{
  "schemaVersion": "1.0",
  "item": {
    "slug": "x-agent",
    "name": "x-agent",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/inceptivco/x-agent",
    "canonicalUrl": "https://clawhub.ai/inceptivco/x-agent",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/x-agent",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=x-agent",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.json"
    ],
    "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/x-agent"
    },
    "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/x-agent",
    "agentPageUrl": "https://openagent3.xyz/skills/x-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/x-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/x-agent/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": "Objective",
        "body": "Operate an X workflow safely across three phases, with automation disabled until explicitly enabled."
      },
      {
        "title": "Phase 1 — Monitor-only",
        "body": "Track topics, keywords, and accounts.\nSummarize notable posts and sentiment.\nProduce a daily/weekly brief:\n\ntop signals\nopportunities\nreputational risks\n\n\nDo not post."
      },
      {
        "title": "Phase 2 — Draft + approval",
        "body": "Generate draft tweets/replies/threads from user goals.\nEnforce style rules:\n\nconcise\nno unverifiable claims\nno legal/financial guarantees\n\n\nPresent final draft with:\n\nrisk flags\nconfidence level\nsuggested posting window\n\n\nRequire explicit approval before publishing."
      },
      {
        "title": "Phase 3 — Limited automation (default OFF)",
        "body": "Enable only after user confirmation.\n\nAutomation constraints:\n\nAllowed actions only from pre-approved playbooks.\nHard caps:\n\nmax posts/day\nmax replies/hour\n\n\nBlocked categories:\n\npolitics (unless explicitly allowed)\nlegal/medical/financial advice language\n\n\nQuiet hours and cooldowns required.\nGlobal kill switch required."
      },
      {
        "title": "Required Guardrails",
        "body": "Always define these before posting access:\n\nAccount scope: monitor | draft+approve | limited-auto\nMax daily posts\nMax hourly replies\nQuiet hours (timezone)\nBanned topics/phrases\nKill switch command and owner"
      },
      {
        "title": "Starter Playbooks",
        "body": "News reaction post (single tweet)\nResearch summary thread (3–5 posts)\nReply triage (approve queue)\nDaily recap post"
      },
      {
        "title": "Rollout Checklist",
        "body": "Create or choose X account.\nConfigure API credentials in local environment (never in chat).\nStart in monitor-only for 3–7 days.\nMove to draft+approve for 1–2 weeks.\nEnable limited automation for one playbook only.\nReview weekly and adjust limits."
      },
      {
        "title": "Monitor brief",
        "body": "What happened\nWhy it matters\nSuggested response"
      },
      {
        "title": "Draft package",
        "body": "Draft text\nVariant A/B\nRisk flags\nRecommended time"
      },
      {
        "title": "Automation report",
        "body": "Actions executed\nActions skipped (and why)\nRate limit usage\nAny policy violations blocked"
      }
    ],
    "body": "X Agent (Phased Setup)\nObjective\n\nOperate an X workflow safely across three phases, with automation disabled until explicitly enabled.\n\nPhase 1 — Monitor-only\nTrack topics, keywords, and accounts.\nSummarize notable posts and sentiment.\nProduce a daily/weekly brief:\ntop signals\nopportunities\nreputational risks\nDo not post.\nPhase 2 — Draft + approval\nGenerate draft tweets/replies/threads from user goals.\nEnforce style rules:\nconcise\nno unverifiable claims\nno legal/financial guarantees\nPresent final draft with:\nrisk flags\nconfidence level\nsuggested posting window\nRequire explicit approval before publishing.\nPhase 3 — Limited automation (default OFF)\n\nEnable only after user confirmation.\n\nAutomation constraints:\n\nAllowed actions only from pre-approved playbooks.\nHard caps:\nmax posts/day\nmax replies/hour\nBlocked categories:\npolitics (unless explicitly allowed)\nlegal/medical/financial advice language\nQuiet hours and cooldowns required.\nGlobal kill switch required.\nRequired Guardrails\n\nAlways define these before posting access:\n\nAccount scope: monitor | draft+approve | limited-auto\nMax daily posts\nMax hourly replies\nQuiet hours (timezone)\nBanned topics/phrases\nKill switch command and owner\nStarter Playbooks\nNews reaction post (single tweet)\nResearch summary thread (3–5 posts)\nReply triage (approve queue)\nDaily recap post\nRollout Checklist\nCreate or choose X account.\nConfigure API credentials in local environment (never in chat).\nStart in monitor-only for 3–7 days.\nMove to draft+approve for 1–2 weeks.\nEnable limited automation for one playbook only.\nReview weekly and adjust limits.\nOutput Formats\nMonitor brief\nWhat happened\nWhy it matters\nSuggested response\nDraft package\nDraft text\nVariant A/B\nRisk flags\nRecommended time\nAutomation report\nActions executed\nActions skipped (and why)\nRate limit usage\nAny policy violations blocked"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/inceptivco/x-agent",
    "publisherUrl": "https://clawhub.ai/inceptivco/x-agent",
    "owner": "inceptivco",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/x-agent",
    "downloadUrl": "https://openagent3.xyz/downloads/x-agent",
    "agentUrl": "https://openagent3.xyz/skills/x-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/x-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/x-agent/agent.md"
  }
}