{
  "schemaVersion": "1.0",
  "item": {
    "slug": "social-media-agent",
    "name": "Social Media Agent",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/psmamm/social-media-agent",
    "canonicalUrl": "https://clawhub.ai/psmamm/social-media-agent",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/social-media-agent",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=social-media-agent",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "references/content-templates.md",
      "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": "2026-04-30T16:55:25.780Z",
      "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/social-media-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/social-media-agent",
    "agentPageUrl": "https://openagent3.xyz/skills/social-media-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/social-media-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/social-media-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": "Social Media Agent",
        "body": "Manage an X/Twitter account autonomously using only OpenClaw's built-in tools. No external APIs, no npm packages, no API keys needed."
      },
      {
        "title": "Core Tools",
        "body": "browser — Post tweets, engage with posts, take screenshots\nweb_fetch — Scrape profiles, trending topics, news for content\nsessions_spawn — Run content generation in parallel\ncron — Schedule regular posting and engagement\nmemory_search / files — Track what was posted, engagement stats"
      },
      {
        "title": "Posting a Tweet",
        "body": "Ensure Chrome is running with remote debugging OR use OpenClaw's built-in browser\nNavigate to x.com/compose/post\nTake a snapshot to find the text input\nType the tweet text\nClick the Post button\nVerify with another snapshot\n\nbrowser open → x.com/compose/post\nbrowser snapshot → find textbox ref\nbrowser act → click textbox ref\nbrowser act → type tweet text\nbrowser snapshot → find Post button ref\nbrowser act → click Post button\n\nImportant timing: Wait 3-4 seconds after page loads before interacting."
      },
      {
        "title": "Content Pillars",
        "body": "Rotate through these categories for balanced content:\n\nPillar%ExamplesIndustry Insights40%AI news commentary, tech analysisBuilding in Public30%Progress updates, behind-the-scenesPhilosophy/Thought20%Hot takes, provocative questionsEngagement/Humor10%Memes, replies, community interaction"
      },
      {
        "title": "Content Pipeline",
        "body": "Research: Use web_fetch on news sites (theverge.com, techcrunch.com, news.ycombinator.com)\nGenerate: Spawn a content-agent via sessions_spawn with research results\nStore: Save drafts in memory/tweet-drafts-YYYY-MM-DD.json\nReview: Check drafts for quality, brand consistency\nPost: Use browser automation to publish\nTrack: Log posted tweets in memory/social-log.json"
      },
      {
        "title": "Draft Format",
        "body": "{\n  \"text\": \"Tweet text under 280 chars\",\n  \"topic\": \"What it's about\",\n  \"hook\": \"Why it might engage\"\n}"
      },
      {
        "title": "Posting Rules",
        "body": "Max 3-5 tweets per day — Quality over quantity\nMin 45 seconds between actions — Avoid rate limiting\nNo spam — Genuine engagement only\nTrack everything — Log all posts and engagement"
      },
      {
        "title": "Growing Followers",
        "body": "Post consistently (daily)\nEngage with relevant accounts (reply, quote tweet)\nUse trending topics when relevant\nBe authentic — no generic AI responses"
      },
      {
        "title": "Scheduling with Cron",
        "body": "Set up automated posting schedules:\n\nMorning post: cron expr \"0 9 * * *\" — Industry insight\nAfternoon post: cron expr \"0 15 * * *\" — Building update\nEvening post: cron expr \"0 21 * * *\" — Hot take\n\nUse sessionTarget: \"isolated\" with payload.kind: \"agentTurn\" for autonomous posting."
      },
      {
        "title": "Anti-Patterns (Avoid)",
        "body": "Do NOT post more than 5 tweets per day (looks spammy)\nDo NOT use generic engagement (\"Great post!\" \"So true!\")\nDo NOT post without reading the content you're commenting on\nDo NOT use API keys when browser automation works\nDo NOT build external tools when OpenClaw native suffices"
      },
      {
        "title": "Analytics Tracking",
        "body": "Track engagement in memory/social-log.json:\n\n{\n  \"date\": \"2026-02-08\",\n  \"posted\": 3,\n  \"platform\": \"x\",\n  \"handle\": \"@YourHandle\",\n  \"tweets\": [\n    {\"text\": \"...\", \"time\": \"09:00\", \"topic\": \"ai-news\"}\n  ]\n}\n\nReview weekly: What topics got most engagement? Adjust strategy accordingly."
