{
  "schemaVersion": "1.0",
  "item": {
    "slug": "social-reader",
    "name": "social-reader",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/HackSing/social-reader",
    "canonicalUrl": "https://clawhub.ai/HackSing/social-reader",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/social-reader",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=social-reader",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "archive.json",
      "drafts.json",
      "fetcher.py",
      "input_urls.txt",
      "notifier.py",
      "pending_tweets.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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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-reader"
    },
    "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-reader",
    "agentPageUrl": "https://openagent3.xyz/skills/social-reader/agent",
    "manifestUrl": "https://openagent3.xyz/skills/social-reader/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/social-reader/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 Reader Skill",
        "body": "This skill provides a social media content scraping and monitoring workflow. It offers two usage modes:\n\nInteractive Mode: Agent fetches a single post in real-time for reading, discussion, or reply generation within a conversation.\nPipeline Mode: Background batch patrol of sources, with LLM distillation and review notifications."
      },
      {
        "title": "Dependencies",
        "body": "pip install requests"
      },
      {
        "title": "Configuration Files",
        "body": "FilePurposeprompt.txtLLM system prompt for the Processor nodesources.jsonList of monitored accounts and fetch intervals (pipeline mode)input_urls.txtManually entered post URLs (one per line, # for comments)seen_ids.jsonDeduplication cache for seen post IDs (pipeline mode only)pending_tweets.jsonQueue of unprocessed posts from the Watcherdrafts.jsonLLM-distilled drafts from the Processorarchive.jsonArchived history records"
      },
      {
        "title": "Environment Variables (required only for Pipeline Mode Processor)",
        "body": "VariableDescriptionDefaultLLM_API_KEYLLM API key (required)NoneLLM_BASE_URLAPI endpointhttps://api.openai.com/v1LLM_MODELModel namegpt-4o-mini"
      },
      {
        "title": "Mode 1: Agent Interactive Call (Recommended)",
        "body": "When a user sends a social media post link and asks you to \"read and discuss\" or \"generate a quality reply\", call fetcher.py directly — do NOT use run_pipeline.py.\n\nrun_pipeline.py triggers deduplication cache, fixed LLM distillation, and browser popups, which are unsuitable for interactive scenarios."
      },
      {
        "title": "Usage Example",
        "body": "import sys\n\nskill_dir = r\"d:\\AIWareTop\\Agent\\openclaw-skills\\social-reader\"\nif skill_dir not in sys.path:\n    sys.path.append(skill_dir)\n\nfrom fetcher import get_tweet\n\nresult = get_tweet(\"https://x.com/user/status/123456\")\n\nif result.get(\"success\"):\n    content = result[\"content\"]\n    # Now you can discuss the content with the user or generate a reply"
      },
      {
        "title": "get_tweet() Return Structure",
        "body": "{\n  \"source\": \"fxtwitter\",\n  \"success\": true,\n  \"type\": \"tweet\",\n  \"content\": {\n    \"text\": \"Post body text\",\n    \"author\": \"Display name\",\n    \"username\": \"Username handle\",\n    \"created_at\": \"Publish time\",\n    \"likes\": 123,\n    \"retweets\": 45,\n    \"views\": 6789,\n    \"replies\": 10,\n    \"media\": [\"image_url_1\", \"image_url_2\"]\n  }\n}\n\nWhen type is \"article\" (long-form post), content additionally contains:\n\ntitle: Article title\npreview: Preview text\nfull_text: Full article body (Markdown format)\ncover_image: Cover image URL\n\nThis call is completely stateless — it writes no cache files and triggers no notification services."
      },
      {
        "title": "Mode 2: Background Pipeline Batch Processing",
        "body": "Use run_pipeline.py to chain Watcher → Processor → Action nodes. Suitable for scheduled tasks or batch processing."
      },
      {
        "title": "Three Core Nodes",
        "body": "Watcher (watcher.py)\n\nReads input_urls.txt or sources.json, deduplicates via seen_ids.json, writes new posts to pending_tweets.json.\n\n\n\nProcessor (processor.py)\n\nReads pending_tweets.json, calls LLM to generate commentary, outputs to drafts.json.\nRequires LLM_API_KEY environment variable.\n\n\n\nAction (notifier.py)\n\nStarts a local HTTP review server (port 18923), opens a browser review page with approve/reject/rewrite/archive controls."
