{
  "schemaVersion": "1.0",
  "item": {
    "slug": "error-guard",
    "name": "Error Guard — Control‑Plane Safety",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/Amar1432/error-guard",
    "canonicalUrl": "https://clawhub.ai/Amar1432/error-guard",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/error-guard",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=error-guard",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "benchmark-worker.ts",
      "state.ts",
      "worker-events.ts",
      "heartbeat.ts",
      "spawn.ts",
      "control.ts"
    ],
    "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": "error-guard",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T00:28:48.293Z",
      "expiresAt": "2026-05-07T00:28:48.293Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=error-guard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=error-guard",
        "contentDisposition": "attachment; filename=\"error-guard-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "error-guard"
      },
      "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/error-guard"
    },
    "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/error-guard",
    "agentPageUrl": "https://openagent3.xyz/skills/error-guard/agent",
    "manifestUrl": "https://openagent3.xyz/skills/error-guard/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/error-guard/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": "error-guard",
        "body": "⚠️ System‑level skill (Advanced users)\n\nThis skill defines the control‑plane safety primitives for OpenClaw.\nIt is intentionally minimal, non‑blocking, and designed to prevent agent freezes, deadlocks, and unrecoverable states when running long‑lived or high‑risk workloads."
      },
      {
        "title": "Design Principles",
        "body": "Warning: This skill operates at the agent control‑plane level.\nIt should be installed only by users who understand OpenClaw’s execution model and are running workloads that can block, hang, or run for extended periods.\n\nMain agent never blocks: no long exec, no external I/O, no LLM calls.\nEvent-driven: workers emit events; the control plane listens.\nFail-safe first: recovery commands must always respond.\nMinimal state: track only task metadata (never payloads)."
      },
      {
        "title": "/status",
        "body": "Report current system health and task registry state.\n\nReturns:\n\nActive tasks (taskId, type, state)\nStart time and last heartbeat\nFlags for stalled or overdue tasks\n\nConstraints:\n\nMust run in constant time\nMust not call any model or external API"
      },
      {
        "title": "/flush",
        "body": "Emergency stop.\n\nImmediately:\n\nCancel all active tasks\nKill active exec/process sessions\nClear pending message queue\nReset in-memory task registry\n\nConstraints:\n\nMust always respond\nNo waiting on workers\nNo model calls"
      },
      {
        "title": "/recover",
        "body": "Safe recovery sequence.\n\nSteps:\n\nExecute /flush\nReset control-plane state\nOptionally reload skills/state (no container restart)"
      },
      {
        "title": "Future Extensions (Not Implemented Yet)",
        "body": "Sub-agent runner helper (event-driven)\nTask watchdogs with TTL and silence detection\nStructured event protocol (task.started, task.heartbeat, task.completed, ...)\nBack-pressure and task classes (interactive / batch / background)"
      },
      {
        "title": "Security & Privacy",
        "body": "This skill does not store payloads, prompts, messages, or model outputs\nOnly minimal task metadata is persisted (taskId, timestamps, state)\nNo API keys, credentials, or user data are read or written\nSafe to publish and share publicly"
      },
      {
        "title": "Non-Goals",
        "body": "No business logic\nNo background polling loops\nNo user-facing features\nNo LLM reasoning paths\n\nThis skill is the last line of defense. Keep it small, fast, and reliable."
      }
    ],
    "body": "error-guard\n\n⚠️ System‑level skill (Advanced users)\n\nThis skill defines the control‑plane safety primitives for OpenClaw. It is intentionally minimal, non‑blocking, and designed to prevent agent freezes, deadlocks, and unrecoverable states when running long‑lived or high‑risk workloads.\n\nDesign Principles\n\nWarning: This skill operates at the agent control‑plane level. It should be installed only by users who understand OpenClaw’s execution model and are running workloads that can block, hang, or run for extended periods.\n\nMain agent never blocks: no long exec, no external I/O, no LLM calls.\nEvent-driven: workers emit events; the control plane listens.\nFail-safe first: recovery commands must always respond.\nMinimal state: track only task metadata (never payloads).\nCommand Surface (Phase 1)\n/status\n\nReport current system health and task registry state.\n\nReturns:\n\nActive tasks (taskId, type, state)\nStart time and last heartbeat\nFlags for stalled or overdue tasks\n\nConstraints:\n\nMust run in constant time\nMust not call any model or external API\n/flush\n\nEmergency stop.\n\nImmediately:\n\nCancel all active tasks\nKill active exec/process sessions\nClear pending message queue\nReset in-memory task registry\n\nConstraints:\n\nMust always respond\nNo waiting on workers\nNo model calls\n/recover\n\nSafe recovery sequence.\n\nSteps:\n\nExecute /flush\nReset control-plane state\nOptionally reload skills/state (no container restart)\nFuture Extensions (Not Implemented Yet)\nSub-agent runner helper (event-driven)\nTask watchdogs with TTL and silence detection\nStructured event protocol (task.started, task.heartbeat, task.completed, ...)\nBack-pressure and task classes (interactive / batch / background)\nSecurity & Privacy\nThis skill does not store payloads, prompts, messages, or model outputs\nOnly minimal task metadata is persisted (taskId, timestamps, state)\nNo API keys, credentials, or user data are read or written\nSafe to publish and share publicly\nNon-Goals\nNo business logic\nNo background polling loops\nNo user-facing features\nNo LLM reasoning paths\n\nThis skill is the last line of defense. Keep it small, fast, and reliable."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Amar1432/error-guard",
    "publisherUrl": "https://clawhub.ai/Amar1432/error-guard",
    "owner": "Amar1432",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/error-guard",
    "downloadUrl": "https://openagent3.xyz/downloads/error-guard",
    "agentUrl": "https://openagent3.xyz/skills/error-guard/agent",
    "manifestUrl": "https://openagent3.xyz/skills/error-guard/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/error-guard/agent.md"
  }
}