{
  "schemaVersion": "1.0",
  "item": {
    "slug": "summarizer",
    "name": "Summarizer",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/ivangdavila/summarizer",
    "canonicalUrl": "https://clawhub.ai/ivangdavila/summarizer",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/summarizer",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=summarizer",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "formats.md",
      "techniques.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/summarizer"
    },
    "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/summarizer",
    "agentPageUrl": "https://openagent3.xyz/skills/summarizer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/summarizer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/summarizer/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": "Core Principle",
        "body": "Good summaries preserve meaning while eliminating noise. Bad ones drop critical points or miss the audience.\n\nSummarization = Compression + Preservation + Adaptation"
      },
      {
        "title": "Protocol",
        "body": "Analyze → Select technique → Extract → Compress → Format → Verify"
      },
      {
        "title": "1. Analyze",
        "body": "Before summarizing, determine:\n\nLength of source — tweet vs book chapter\nComplexity — technical, narrative, data-heavy\nAudience — expert, general, executive, student\nPurpose — quick overview, decision support, study aid"
      },
      {
        "title": "2. Select Technique",
        "body": "Match technique to content (see techniques.md):\n\nContent typeBest techniqueSimple/shortZero-shot directTechnical/complexChain-of-thoughtAudience-specificRole-basedConsistent style neededFew-shotStrict requirementsInstruction-heavy"
      },
      {
        "title": "3. Extract",
        "body": "Identify what matters:\n\nCore argument or thesis\nKey supporting points (3-5 max)\nCritical data or evidence\nConclusions and implications\n\nRule: If you can't identify the core argument, you don't understand it yet."
      },
      {
        "title": "4. Compress",
        "body": "Apply compression levels:\n\nTLDR — 1 sentence, core message only\nBrief — 2-3 sentences, message + key support\nStandard — paragraph, covers main points\nExtended — multiple paragraphs, preserves nuance"
      },
      {
        "title": "5. Format",
        "body": "Match output to purpose (see formats.md):\n\nBullet points for scanning\nParagraph for reading\nStructured sections for reports\nTweet-length for social"
      },
      {
        "title": "6. Verify",
        "body": "Before delivering, check:\n\nCore message preserved?\n Key points included?\n Nothing critical dropped?\n Appropriate for audience?\n Right length for purpose?"
      },
      {
        "title": "Output Markers",
        "body": "📝 SUMMARY ([level]: [word count])\n[Content]\n\n💡 KEY POINTS\n• [Point 1]\n• [Point 2]\n\n⚠️ OMITTED (if relevant)\n[What was cut and why]"
      },
      {
        "title": "Decline When",
        "body": "Source is ambiguous, contradictory without resolution, or summarizing would lose essential nuance the user needs.\n\nReferences: techniques.md, formats.md"
      }
    ],
    "body": "Core Principle\n\nGood summaries preserve meaning while eliminating noise. Bad ones drop critical points or miss the audience.\n\nSummarization = Compression + Preservation + Adaptation\n\nProtocol\nAnalyze → Select technique → Extract → Compress → Format → Verify\n\n1. Analyze\n\nBefore summarizing, determine:\n\nLength of source — tweet vs book chapter\nComplexity — technical, narrative, data-heavy\nAudience — expert, general, executive, student\nPurpose — quick overview, decision support, study aid\n2. Select Technique\n\nMatch technique to content (see techniques.md):\n\nContent type\tBest technique\nSimple/short\tZero-shot direct\nTechnical/complex\tChain-of-thought\nAudience-specific\tRole-based\nConsistent style needed\tFew-shot\nStrict requirements\tInstruction-heavy\n3. Extract\n\nIdentify what matters:\n\nCore argument or thesis\nKey supporting points (3-5 max)\nCritical data or evidence\nConclusions and implications\n\nRule: If you can't identify the core argument, you don't understand it yet.\n\n4. Compress\n\nApply compression levels:\n\nTLDR — 1 sentence, core message only\nBrief — 2-3 sentences, message + key support\nStandard — paragraph, covers main points\nExtended — multiple paragraphs, preserves nuance\n5. Format\n\nMatch output to purpose (see formats.md):\n\nBullet points for scanning\nParagraph for reading\nStructured sections for reports\nTweet-length for social\n6. Verify\n\nBefore delivering, check:\n\n Core message preserved?\n Key points included?\n Nothing critical dropped?\n Appropriate for audience?\n Right length for purpose?\nOutput Markers\n📝 SUMMARY ([level]: [word count])\n[Content]\n\n💡 KEY POINTS\n• [Point 1]\n• [Point 2]\n\n⚠️ OMITTED (if relevant)\n[What was cut and why]\n\nDecline When\n\nSource is ambiguous, contradictory without resolution, or summarizing would lose essential nuance the user needs.\n\nReferences: techniques.md, formats.md"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ivangdavila/summarizer",
    "publisherUrl": "https://clawhub.ai/ivangdavila/summarizer",
    "owner": "ivangdavila",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/summarizer",
    "downloadUrl": "https://openagent3.xyz/downloads/summarizer",
    "agentUrl": "https://openagent3.xyz/skills/summarizer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/summarizer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/summarizer/agent.md"
  }
}