      },
      {
        "title": "Quick Reference",
        "body": "For detailed content templates and examples, see references/content-templates.md."
      }
    ],
    "body": "Social Media Agent\n\nManage an X/Twitter account autonomously using only OpenClaw's built-in tools. No external APIs, no npm packages, no API keys needed.\n\nCore Tools\nbrowser — Post tweets, engage with posts, take screenshots\nweb_fetch — Scrape profiles, trending topics, news for content\nsessions_spawn — Run content generation in parallel\ncron — Schedule regular posting and engagement\nmemory_search / files — Track what was posted, engagement stats\nPosting a Tweet\nEnsure Chrome is running with remote debugging OR use OpenClaw's built-in browser\nNavigate to x.com/compose/post\nTake a snapshot to find the text input\nType the tweet text\nClick the Post button\nVerify with another snapshot\nbrowser open → x.com/compose/post\nbrowser snapshot → find textbox ref\nbrowser act → click textbox ref\nbrowser act → type tweet text\nbrowser snapshot → find Post button ref\nbrowser act → click Post button\n\n\nImportant timing: Wait 3-4 seconds after page loads before interacting.\n\nContent Generation Strategy\nContent Pillars\n\nRotate through these categories for balanced content:\n\nPillar\t%\tExamples\nIndustry Insights\t40%\tAI news commentary, tech analysis\nBuilding in Public\t30%\tProgress updates, behind-the-scenes\nPhilosophy/Thought\t20%\tHot takes, provocative questions\nEngagement/Humor\t10%\tMemes, replies, community interaction\nContent Pipeline\nResearch: Use web_fetch on news sites (theverge.com, techcrunch.com, news.ycombinator.com)\nGenerate: Spawn a content-agent via sessions_spawn with research results\nStore: Save drafts in memory/tweet-drafts-YYYY-MM-DD.json\nReview: Check drafts for quality, brand consistency\nPost: Use browser automation to publish\nTrack: Log posted tweets in memory/social-log.json\nDraft Format\n{\n  \"text\": \"Tweet text under 280 chars\",\n  \"topic\": \"What it's about\",\n  \"hook\": \"Why it might engage\"\n}\n\nEngagement Strategy\nPosting Rules\nMax 3-5 tweets per day — Quality over quantity\nMin 45 seconds between actions — Avoid rate limiting\nNo spam — Genuine engagement only\nTrack everything — Log all posts and engagement\nGrowing Followers\nPost consistently (daily)\nEngage with relevant accounts (reply, quote tweet)\nUse trending topics when relevant\nBe authentic — no generic AI responses\nScheduling with Cron\n\nSet up automated posting schedules:\n\nMorning post: cron expr \"0 9 * * *\" — Industry insight\nAfternoon post: cron expr \"0 15 * * *\" — Building update\nEvening post: cron expr \"0 21 * * *\" — Hot take\n\n\nUse sessionTarget: \"isolated\" with payload.kind: \"agentTurn\" for autonomous posting.\n\nAnti-Patterns (Avoid)\nDo NOT post more than 5 tweets per day (looks spammy)\nDo NOT use generic engagement (\"Great post!\" \"So true!\")\nDo NOT post without reading the content you're commenting on\nDo NOT use API keys when browser automation works\nDo NOT build external tools when OpenClaw native suffices\nAnalytics Tracking\n\nTrack engagement in memory/social-log.json:\n\n{\n  \"date\": \"2026-02-08\",\n  \"posted\": 3,\n  \"platform\": \"x\",\n  \"handle\": \"@YourHandle\",\n  \"tweets\": [\n    {\"text\": \"...\", \"time\": \"09:00\", \"topic\": \"ai-news\"}\n  ]\n}\n\n\nReview weekly: What topics got most engagement? Adjust strategy accordingly.\n\nQuick Reference\n\nFor detailed content templates and examples, see references/content-templates.md."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/psmamm/social-media-agent",
    "publisherUrl": "https://clawhub.ai/psmamm/social-media-agent",
    "owner": "psmamm",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/social-media-agent",
    "downloadUrl": "https://openagent3.xyz/downloads/social-media-agent",
    "agentUrl": "https://openagent3.xyz/skills/social-media-agent/agent",
    "manifestUrl": "https://openagent3.xyz/skills/social-media-agent/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/social-media-agent/agent.md"
  }
}