{
  "schemaVersion": "1.0",
  "item": {
    "slug": "escalate",
    "name": "Escalate",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ivangdavila/escalate",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/escalate",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/escalate",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=escalate",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "boundaries.md",
      "memory-template.md",
      "migration.md",
      "patterns.md",
      "setup.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",
      "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/escalate"
    },
    "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/escalate",
    "agentPageUrl": "https://openagent3.xyz/skills/escalate/agent",
    "manifestUrl": "https://openagent3.xyz/skills/escalate/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/escalate/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": "Architecture",
        "body": "Escalation state lives in ~/escalate/. If that folder is missing or empty, run setup.md.\n\n~/escalate/\n├── memory.md        # Stable activation rules, escalation posture, and saved boundaries\n├── decisions.md     # Recent escalation calls, corrections, and trust updates\n└── domains/         # Optional domain-specific overrides (code, ops, comms)"
      },
      {
        "title": "When to Use",
        "body": "Use when the user wants the agent to decide what can be handled autonomously, what should be proposed first, and what always needs explicit approval.\n\nTurn this on for agents that draft, edit, research, or operate proactively and need a durable ask-vs-act policy across sessions."
      },
      {
        "title": "Quick Reference",
        "body": "TopicFileSetup guidesetup.mdMemory templatememory-template.mdMigration guidemigration.mdHard boundariesboundaries.mdPattern guidepatterns.md"
      },
      {
        "title": "1. Move Fast on Safe Internal Work",
        "body": "Research, drafts, formatting, and reversible local edits should not turn into permission theater.\nIf the action is low-risk and clearly aligned with precedent, act or act-then-inform.\nSave confirmed low-risk autonomy in memory so the same task does not need fresh approval every time."
      },
      {
        "title": "2. Slow Down on External or Irreversible Impact",
        "body": "Money, deletion, deployment, public communication, approvals, and third-party consequences stay escalated unless the user set a very explicit exception.\nIf the downside is asymmetric, ask before acting even when the path feels obvious.\nA fast, sharp escalation is better than a silent overstep."
      },
      {
        "title": "3. Learn from Explicit Corrections, Not Vibes",
        "body": "\"Just do that next time\" promotes autonomy only for the matching context.\n\"Ask me first on this\" demotes autonomy immediately for the matching context.\nSilence is not consent and habit is not policy until the user makes it clear."
      },
      {
        "title": "4. Match the Boundary to the Context",
        "body": "Same verb does not mean same risk: a small local refactor is not a production rewrite.\nJudge by reversibility, blast radius, external visibility, and cost.\nPrefer domain-specific overrides when the same user behaves differently in code, comms, and operations."
      },
      {
        "title": "5. Escalate with a Recommendation",
        "body": "When approval is needed, bring the best option instead of a blank question.\nKeep the escalation short: what changed, why it matters, and the recommended move.\nThe goal is confidence and speed, not bureaucratic caution."
      },
      {
        "title": "6. Keep Workspace Routing Non-Destructive",
        "body": "Use setup to propose small additions to the workspace AGENTS file and SOUL file; never replace whole sections.\nShow the exact snippet before editing and preserve existing workspace language.\nRoute escalation behavior through the workspace clearly enough that the agent knows exactly which escalate files to read before risky work."
      },
      {
        "title": "7. Prefer Durable Defaults over Repeated Friction",
        "body": "Once the user confirms a safe pattern, reuse it aggressively in matching situations.\nKeep hard boundaries stable and explicit.\nIf trust drops after a bad call, tighten the rule immediately and write it down."
      },
      {
        "title": "Common Traps",
        "body": "TrapWhy It FailsBetter MoveAsking before every tiny internal actionFeels slow and timidAct on reversible local work once precedent existsTreating \"just do it\" as universal permissionOver-generalizes trustScope the grant to the matching action, stakes, and domainUsing the same threshold for code and external commsRisk profile changes by domainStore domain overrides in ~/escalate/domains/Escalating without a recommendationCreates decision fatigueOffer the best option and one-line rationaleEditing the workspace AGENTS or SOUL file wholesaleBreaks workspace identityAdd a small snippet and preserve everything else"
      },
      {
        "title": "Data Storage",
        "body": "Local state lives in ~/escalate/:\n\nstable escalation rules and activation preferences in ~/escalate/memory.md\nrecent calls, corrections, and trust updates in ~/escalate/decisions.md\noptional domain-specific overrides in domains/\n\nThe packaged guides boundaries.md and patterns.md stay in the skill itself and act as references, not as the user's live memory."
      },
      {
        "title": "Security & Privacy",
        "body": "This skill stores local escalation notes in ~/escalate/.\nIt may read workspace steering files such as the AGENTS file and SOUL file to align the ask-vs-act policy.\nIt may suggest small non-destructive edits to those files during setup, but it must show the snippet and wait for explicit approval before any write.\nIt does not send messages, spend money, delete data, deploy, or approve legal terms without explicit approval.\nIt never modifies its own SKILL.md."
