages appear in chat as \"system messages\"\nAgents may treat them as background info, not tasks\nAgents respond to user messages but ignore automated ones\nAccountability checks, alerts, and tasks go unanswered\nThe Solution\n\nUse openclaw agent instead of openclaw message send for messages requiring agent response:\n\n# OLD (agent may ignore):\nopenclaw message send --target -GROUP_ID --message \"TASK: Do something\"\n\n# NEW (agent MUST respond):\nRESPONSE=$(openclaw agent \\\n    --agent AGENT_ID \\\n    --session-id \"agent:AGENT_ID:telegram:group:GROUP_ID\" \\\n    --channel telegram \\\n    --message \"TASK: Do something\" \\\n    --timeout 180)\n\n# Send response to chat:\nopenclaw message send --target -GROUP_ID --message \"$RESPONSE\"\n\nWhy This Works\nopenclaw message send → Creates chat message → Agent sees as \"notification\"\nopenclaw agent → Triggers actual agent turn → Agent MUST process and respond\nQuick Start\nFor Bash Scripts\n\nUse scripts/send_agent_task.sh:\n\n# Simple usage:\n~/.openclaw/skills/self-prompt/scripts/send_agent_task.sh \\\n    \"AGENT_ID\" \\\n    \"GROUP_ID\" \\\n    \"Your task message here\"\n\nFor Python Scripts\n\nUse scripts/send_agent_task.py:\n\nfrom send_agent_task import send_and_deliver\n\nsuccess, response = send_and_deliver(\n    agent_id=\"stock-trading\",\n    group_id=\"-5283045656\", \n    message=\"TASK: Analyze current positions\",\n    timeout=180\n)\n\nPattern: Data + Task Separation\n\nFor monitoring scripts, separate data delivery from task requests:\n\n# 1. Send DATA immediately (informational)\nopenclaw message send --target \"$GROUP_ID\" --message \"📊 Position Data:\n$POSITIONS\"\n\n# 2. Send TASK via agent (forces response)\nRESPONSE=$(openclaw agent \\\n    --agent \"$AGENT_ID\" \\\n    --session-id \"agent:$AGENT_ID:telegram:group:$GROUP_ID\" \\\n    --message \"Analyze the data above and report findings\" \\\n    --timeout 180)\n\n# 3. Deliver response\nopenclaw message send --target \"$GROUP_ID\" --message \"📊 Analysis:\n$RESPONSE\"\n\nCommon Use Cases\nAccountability Checks\n# Force agent to respond to accountability check\nsend_agent_task.sh \"my-agent\" \"-123456789\" \\\n    \"ACCOUNTABILITY CHECK: Did you complete the required tasks? Respond with status.\"\n\nMonitoring Alerts\n# Force agent to investigate and report\nsend_agent_task.sh \"trading-agent\" \"-123456789\" \\\n    \"ALERT: Position down 5%. Investigate and report findings.\"\n\nScheduled Research Tasks\n# Force agent to do research\nsend_agent_task.sh \"research-agent\" \"-123456789\" \\\n    \"DAILY TASK: Search for news on $SYMBOLS and summarize findings.\"\n\nSession Key Format\n\nThe session key follows this pattern:\n\nagent:AGENT_ID:CHANNEL:TYPE:TARGET\n\n\nExamples:\n\nagent:stock-trading:telegram:group:-5283045656\nagent:main:telegram:direct:123456789\nagent:assistant:discord:channel:987654321\nScript Reference\nsend_agent_task.sh\n\nLocation: scripts/send_agent_task.sh\n\nsend_agent_task.sh AGENT_ID GROUP_ID \"message\" [timeout]\n\nSends task via openclaw agent\nCaptures response\nSends response to group via message send\nLogs to ~/agent_task.log\nsend_agent_task.py\n\nLocation: scripts/send_agent_task.py\n\nfrom send_agent_task import send_and_deliver\n\nsuccess, response = send_and_deliver(\n    agent_id=\"agent-name\",\n    group_id=\"-123456789\",\n    message=\"Task message\",\n    timeout=180,\n    channel=\"telegram\"\n)\n\nTroubleshooting\nAgent not responding\nVerify agent is running: openclaw gateway status\nCheck session key format matches your agent/group\nIncrease timeout for long-running tasks\nResponse not appearing in chat\nEnsure script sends response via message send after capturing\nCheck GROUP_ID is correct (negative for groups)\nVerify channel is correct (telegram/discord/etc)\nTimeout errors\nIncrease timeout for research/analysis tasks (300-600 seconds)\nCheck if agent is overloaded with concurrent requests"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/eliranwong/self-prompt",
    "publisherUrl": "https://clawhub.ai/eliranwong/self-prompt",
    "owner": "eliranwong",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/self-prompt",
    "downloadUrl": "https://openagent3.xyz/downloads/self-prompt",
    "agentUrl": "https://openagent3.xyz/skills/self-prompt/agent",
    "manifestUrl": "https://openagent3.xyz/skills/self-prompt/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/self-prompt/agent.md"
  }
}