{
  "schemaVersion": "1.0",
  "item": {
    "slug": "mineru-skill",
    "name": "MinerU PDF Parser",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/TsekaLuk/mineru-skill",
    "canonicalUrl": "https://clawhub.ai/TsekaLuk/mineru-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/mineru-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mineru-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "requirements.txt",
      "SKILL.md",
      "scripts/mineru_v2.py",
      "scripts/mineru_async.py",
      "scripts/mineru_stable.py",
      "references/api_reference.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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/mineru-skill"
    },
    "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/mineru-skill",
    "agentPageUrl": "https://openagent3.xyz/skills/mineru-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mineru-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mineru-skill/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": "MinerU Document Parser",
        "body": "Convert PDF, Word, PPT, and images to clean Markdown using MinerU's VLM engine — LaTeX formulas, tables, and images all preserved."
      },
      {
        "title": "Setup",
        "body": "Get free API token at https://mineru.net/user-center/api-token\n\nexport MINERU_TOKEN=\"your-token-here\"\n\nLimits: 2000 pages/day · 200 MB per file · 600 pages per file"
      },
      {
        "title": "Supported File Types",
        "body": "TypeFormats📕 PDF.pdf — papers, textbooks, scanned docs📝 Word.docx — reports, manuscripts📊 PPT.pptx — slides, presentations🖼️ Image.jpg, .jpeg, .png — OCR extraction"
      },
      {
        "title": "Single File",
        "body": "python3 scripts/mineru_v2.py --file ./document.pdf --output ./output/"
      },
      {
        "title": "Batch Directory with Resume",
        "body": "python3 scripts/mineru_v2.py \\\n  --dir ./docs/ \\\n  --output ./output/ \\\n  --workers 10 \\\n  --resume"
      },
      {
        "title": "Direct to Obsidian",
        "body": "python3 scripts/mineru_v2.py \\\n  --dir ./pdfs/ \\\n  --output \"~/Library/Mobile Documents/com~apple~CloudDocs/Obsidian/VaultName/\" \\\n  --resume"
      },
      {
        "title": "Chinese Documents",
        "body": "python3 scripts/mineru_v2.py --dir ./papers/ --output ./output/ --language ch"
      },
      {
        "title": "Complex Layouts (Slow but Most Accurate)",
        "body": "python3 scripts/mineru_v2.py --file ./paper.pdf --output ./output/ --model vlm"
      },
      {
        "title": "CLI Options",
        "body": "--dir PATH          Input directory (PDF/Word/PPT/images)\n--file PATH         Single file\n--output PATH       Output directory (default: ./output/)\n--workers N         Concurrent workers (default: 5, max: 15)\n--resume            Skip already processed files\n--model MODEL       Model version: pipeline | vlm | MinerU-HTML (default: vlm)\n--language LANG     Document language: auto | en | ch (default: auto)\n--no-formula        Disable formula recognition\n--no-table          Disable table extraction\n--token TOKEN       API token (overrides MINERU_TOKEN env var)"
      },
      {
        "title": "Model Version Guide",
        "body": "ModelSpeedAccuracyBest Forpipeline⚡ FastHighStandard docs, most use casesvlm🐢 SlowHighestComplex layouts, multi-column, mixed text+figuresMinerU-HTML⚡ FastHighWeb-style output, HTML-ready content"
      },
      {
        "title": "Script Selection",
        "body": "ScriptUse Whenmineru_v2.pyDefault — async parallel (up to 15 workers)mineru_async.pyFast network, need maximum throughputmineru_stable.pyUnstable network — sequential, max retry"
      },
      {
        "title": "Output Structure",
        "body": "output/\n├── document-name/\n│   ├── document-name.md    # Main Markdown\n│   ├── images/             # Extracted images\n│   └── content.json        # Metadata"
      },
      {
        "title": "Performance",
        "body": "WorkersSpeed1 (sequential)1.2 files/min53.1 files/min155.6 files/min"
      },
      {
        "title": "Error Handling",
        "body": "5x auto-retry with exponential backoff\nUse --resume to continue interrupted batches\nFailed files listed at end of run"
      },
      {
        "title": "API Reference",
        "body": "For detailed API documentation, see references/api_reference.md."