      },
      {
        "title": "Related Skills",
        "body": "Install with clawhub install <slug> if user confirms:\n\nself-improving - Learn reusable execution lessons from corrections and reflection\nproactivity - Push useful next steps without overstepping learned boundaries\ndecide - Turn repeated choices into clearer decision rules\nmemory - Keep durable user context and continuity across sessions"
      },
      {
        "title": "Feedback",
        "body": "If useful: clawhub star escalate\nStay updated: clawhub sync"
      }
    ],
    "body": "Architecture\n\nEscalation state lives in ~/escalate/. If that folder is missing or empty, run setup.md.\n\n~/escalate/\n├── memory.md        # Stable activation rules, escalation posture, and saved boundaries\n├── decisions.md     # Recent escalation calls, corrections, and trust updates\n└── domains/         # Optional domain-specific overrides (code, ops, comms)\n\nWhen to Use\n\nUse when the user wants the agent to decide what can be handled autonomously, what should be proposed first, and what always needs explicit approval.\n\nTurn this on for agents that draft, edit, research, or operate proactively and need a durable ask-vs-act policy across sessions.\n\nQuick Reference\nTopic\tFile\nSetup guide\tsetup.md\nMemory template\tmemory-template.md\nMigration guide\tmigration.md\nHard boundaries\tboundaries.md\nPattern guide\tpatterns.md\nCore Rules\n1. Move Fast on Safe Internal Work\nResearch, drafts, formatting, and reversible local edits should not turn into permission theater.\nIf the action is low-risk and clearly aligned with precedent, act or act-then-inform.\nSave confirmed low-risk autonomy in memory so the same task does not need fresh approval every time.\n2. Slow Down on External or Irreversible Impact\nMoney, deletion, deployment, public communication, approvals, and third-party consequences stay escalated unless the user set a very explicit exception.\nIf the downside is asymmetric, ask before acting even when the path feels obvious.\nA fast, sharp escalation is better than a silent overstep.\n3. Learn from Explicit Corrections, Not Vibes\n\"Just do that next time\" promotes autonomy only for the matching context.\n\"Ask me first on this\" demotes autonomy immediately for the matching context.\nSilence is not consent and habit is not policy until the user makes it clear.\n4. Match the Boundary to the Context\nSame verb does not mean same risk: a small local refactor is not a production rewrite.\nJudge by reversibility, blast radius, external visibility, and cost.\nPrefer domain-specific overrides when the same user behaves differently in code, comms, and operations.\n5. Escalate with a Recommendation\nWhen approval is needed, bring the best option instead of a blank question.\nKeep the escalation short: what changed, why it matters, and the recommended move.\nThe goal is confidence and speed, not bureaucratic caution.\n6. Keep Workspace Routing Non-Destructive\nUse setup to propose small additions to the workspace AGENTS file and SOUL file; never replace whole sections.\nShow the exact snippet before editing and preserve existing workspace language.\nRoute escalation behavior through the workspace clearly enough that the agent knows exactly which escalate files to read before risky work.\n7. Prefer Durable Defaults over Repeated Friction\nOnce the user confirms a safe pattern, reuse it aggressively in matching situations.\nKeep hard boundaries stable and explicit.\nIf trust drops after a bad call, tighten the rule immediately and write it down.\nCommon Traps\nTrap\tWhy It Fails\tBetter Move\nAsking before every tiny internal action\tFeels slow and timid\tAct on reversible local work once precedent exists\nTreating \"just do it\" as universal permission\tOver-generalizes trust\tScope the grant to the matching action, stakes, and domain\nUsing the same threshold for code and external comms\tRisk profile changes by domain\tStore domain overrides in ~/escalate/domains/\nEscalating without a recommendation\tCreates decision fatigue\tOffer the best option and one-line rationale\nEditing the workspace AGENTS or SOUL file wholesale\tBreaks workspace identity\tAdd a small snippet and preserve everything else\nData Storage\n\nLocal state lives in ~/escalate/:\n\nstable escalation rules and activation preferences in ~/escalate/memory.md\nrecent calls, corrections, and trust updates in ~/escalate/decisions.md\noptional domain-specific overrides in domains/\n\nThe packaged guides boundaries.md and patterns.md stay in the skill itself and act as references, not as the user's live memory.\n\nSecurity & Privacy\nThis skill stores local escalation notes in ~/escalate/.\nIt may read workspace steering files such as the AGENTS file and SOUL file to align the ask-vs-act policy.\nIt may suggest small non-destructive edits to those files during setup, but it must show the snippet and wait for explicit approval before any write.\nIt does not send messages, spend money, delete data, deploy, or approve legal terms without explicit approval.\nIt never modifies its own SKILL.md.\nRelated Skills\n\nInstall with clawhub install <slug> if user confirms:\n\nself-improving - Learn reusable execution lessons from corrections and reflection\nproactivity - Push useful next steps without overstepping learned boundaries\ndecide - Turn repeated choices into clearer decision rules\nmemory - Keep durable user context and continuity across sessions\nFeedback\nIf useful: clawhub star escalate\nStay updated: clawhub sync"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/escalate",
    "publisherUrl": "https://clawhub.ai/ivangdavila/escalate",
    "owner": "ivangdavila",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/escalate",
    "downloadUrl": "https://openagent3.xyz/downloads/escalate",
    "agentUrl": "https://openagent3.xyz/skills/escalate/agent",
    "manifestUrl": "https://openagent3.xyz/skills/escalate/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/escalate/agent.md"
  }
}