      },
      {
        "title": "CLI Examples",
        "body": "# Full pipeline\npython run_pipeline.py\n\n# Specific URL\npython run_pipeline.py https://x.com/elonmusk/status/123456\n\n# Single node execution\npython run_pipeline.py --watch-only\npython run_pipeline.py --process-only\npython run_pipeline.py --notify-only"
      }
    ],
    "body": "Social Reader Skill\n\nThis skill provides a social media content scraping and monitoring workflow. It offers two usage modes:\n\nInteractive Mode: Agent fetches a single post in real-time for reading, discussion, or reply generation within a conversation.\nPipeline Mode: Background batch patrol of sources, with LLM distillation and review notifications.\nDependencies\npip install requests\n\nConfiguration Files\nFile\tPurpose\nprompt.txt\tLLM system prompt for the Processor node\nsources.json\tList of monitored accounts and fetch intervals (pipeline mode)\ninput_urls.txt\tManually entered post URLs (one per line, # for comments)\nseen_ids.json\tDeduplication cache for seen post IDs (pipeline mode only)\npending_tweets.json\tQueue of unprocessed posts from the Watcher\ndrafts.json\tLLM-distilled drafts from the Processor\narchive.json\tArchived history records\nEnvironment Variables (required only for Pipeline Mode Processor)\nVariable\tDescription\tDefault\nLLM_API_KEY\tLLM API key (required)\tNone\nLLM_BASE_URL\tAPI endpoint\thttps://api.openai.com/v1\nLLM_MODEL\tModel name\tgpt-4o-mini\nMode 1: Agent Interactive Call (Recommended)\n\nWhen a user sends a social media post link and asks you to \"read and discuss\" or \"generate a quality reply\", call fetcher.py directly — do NOT use run_pipeline.py.\n\nrun_pipeline.py triggers deduplication cache, fixed LLM distillation, and browser popups, which are unsuitable for interactive scenarios.\n\nUsage Example\nimport sys\n\nskill_dir = r\"d:\\AIWareTop\\Agent\\openclaw-skills\\social-reader\"\nif skill_dir not in sys.path:\n    sys.path.append(skill_dir)\n\nfrom fetcher import get_tweet\n\nresult = get_tweet(\"https://x.com/user/status/123456\")\n\nif result.get(\"success\"):\n    content = result[\"content\"]\n    # Now you can discuss the content with the user or generate a reply\n\nget_tweet() Return Structure\n{\n  \"source\": \"fxtwitter\",\n  \"success\": true,\n  \"type\": \"tweet\",\n  \"content\": {\n    \"text\": \"Post body text\",\n    \"author\": \"Display name\",\n    \"username\": \"Username handle\",\n    \"created_at\": \"Publish time\",\n    \"likes\": 123,\n    \"retweets\": 45,\n    \"views\": 6789,\n    \"replies\": 10,\n    \"media\": [\"image_url_1\", \"image_url_2\"]\n  }\n}\n\n\nWhen type is \"article\" (long-form post), content additionally contains:\n\ntitle: Article title\npreview: Preview text\nfull_text: Full article body (Markdown format)\ncover_image: Cover image URL\n\nThis call is completely stateless — it writes no cache files and triggers no notification services.\n\nMode 2: Background Pipeline Batch Processing\n\nUse run_pipeline.py to chain Watcher → Processor → Action nodes. Suitable for scheduled tasks or batch processing.\n\nThree Core Nodes\n\nWatcher (watcher.py)\n\nReads input_urls.txt or sources.json, deduplicates via seen_ids.json, writes new posts to pending_tweets.json.\n\nProcessor (processor.py)\n\nReads pending_tweets.json, calls LLM to generate commentary, outputs to drafts.json.\nRequires LLM_API_KEY environment variable.\n\nAction (notifier.py)\n\nStarts a local HTTP review server (port 18923), opens a browser review page with approve/reject/rewrite/archive controls.\nCLI Examples\n# Full pipeline\npython run_pipeline.py\n\n# Specific URL\npython run_pipeline.py https://x.com/elonmusk/status/123456\n\n# Single node execution\npython run_pipeline.py --watch-only\npython run_pipeline.py --process-only\npython run_pipeline.py --notify-only"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/HackSing/social-reader",
    "publisherUrl": "https://clawhub.ai/HackSing/social-reader",
    "owner": "HackSing",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/social-reader",
    "downloadUrl": "https://openagent3.xyz/downloads/social-reader",
    "agentUrl": "https://openagent3.xyz/skills/social-reader/agent",
    "manifestUrl": "https://openagent3.xyz/skills/social-reader/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/social-reader/agent.md"
  }
}