{
  "schemaVersion": "1.0",
  "item": {
    "slug": "parallel-extract",
    "name": "Parallel Extract",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/NormallyGaussian/parallel-extract",
    "canonicalUrl": "https://clawhub.ai/NormallyGaussian/parallel-extract",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/parallel-extract",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=parallel-extract",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "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",
      "slug": "parallel-extract",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-06T21:42:34.581Z",
      "expiresAt": "2026-05-13T21:42:34.581Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=parallel-extract",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=parallel-extract",
        "contentDisposition": "attachment; filename=\"parallel-extract-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "parallel-extract"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/parallel-extract"
    },
    "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/parallel-extract",
    "agentPageUrl": "https://openagent3.xyz/skills/parallel-extract/agent",
    "manifestUrl": "https://openagent3.xyz/skills/parallel-extract/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/parallel-extract/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": "Parallel Extract",
        "body": "Extract clean, LLM-ready content from URLs. Handles webpages, articles, PDFs, and JavaScript-heavy sites that need rendering."
      },
      {
        "title": "When to Use",
        "body": "Trigger this skill when the user asks for:\n\n\"read this URL\", \"fetch this page\", \"extract from...\"\n\"get the content from [URL]\"\n\"what does this article say?\"\nReading PDFs, JS-heavy pages, or paywalled content\nGetting clean markdown from messy web pages\n\nUse Search to discover; use Extract to read."
      },
      {
        "title": "Quick Start",
        "body": "parallel-cli extract \"https://example.com/article\" --json"
      },
      {
        "title": "Basic Usage",
        "body": "parallel-cli extract \"<url>\" [options]"
      },
      {
        "title": "Common Flags",
        "body": "FlagDescription--url \"<url>\"URL to extract (repeatable, max 10)--objective \"<focus>\"Focus extraction on specific content--jsonOutput as JSON--excerpts / --no-excerptsInclude relevant excerpts (default: on)--full-content / --no-full-contentInclude full page content--excerpts-max-chars NMax chars per excerpt--excerpts-max-total-chars NMax total excerpt chars--full-max-chars NMax full content chars-o <file>Save output to file"
      },
      {
        "title": "Examples",
        "body": "Basic extraction:\n\nparallel-cli extract \"https://example.com/article\" --json\n\nFocused extraction:\n\nparallel-cli extract \"https://example.com/pricing\" \\\n  --objective \"pricing tiers and features\" \\\n  --json\n\nFull content for PDFs:\n\nparallel-cli extract \"https://example.com/whitepaper.pdf\" \\\n  --full-content \\\n  --json\n\nMultiple URLs:\n\nparallel-cli extract \\\n  --url \"https://example.com/page1\" \\\n  --url \"https://example.com/page2\" \\\n  --json"
      },
      {
        "title": "Default Workflow",
        "body": "Search with an objective + keyword queries\nInspect titles/URLs/dates; choose the best sources\nExtract the specific pages you need (top N URLs)\nAnswer using the extracted excerpts/content"
      },
      {
        "title": "Objective",
        "body": "When extracting, provide context:\n\nWhat specific information you're looking for\nWhy you need it (helps focus extraction)\n\nGood: --objective \"Find the installation steps and system requirements\"\n\nPoor: --objective \"Read the page\""
      },
      {
        "title": "Response Format",
        "body": "Returns structured JSON with:\n\nurl — source URL\ntitle — page title\nexcerpts[] — relevant text excerpts (if enabled)\nfull_content — complete page content (if enabled)\npublish_date — when available"
      },
      {
        "title": "Output Handling",
        "body": "When turning extracted content into a user-facing answer:\n\nKeep content verbatim — do not paraphrase unnecessarily\nExtract ALL list items exhaustively\nStrip noise: nav menus, footers, ads, \"click here\" links\nPreserve all facts, names, numbers, dates, quotes\nInclude URL + publish_date for transparency"
      },
      {
        "title": "Running Out of Context?",
