{ "schemaVersion": "1.0", "item": { "slug": "docling", "name": "Docling", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/Er3mit4/docling", "canonicalUrl": "https://clawhub.ai/Er3mit4/docling", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/docling", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=docling", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/cli-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", "slug": "docling", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-02T15:42:27.842Z", "expiresAt": "2026-05-09T15:42:27.842Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=docling", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=docling", "contentDisposition": "attachment; filename=\"docling-1.0.2.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "docling" }, "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/docling" }, "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/docling", "agentPageUrl": "https://openagent3.xyz/skills/docling/agent", "manifestUrl": "https://openagent3.xyz/skills/docling/agent.json", "briefUrl": "https://openagent3.xyz/skills/docling/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": "Docling - Document & Web Content Extraction", "body": "CLI tool for parsing documents and web pages into clean, structured text. Uses GPU acceleration for OCR and ML models." }, { "title": "Prerequisites", "body": "docling CLI must be installed (e.g., via pipx install docling)\nFor GPU support: NVIDIA GPU with CUDA drivers" }, { "title": "When to Use", "body": "Extract content from a URL → Use docling (not web_fetch)\nSearch for information → Use web_search (Brave)\nParse PDFs, DOCX, PPTX → Use docling\nOCR on images → Use docling" }, { "title": "Web Page → Markdown (default)", "body": "docling \"\" --from html --to md\n\nOutput: creates a .md file in current directory (or use --output)" }, { "title": "Web Page → Plain Text", "body": "docling \"\" --from html --to text --output /tmp/docling_out" }, { "title": "PDF with OCR", "body": "docling \"/path/to/file.pdf\" --ocr --device cuda --output /tmp/docling_out" }, { "title": "Key Options", "body": "OptionValuesDescription--fromhtml, pdf, docx, pptx, image, md, csv, xlsxInput format--tomd, text, json, yaml, htmlOutput format--deviceauto, cuda, cpuAccelerator (default: auto)--outputpathOutput directory (recommended: use controlled temp dir)--ocrflagEnable OCR for images/scanned PDFs--tablesflagExtract tables (default: on)" }, { "title": "Security Notes", "body": "⚠️ Avoid these flags unless you trust the source:\n\n--enable-remote-services - can send data to remote endpoints\n--allow-external-plugins - loads third-party code\nCustom --headers with untrusted values - can redirect requests" }, { "title": "Workflow", "body": "For web content extraction: Use docling \"\" --from html --to text --output /tmp/docling_out\nRead the output file from the specified output directory\nClean up the output directory after reading" }, { "title": "GPU Support", "body": "Docling supports GPU acceleration via CUDA (NVIDIA). Verify CUDA is available:\n\npython -c \"import torch; print(torch.cuda.is_available())\"" }, { "title": "Full CLI Reference", "body": "See references/cli-reference.md for complete option list." } ], "body": "Docling - Document & Web Content Extraction\n\nCLI tool for parsing documents and web pages into clean, structured text. Uses GPU acceleration for OCR and ML models.\n\nPrerequisites\ndocling CLI must be installed (e.g., via pipx install docling)\nFor GPU support: NVIDIA GPU with CUDA drivers\nWhen to Use\nExtract content from a URL → Use docling (not web_fetch)\nSearch for information → Use web_search (Brave)\nParse PDFs, DOCX, PPTX → Use docling\nOCR on images → Use docling\nQuick Commands\nWeb Page → Markdown (default)\ndocling \"\" --from html --to md\n\n\nOutput: creates a .md file in current directory (or use --output)\n\nWeb Page → Plain Text\ndocling \"\" --from html --to text --output /tmp/docling_out\n\nPDF with OCR\ndocling \"/path/to/file.pdf\" --ocr --device cuda --output /tmp/docling_out\n\nKey Options\nOption\tValues\tDescription\n--from\thtml, pdf, docx, pptx, image, md, csv, xlsx\tInput format\n--to\tmd, text, json, yaml, html\tOutput format\n--device\tauto, cuda, cpu\tAccelerator (default: auto)\n--output\tpath\tOutput directory (recommended: use controlled temp dir)\n--ocr\tflag\tEnable OCR for images/scanned PDFs\n--tables\tflag\tExtract tables (default: on)\nSecurity Notes\n\n⚠️ Avoid these flags unless you trust the source:\n\n--enable-remote-services - can send data to remote endpoints\n--allow-external-plugins - loads third-party code\nCustom --headers with untrusted values - can redirect requests\nWorkflow\nFor web content extraction: Use docling \"\" --from html --to text --output /tmp/docling_out\nRead the output file from the specified output directory\nClean up the output directory after reading\nGPU Support\n\nDocling supports GPU acceleration via CUDA (NVIDIA). Verify CUDA is available:\n\npython -c \"import torch; print(torch.cuda.is_available())\"\n\nFull CLI Reference\n\nSee references/cli-reference.md for complete option list." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Er3mit4/docling", "publisherUrl": "https://clawhub.ai/Er3mit4/docling", "owner": "Er3mit4", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/docling", "downloadUrl": "https://openagent3.xyz/downloads/docling", "agentUrl": "https://openagent3.xyz/skills/docling/agent", "manifestUrl": "https://openagent3.xyz/skills/docling/agent.json", "briefUrl": "https://openagent3.xyz/skills/docling/agent.md" } }