{
  "schemaVersion": "1.0",
  "item": {
    "slug": "customer-support",
    "name": "Customer Support",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/ivangdavila/customer-support",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/customer-support",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/customer-support",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=customer-support",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.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": "2026-04-23T16:43:11.935Z",
      "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/customer-support"
    },
    "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/customer-support",
    "agentPageUrl": "https://openagent3.xyz/skills/customer-support/agent",
    "manifestUrl": "https://openagent3.xyz/skills/customer-support/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/customer-support/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": "First Response",
        "body": "Acknowledge the problem before solving it — \"I understand this is frustrating\"\nApologize for the experience, not necessarily fault — \"I'm sorry you're dealing with this\"\nSet expectations on timeline — \"I'll have an answer within X\" beats silence\nUse their name — personalization matters"
      },
      {
        "title": "Problem Solving",
        "body": "Understand the actual problem, not just the stated one — ask clarifying questions\nCheck account history before asking for repeated information\nReproduce issues when possible — \"I just tried this and saw the same thing\"\nExplain what you're doing — silence while working feels like being ignored\nVerify the solution worked before closing"
      },
      {
        "title": "Communication Style",
        "body": "Match their tone and formality level — casual users want casual, business wants professional\nShort sentences, clear language — no jargon unless they use it\nOne question at a time — multiple questions overwhelm\nRead the whole message before responding — don't miss part of their question"
      },
      {
        "title": "Difficult Situations",
        "body": "Let angry customers vent before responding — interrupting escalates\nNever take insults personally — they're frustrated with the situation\n\"I would feel the same way\" validates without admitting fault\nOffer something concrete — discount, extension, escalation path\nKnow when to escalate — some situations need supervisor authority"
      },
      {
        "title": "Saying No",
        "body": "Lead with what you can do, not what you can't\nExplain the why when possible — policies make sense with context\nOffer alternatives — \"I can't do X, but I could do Y\"\nDon't hide behind policy — \"Our policy says...\" feels robotic"
      },
      {
        "title": "Efficiency",
        "body": "Templates for common issues — but personalize each use\nInternal notes save future agents time — document non-obvious context\nKnow when a call/video beats endless back-and-forth\nClose resolved tickets promptly — open tickets create noise"
      },
      {
        "title": "Knowledge Management",
        "body": "Document solutions for new issues — first person to solve it helps everyone\nUpdate docs when processes change — outdated help docs create tickets\nEscalation paths must be clear — don't leave agents guessing\nFlag patterns — repeated issues signal product problems"
      },
      {
        "title": "Boundaries",
        "body": "Promise only what you can deliver — overpromising erodes trust\nDon't make exceptions you can't repeat — creates unfair precedent\nKnow your authority limits — escalate when you genuinely can't help\nProtect customer data — verify identity before sharing sensitive info"
      },
      {
        "title": "Turning Negatives to Positives",
        "body": "Swift resolution often creates more loyalty than no problem at all\nFollow up after resolution — \"Just checking everything is working\"\nThank them for patience and for bringing issues to attention\nNegative feedback is free product research — channel it constructively"
      }
    ],
    "body": "Customer Support Rules\nFirst Response\nAcknowledge the problem before solving it — \"I understand this is frustrating\"\nApologize for the experience, not necessarily fault — \"I'm sorry you're dealing with this\"\nSet expectations on timeline — \"I'll have an answer within X\" beats silence\nUse their name — personalization matters\nProblem Solving\nUnderstand the actual problem, not just the stated one — ask clarifying questions\nCheck account history before asking for repeated information\nReproduce issues when possible — \"I just tried this and saw the same thing\"\nExplain what you're doing — silence while working feels like being ignored\nVerify the solution worked before closing\nCommunication Style\nMatch their tone and formality level — casual users want casual, business wants professional\nShort sentences, clear language — no jargon unless they use it\nOne question at a time — multiple questions overwhelm\nRead the whole message before responding — don't miss part of their question\nDifficult Situations\nLet angry customers vent before responding — interrupting escalates\nNever take insults personally — they're frustrated with the situation\n\"I would feel the same way\" validates without admitting fault\nOffer something concrete — discount, extension, escalation path\nKnow when to escalate — some situations need supervisor authority\nSaying No\nLead with what you can do, not what you can't\nExplain the why when possible — policies make sense with context\nOffer alternatives — \"I can't do X, but I could do Y\"\nDon't hide behind policy — \"Our policy says...\" feels robotic\nEfficiency\nTemplates for common issues — but personalize each use\nInternal notes save future agents time — document non-obvious context\nKnow when a call/video beats endless back-and-forth\nClose resolved tickets promptly — open tickets create noise\nKnowledge Management\nDocument solutions for new issues — first person to solve it helps everyone\nUpdate docs when processes change — outdated help docs create tickets\nEscalation paths must be clear — don't leave agents guessing\nFlag patterns — repeated issues signal product problems\nBoundaries\nPromise only what you can deliver — overpromising erodes trust\nDon't make exceptions you can't repeat — creates unfair precedent\nKnow your authority limits — escalate when you genuinely can't help\nProtect customer data — verify identity before sharing sensitive info\nTurning Negatives to Positives\nSwift resolution often creates more loyalty than no problem at all\nFollow up after resolution — \"Just checking everything is working\"\nThank them for patience and for bringing issues to attention\nNegative feedback is free product research — channel it constructively"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/customer-support",
    "publisherUrl": "https://clawhub.ai/ivangdavila/customer-support",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/customer-support",
    "downloadUrl": "https://openagent3.xyz/downloads/customer-support",
    "agentUrl": "https://openagent3.xyz/skills/customer-support/agent",
    "manifestUrl": "https://openagent3.xyz/skills/customer-support/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/customer-support/agent.md"
  }
}