        "body": "For long conversations, save results and use sessions_spawn:\n\nparallel-cli extract \"<url>\" --json -o /tmp/extract-<topic>.json\n\nThen spawn a sub-agent:\n\n{\n  \"tool\": \"sessions_spawn\",\n  \"task\": \"Read /tmp/extract-<topic>.json and summarize the key content.\",\n  \"label\": \"extract-summary\"\n}"
      },
      {
        "title": "Error Handling",
        "body": "Exit CodeMeaning0Success1Unexpected error (network, parse)2Invalid arguments3API error (non-2xx)"
      },
      {
        "title": "Prerequisites",
        "body": "Get an API key at parallel.ai\nInstall the CLI:\n\ncurl -fsSL https://parallel.ai/install.sh | bash\nexport PARALLEL_API_KEY=your-key"
      },
      {
        "title": "References",
        "body": "API Docs\nExtract API Reference"
      }
    ],
    "body": "Parallel Extract\n\nExtract clean, LLM-ready content from URLs. Handles webpages, articles, PDFs, and JavaScript-heavy sites that need rendering.\n\nWhen to Use\n\nTrigger this skill when the user asks for:\n\n\"read this URL\", \"fetch this page\", \"extract from...\"\n\"get the content from [URL]\"\n\"what does this article say?\"\nReading PDFs, JS-heavy pages, or paywalled content\nGetting clean markdown from messy web pages\n\nUse Search to discover; use Extract to read.\n\nQuick Start\nparallel-cli extract \"https://example.com/article\" --json\n\nCLI Reference\nBasic Usage\nparallel-cli extract \"<url>\" [options]\n\nCommon Flags\nFlag\tDescription\n--url \"<url>\"\tURL to extract (repeatable, max 10)\n--objective \"<focus>\"\tFocus extraction on specific content\n--json\tOutput as JSON\n--excerpts / --no-excerpts\tInclude relevant excerpts (default: on)\n--full-content / --no-full-content\tInclude full page content\n--excerpts-max-chars N\tMax chars per excerpt\n--excerpts-max-total-chars N\tMax total excerpt chars\n--full-max-chars N\tMax full content chars\n-o <file>\tSave output to file\nExamples\n\nBasic extraction:\n\nparallel-cli extract \"https://example.com/article\" --json\n\n\nFocused extraction:\n\nparallel-cli extract \"https://example.com/pricing\" \\\n  --objective \"pricing tiers and features\" \\\n  --json\n\n\nFull content for PDFs:\n\nparallel-cli extract \"https://example.com/whitepaper.pdf\" \\\n  --full-content \\\n  --json\n\n\nMultiple URLs:\n\nparallel-cli extract \\\n  --url \"https://example.com/page1\" \\\n  --url \"https://example.com/page2\" \\\n  --json\n\nDefault Workflow\nSearch with an objective + keyword queries\nInspect titles/URLs/dates; choose the best sources\nExtract the specific pages you need (top N URLs)\nAnswer using the extracted excerpts/content\nBest-Practice Prompting\nObjective\n\nWhen extracting, provide context:\n\nWhat specific information you're looking for\nWhy you need it (helps focus extraction)\n\nGood: --objective \"Find the installation steps and system requirements\"\n\nPoor: --objective \"Read the page\"\n\nResponse Format\n\nReturns structured JSON with:\n\nurl — source URL\ntitle — page title\nexcerpts[] — relevant text excerpts (if enabled)\nfull_content — complete page content (if enabled)\npublish_date — when available\nOutput Handling\n\nWhen turning extracted content into a user-facing answer:\n\nKeep content verbatim — do not paraphrase unnecessarily\nExtract ALL list items exhaustively\nStrip noise: nav menus, footers, ads, \"click here\" links\nPreserve all facts, names, numbers, dates, quotes\nInclude URL + publish_date for transparency\nRunning Out of Context?\n\nFor long conversations, save results and use sessions_spawn:\n\nparallel-cli extract \"<url>\" --json -o /tmp/extract-<topic>.json\n\n\nThen spawn a sub-agent:\n\n{\n  \"tool\": \"sessions_spawn\",\n  \"task\": \"Read /tmp/extract-<topic>.json and summarize the key content.\",\n  \"label\": \"extract-summary\"\n}\n\nError Handling\nExit Code\tMeaning\n0\tSuccess\n1\tUnexpected error (network, parse)\n2\tInvalid arguments\n3\tAPI error (non-2xx)\nPrerequisites\nGet an API key at parallel.ai\nInstall the CLI:\ncurl -fsSL https://parallel.ai/install.sh | bash\nexport PARALLEL_API_KEY=your-key\n\nReferences\nAPI Docs\nExtract API Reference"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/NormallyGaussian/parallel-extract",
    "publisherUrl": "https://clawhub.ai/NormallyGaussian/parallel-extract",
    "owner": "NormallyGaussian",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/parallel-extract",
    "downloadUrl": "https://openagent3.xyz/downloads/parallel-extract",
    "agentUrl": "https://openagent3.xyz/skills/parallel-extract/agent",
    "manifestUrl": "https://openagent3.xyz/skills/parallel-extract/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/parallel-extract/agent.md"
  }
}