      }
    ],
    "body": "MinerU Document Parser\n\nConvert PDF, Word, PPT, and images to clean Markdown using MinerU's VLM engine — LaTeX formulas, tables, and images all preserved.\n\nSetup\nGet free API token at https://mineru.net/user-center/api-token\nexport MINERU_TOKEN=\"your-token-here\"\n\n\nLimits: 2000 pages/day · 200 MB per file · 600 pages per file\n\nSupported File Types\nType\tFormats\n📕 PDF\t.pdf — papers, textbooks, scanned docs\n📝 Word\t.docx — reports, manuscripts\n📊 PPT\t.pptx — slides, presentations\n🖼️ Image\t.jpg, .jpeg, .png — OCR extraction\nCommands\nSingle File\npython3 scripts/mineru_v2.py --file ./document.pdf --output ./output/\n\nBatch Directory with Resume\npython3 scripts/mineru_v2.py \\\n  --dir ./docs/ \\\n  --output ./output/ \\\n  --workers 10 \\\n  --resume\n\nDirect to Obsidian\npython3 scripts/mineru_v2.py \\\n  --dir ./pdfs/ \\\n  --output \"~/Library/Mobile Documents/com~apple~CloudDocs/Obsidian/VaultName/\" \\\n  --resume\n\nChinese Documents\npython3 scripts/mineru_v2.py --dir ./papers/ --output ./output/ --language ch\n\nComplex Layouts (Slow but Most Accurate)\npython3 scripts/mineru_v2.py --file ./paper.pdf --output ./output/ --model vlm\n\nCLI Options\n--dir PATH          Input directory (PDF/Word/PPT/images)\n--file PATH         Single file\n--output PATH       Output directory (default: ./output/)\n--workers N         Concurrent workers (default: 5, max: 15)\n--resume            Skip already processed files\n--model MODEL       Model version: pipeline | vlm | MinerU-HTML (default: vlm)\n--language LANG     Document language: auto | en | ch (default: auto)\n--no-formula        Disable formula recognition\n--no-table          Disable table extraction\n--token TOKEN       API token (overrides MINERU_TOKEN env var)\n\nModel Version Guide\nModel\tSpeed\tAccuracy\tBest For\npipeline\t⚡ Fast\tHigh\tStandard docs, most use cases\nvlm\t🐢 Slow\tHighest\tComplex layouts, multi-column, mixed text+figures\nMinerU-HTML\t⚡ Fast\tHigh\tWeb-style output, HTML-ready content\nScript Selection\nScript\tUse When\nmineru_v2.py\tDefault — async parallel (up to 15 workers)\nmineru_async.py\tFast network, need maximum throughput\nmineru_stable.py\tUnstable network — sequential, max retry\nOutput Structure\noutput/\n├── document-name/\n│   ├── document-name.md    # Main Markdown\n│   ├── images/             # Extracted images\n│   └── content.json        # Metadata\n\nPerformance\nWorkers\tSpeed\n1 (sequential)\t1.2 files/min\n5\t3.1 files/min\n15\t5.6 files/min\nError Handling\n5x auto-retry with exponential backoff\nUse --resume to continue interrupted batches\nFailed files listed at end of run\nAPI Reference\n\nFor detailed API documentation, see references/api_reference.md."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/TsekaLuk/mineru-skill",
    "publisherUrl": "https://clawhub.ai/TsekaLuk/mineru-skill",
    "owner": "TsekaLuk",
    "version": "2.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/mineru-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/mineru-skill",
    "agentUrl": "https://openagent3.xyz/skills/mineru-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/mineru-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/mineru-skill/agent.md"
  }
}