{
  "schemaVersion": "1.0",
  "item": {
    "slug": "x-actionbook-recap",
    "name": "X Actionbook Recap",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/jack4world/x-actionbook-recap",
    "canonicalUrl": "https://clawhub.ai/jack4world/x-actionbook-recap",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/x-actionbook-recap",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=x-actionbook-recap",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/checklist.md",
      "references/image-card.md",
      "references/templates.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": "2026-05-07T17:22:31.273Z",
      "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/x-actionbook-recap"
    },
    "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-actionbook-recap",
    "agentPageUrl": "https://openagent3.xyz/skills/x-actionbook-recap/agent",
    "manifestUrl": "https://openagent3.xyz/skills/x-actionbook-recap/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/x-actionbook-recap/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": "What this skill is for",
        "body": "Produce a repeatable “collect → extract → summarize → publish” workflow for any X handle (optionally with a keyword) using the actionbook-rs approach:\n\nactionbook browser open the profile/search page\nactionbook browser snapshot to get the accessibility tree (incl. article nodes)\n(optional) actionbook browser eval to scroll\nextract post text from article blocks\nanalyze + draft output (Chinese internal notes; English publish)\npublish on X (neutral tone; optionally attach an image)"
      },
      {
        "title": "Guardrails",
        "body": "Infinite scroll is not exhaustive; be explicit about coverage limits.\nDon’t quote “recent interviews” unless the user provides exact links/timestamps.\nPublishing is external action: confirm the target account + final copy before posting."
      },
      {
        "title": "1) Collect posts (Actionbook)",
        "body": "Pick one entry point:\n\nProfile: https://x.com/<handle>\nSearch (keyword + optional recency): https://x.com/search?q=from%3A<handle>%20<keyword>&src=typed_query&f=live\n\nCommands (example):\n\n# open (profile)\nactionbook browser open \"https://x.com/<handle>\"\n\n# snapshot (repeat after each scroll)\nactionbook browser snapshot --refs aria --depth 18 --max-chars 12000\n\n# scroll a bit\nactionbook browser eval \"window.scrollBy(0, 2200)\"\n\nExtraction heuristic:\n\nIn snapshots, locate article nodes that contain the post text.\nRecord for each post:\n\ntext (verbatim)\ntimestamp shown (relative or absolute)\nURL if present\nwhether it’s a repost/quote (note it)\n\nStop condition:\n\nYou have enough coverage for the user’s time window (e.g., 7 days) OR diminishing returns."
      },
      {
        "title": "2) Summarize (Chinese notes)",
        "body": "Write a compact Chinese working summary:\n\nthemes (3–6 bullets)\nrepresentative posts (links)\nwhat’s missing / uncertainty"
      },
      {
        "title": "3) Draft publish copy (English, neutral)",
        "body": "Choose output type:\n\nSingle post (≤280 chars) OR\nThread (6–10 parts) if needed\n\nUse neutral framing:\n\n“Observation from public posts …”\navoid mind-reading; separate “what he said” from interpretation\n\nUse templates in references/templates.md."
      },
      {
        "title": "4) Image (optional but recommended)",
        "body": "Preferred options (no Python required):\n\nClean crop of the relevant post (browser screenshot at 1280×720 + zoom)\nA simple HTML/SVG card rendered in browser and screenshotted (see references/image-card.md)"
      },
      {
        "title": "5) Publish on X",
        "body": "If using OpenClaw browser automation:\n\nopen compose\npaste final English copy\nupload image (if any)\npost / thread\n\nConfirm before posting:\n\ntarget handle (e.g., @gblwll)\nfinal text\nimage choice"
      },
      {
        "title": "Bundled references",
        "body": "references/templates.md — recap + thread templates (English)\nreferences/checklist.md — extraction checklist + caveats\nreferences/image-card.md — HTML/SVG card approach (no Pillow)"
      }
    ],
    "body": "X recap via actionbook-rs\nWhat this skill is for\n\nProduce a repeatable “collect → extract → summarize → publish” workflow for any X handle (optionally with a keyword) using the actionbook-rs approach:\n\nactionbook browser open the profile/search page\nactionbook browser snapshot to get the accessibility tree (incl. article nodes)\n(optional) actionbook browser eval to scroll\nextract post text from article blocks\nanalyze + draft output (Chinese internal notes; English publish)\npublish on X (neutral tone; optionally attach an image)\nGuardrails\nInfinite scroll is not exhaustive; be explicit about coverage limits.\nDon’t quote “recent interviews” unless the user provides exact links/timestamps.\nPublishing is external action: confirm the target account + final copy before posting.\nWorkflow\n1) Collect posts (Actionbook)\n\nPick one entry point:\n\nProfile: https://x.com/<handle>\nSearch (keyword + optional recency): https://x.com/search?q=from%3A<handle>%20<keyword>&src=typed_query&f=live\n\nCommands (example):\n\n# open (profile)\nactionbook browser open \"https://x.com/<handle>\"\n\n# snapshot (repeat after each scroll)\nactionbook browser snapshot --refs aria --depth 18 --max-chars 12000\n\n# scroll a bit\nactionbook browser eval \"window.scrollBy(0, 2200)\"\n\n\nExtraction heuristic:\n\nIn snapshots, locate article nodes that contain the post text.\nRecord for each post:\ntext (verbatim)\ntimestamp shown (relative or absolute)\nURL if present\nwhether it’s a repost/quote (note it)\n\nStop condition:\n\nYou have enough coverage for the user’s time window (e.g., 7 days) OR diminishing returns.\n2) Summarize (Chinese notes)\n\nWrite a compact Chinese working summary:\n\nthemes (3–6 bullets)\nrepresentative posts (links)\nwhat’s missing / uncertainty\n3) Draft publish copy (English, neutral)\n\nChoose output type:\n\nSingle post (≤280 chars) OR\nThread (6–10 parts) if needed\n\nUse neutral framing:\n\n“Observation from public posts …”\navoid mind-reading; separate “what he said” from interpretation\n\nUse templates in references/templates.md.\n\n4) Image (optional but recommended)\n\nPreferred options (no Python required):\n\nClean crop of the relevant post (browser screenshot at 1280×720 + zoom)\nA simple HTML/SVG card rendered in browser and screenshotted (see references/image-card.md)\n5) Publish on X\n\nIf using OpenClaw browser automation:\n\nopen compose\npaste final English copy\nupload image (if any)\npost / thread\n\nConfirm before posting:\n\ntarget handle (e.g., @gblwll)\nfinal text\nimage choice\nBundled references\nreferences/templates.md — recap + thread templates (English)\nreferences/checklist.md — extraction checklist + caveats\nreferences/image-card.md — HTML/SVG card approach (no Pillow)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jack4world/x-actionbook-recap",
    "publisherUrl": "https://clawhub.ai/jack4world/x-actionbook-recap",
    "owner": "jack4world",
    "version": "0.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/x-actionbook-recap",
    "downloadUrl": "https://openagent3.xyz/downloads/x-actionbook-recap",
    "agentUrl": "https://openagent3.xyz/skills/x-actionbook-recap/agent",
    "manifestUrl": "https://openagent3.xyz/skills/x-actionbook-recap/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/x-actionbook-recap/agent.md"
  }
}