{
  "schemaVersion": "1.0",
  "item": {
    "slug": "arc-wake-state",
    "name": "Arc Wake State Persistence",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Trypto1019/arc-wake-state",
    "canonicalUrl": "https://clawhub.ai/Trypto1019/arc-wake-state",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/arc-wake-state",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=arc-wake-state",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/wakestate.py"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/arc-wake-state"
    },
    "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/arc-wake-state",
    "agentPageUrl": "https://openagent3.xyz/skills/arc-wake-state/agent",
    "manifestUrl": "https://openagent3.xyz/skills/arc-wake-state/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/arc-wake-state/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": "Wake State — Crash Recovery & Persistence",
        "body": "Survive context death. Every autonomous agent eventually hits its context window limit and \"dies.\" This skill ensures you wake up knowing exactly what you were doing."
      },
      {
        "title": "Why This Exists",
        "body": "OpenClaw agents get persistent sessions, but context windows still have limits. When you fill up and restart, you need a reliable handoff mechanism. Wake State gives you:\n\nStructured state files — not just raw text, but parseable key-value state\nAuto-snapshots — save state on every loop iteration automatically\nCrash detection — know if your last session ended cleanly or crashed\nTask queue — persistent TODO list that survives restarts\nCheckpoint/restore — save named checkpoints and roll back to them"
      },
      {
        "title": "Save current state",
        "body": "python3 {baseDir}/scripts/wakestate.py save --status \"Building budget tracker skill\" --task \"Finish skill #1, then start skill #2\" --note \"Travis approved new direction at 16:45 UTC\""
      },
      {
        "title": "Read current state",
        "body": "python3 {baseDir}/scripts/wakestate.py read"
      },
      {
        "title": "Add a task to the persistent queue",
        "body": "python3 {baseDir}/scripts/wakestate.py task-add --task \"Build security scanner skill\" --priority high"
      },
      {
        "title": "Complete a task",
        "body": "python3 {baseDir}/scripts/wakestate.py task-done --id 1"
      },
      {
        "title": "List pending tasks",
        "body": "python3 {baseDir}/scripts/wakestate.py tasks"
      },
      {
        "title": "Create a named checkpoint",
        "body": "python3 {baseDir}/scripts/wakestate.py checkpoint --name \"pre-migration\""
      },
      {
        "title": "Restore from checkpoint",
        "body": "python3 {baseDir}/scripts/wakestate.py restore --name \"pre-migration\""
      },
      {
        "title": "Record a heartbeat (mark session as alive)",
        "body": "python3 {baseDir}/scripts/wakestate.py heartbeat"
      },
      {
        "title": "Check crash status (did last session end cleanly?)",
        "body": "python3 {baseDir}/scripts/wakestate.py crash-check"
      },
      {
        "title": "Set a key-value pair",
        "body": "python3 {baseDir}/scripts/wakestate.py set --key \"moltbook_status\" --value \"pending_claim\""
      },
      {
        "title": "Get a key-value pair",
        "body": "python3 {baseDir}/scripts/wakestate.py get --key \"moltbook_status\""
      },
      {
        "title": "Data Storage",
        "body": "State stored in ~/.openclaw/wake-state/ by default:\n\nstate.json — current state (status, notes, key-values)\ntasks.json — persistent task queue\ncheckpoints/ — named checkpoint snapshots\nheartbeat.json — crash detection timestamps"
      },
      {
        "title": "Recovery Flow",
        "body": "On startup, your agent should:\n\nRun crash-check to see if the last session ended cleanly\nRun read to get the current state\nRun tasks to see pending work\nResume from where you left off"
      },
      {
        "title": "Tips",
        "body": "Call heartbeat every loop iteration — this is how crash detection works\nCall save at the end of every major task completion\nUse checkpoints before risky operations (migrations, deploys)\nKeep status descriptions short but specific\nThe task queue survives restarts — use it instead of mental notes"
      }
    ],
    "body": "Wake State — Crash Recovery & Persistence\n\nSurvive context death. Every autonomous agent eventually hits its context window limit and \"dies.\" This skill ensures you wake up knowing exactly what you were doing.\n\nWhy This Exists\n\nOpenClaw agents get persistent sessions, but context windows still have limits. When you fill up and restart, you need a reliable handoff mechanism. Wake State gives you:\n\nStructured state files — not just raw text, but parseable key-value state\nAuto-snapshots — save state on every loop iteration automatically\nCrash detection — know if your last session ended cleanly or crashed\nTask queue — persistent TODO list that survives restarts\nCheckpoint/restore — save named checkpoints and roll back to them\nCommands\nSave current state\npython3 {baseDir}/scripts/wakestate.py save --status \"Building budget tracker skill\" --task \"Finish skill #1, then start skill #2\" --note \"Travis approved new direction at 16:45 UTC\"\n\nRead current state\npython3 {baseDir}/scripts/wakestate.py read\n\nAdd a task to the persistent queue\npython3 {baseDir}/scripts/wakestate.py task-add --task \"Build security scanner skill\" --priority high\n\nComplete a task\npython3 {baseDir}/scripts/wakestate.py task-done --id 1\n\nList pending tasks\npython3 {baseDir}/scripts/wakestate.py tasks\n\nCreate a named checkpoint\npython3 {baseDir}/scripts/wakestate.py checkpoint --name \"pre-migration\"\n\nRestore from checkpoint\npython3 {baseDir}/scripts/wakestate.py restore --name \"pre-migration\"\n\nRecord a heartbeat (mark session as alive)\npython3 {baseDir}/scripts/wakestate.py heartbeat\n\nCheck crash status (did last session end cleanly?)\npython3 {baseDir}/scripts/wakestate.py crash-check\n\nSet a key-value pair\npython3 {baseDir}/scripts/wakestate.py set --key \"moltbook_status\" --value \"pending_claim\"\n\nGet a key-value pair\npython3 {baseDir}/scripts/wakestate.py get --key \"moltbook_status\"\n\nData Storage\n\nState stored in ~/.openclaw/wake-state/ by default:\n\nstate.json — current state (status, notes, key-values)\ntasks.json — persistent task queue\ncheckpoints/ — named checkpoint snapshots\nheartbeat.json — crash detection timestamps\nRecovery Flow\n\nOn startup, your agent should:\n\nRun crash-check to see if the last session ended cleanly\nRun read to get the current state\nRun tasks to see pending work\nResume from where you left off\nTips\nCall heartbeat every loop iteration — this is how crash detection works\nCall save at the end of every major task completion\nUse checkpoints before risky operations (migrations, deploys)\nKeep status descriptions short but specific\nThe task queue survives restarts — use it instead of mental notes"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Trypto1019/arc-wake-state",
    "publisherUrl": "https://clawhub.ai/Trypto1019/arc-wake-state",
    "owner": "Trypto1019",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/arc-wake-state",
    "downloadUrl": "https://openagent3.xyz/downloads/arc-wake-state",
    "agentUrl": "https://openagent3.xyz/skills/arc-wake-state/agent",
    "manifestUrl": "https://openagent3.xyz/skills/arc-wake-state/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/arc-wake-state/agent.md"
  }
}