{ "schemaVersion": "1.0", "item": { "slug": "docstrange", "name": "Nanonets OCR", "source": "tencent", "type": "skill", "category": "效率提升", "sourceUrl": "https://clawhub.ai/shhdwi/docstrange", "canonicalUrl": "https://clawhub.ai/shhdwi/docstrange", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/docstrange", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=docstrange", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "package.json", "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", "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/docstrange" }, "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/docstrange", "agentPageUrl": "https://openagent3.xyz/skills/docstrange/agent", "manifestUrl": "https://openagent3.xyz/skills/docstrange/agent.json", "briefUrl": "https://openagent3.xyz/skills/docstrange/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": "DocStrange by Nanonets", "body": "Document extraction API — convert PDFs, images, and documents to markdown, JSON, or CSV with per-field confidence scoring.\n\nGet your API key: https://docstrange.nanonets.com/app" }, { "title": "Quick Start", "body": "curl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@document.pdf\" \\\n -F \"output_format=markdown\"\n\nResponse:\n\n{\n \"success\": true,\n \"record_id\": \"550e8400-e29b-41d4-a716-446655440000\",\n \"status\": \"completed\",\n \"result\": {\n \"markdown\": {\n \"content\": \"# Invoice\\n\\n**Invoice Number:** INV-2024-001...\"\n }\n }\n}" }, { "title": "1. Get Your API Key", "body": "# Visit the dashboard\nhttps://docstrange.nanonets.com/app\n\nSave your API key:\n\nexport DOCSTRANGE_API_KEY=\"your_api_key_here\"" }, { "title": "2. OpenClaw Configuration (Optional)", "body": "Recommended: Use environment variables (most secure):\n\n{\n skills: {\n entries: {\n \"docstrange\": {\n enabled: true,\n // API key loaded from environment variable DOCSTRANGE_API_KEY\n },\n },\n },\n}\n\nAlternative: Store in config file (use with caution):\n\n{\n skills: {\n entries: {\n \"docstrange\": {\n enabled: true,\n env: {\n DOCSTRANGE_API_KEY: \"your_api_key_here\",\n },\n },\n },\n },\n}\n\nSecurity Note: If storing API keys in ~/.openclaw/openclaw.json:\n\nSet file permissions: chmod 600 ~/.openclaw/openclaw.json\nNever commit this file to version control\nPrefer environment variables or your agent's secret store when possible\nRotate keys regularly and limit API key permissions if supported" }, { "title": "Extract to Markdown", "body": "curl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@document.pdf\" \\\n -F \"output_format=markdown\"\n\nAccess content: response[\"result\"][\"markdown\"][\"content\"]" }, { "title": "Extract JSON Fields", "body": "Simple field list:\n\ncurl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@invoice.pdf\" \\\n -F \"output_format=json\" \\\n -F 'json_options=[\"invoice_number\", \"date\", \"total_amount\", \"vendor\"]' \\\n -F \"include_metadata=confidence_score\"\n\nWith JSON schema:\n\ncurl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@invoice.pdf\" \\\n -F \"output_format=json\" \\\n -F 'json_options={\"type\": \"object\", \"properties\": {\"invoice_number\": {\"type\": \"string\"}, \"total_amount\": {\"type\": \"number\"}}}'\n\nResponse with confidence scores:\n\n{\n \"result\": {\n \"json\": {\n \"content\": {\n \"invoice_number\": \"INV-2024-001\",\n \"total_amount\": 500.00\n },\n \"metadata\": {\n \"confidence_score\": {\n \"invoice_number\": 98,\n \"total_amount\": 99\n }\n }\n }\n }\n}" }, { "title": "Extract Tables to CSV", "body": "curl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@table.pdf\" \\\n -F \"output_format=csv\" \\\n -F \"csv_options=table\"" }, { "title": "Async Extraction (Large Documents)", "body": "For documents >5 pages, use async and poll:\n\nQueue the document:\n\ncurl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/async\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@large-document.pdf\" \\\n -F \"output_format=markdown\"\n\n# Returns: {\"record_id\": \"12345\", \"status\": \"processing\"}\n\nPoll for results:\n\ncurl -X GET \"https://extraction-api.nanonets.com/api/v1/extract/results/12345\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\"\n\n# Returns: {\"status\": \"completed\", \"result\": {...}}" }, { "title": "Bounding Boxes", "body": "Get element coordinates for layout analysis:\n\n-F \"include_metadata=bounding_boxes\"" }, { "title": "Hierarchy Output", "body": "Extract document structure (sections, tables, key-value pairs):\n\n-F \"json_options=hierarchy_output\"" }, { "title": "Financial Documents Mode", "body": "Enhanced table and number formatting:\n\n-F \"markdown_options=financial-docs\"" }, { "title": "Custom Instructions", "body": "Guide extraction with prompts:\n\n-F \"custom_instructions=Focus on financial data. Ignore headers.\"\n-F \"prompt_mode=append\"" }, { "title": "Multiple Formats", "body": "Request multiple formats in one call:\n\n-F \"output_format=markdown,json\"" }, { "title": "Use DocStrange For:", "body": "Invoice and receipt processing\nContract text extraction\nBank statement parsing\nForm digitization\nImage OCR (scanned documents)" }, { "title": "Don't Use For:", "body": "Documents >5 pages with sync (use async)\nVideo/audio transcription\nNon-document images" }, { "title": "Best Practices", "body": "Document SizeEndpointNotes<=5 pages/extract/syncImmediate response>5 pages/extract/asyncPoll for results\n\nJSON Extraction:\n\nField list: [\"field1\", \"field2\"] — quick extractions\nJSON schema: {\"type\": \"object\", ...} — strict typing, nested data\n\nConfidence Scores:\n\nAdd include_metadata=confidence_score\nScores are 0-100 per field\nReview fields <80 manually" }, { "title": "Invoice", "body": "{\n \"type\": \"object\",\n \"properties\": {\n \"invoice_number\": {\"type\": \"string\"},\n \"date\": {\"type\": \"string\"},\n \"vendor\": {\"type\": \"string\"},\n \"total\": {\"type\": \"number\"},\n \"line_items\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"description\": {\"type\": \"string\"},\n \"quantity\": {\"type\": \"number\"},\n \"price\": {\"type\": \"number\"}\n }\n }\n }\n }\n}" }, { "title": "Receipt", "body": "{\n \"type\": \"object\",\n \"properties\": {\n \"merchant\": {\"type\": \"string\"},\n \"date\": {\"type\": \"string\"},\n \"total\": {\"type\": \"number\"},\n \"items\": {\n \"type\": \"array\",\n \"items\": {\"type\": \"object\", \"properties\": {\"name\": {\"type\": \"string\"}, \"price\": {\"type\": \"number\"}}}\n }\n }\n}" }, { "title": "Data Handling", "body": "Important: Documents uploaded to DocStrange are transmitted to https://extraction-api.nanonets.com and processed on external servers.\n\nBefore uploading sensitive documents:\n\nReview Nanonets' privacy policy and data retention policies: https://docstrange.nanonets.com/docs\nVerify encryption in transit (HTTPS) and at rest\nConfirm data deletion/retention timelines\nTest with non-sensitive sample documents first\n\nBest practices:\n\nDo not upload highly sensitive PII (SSNs, medical records, financial account numbers) until you've confirmed the service's security and compliance posture\nUse API keys with limited permissions/scopes if available\nRotate API keys regularly (every 90 days recommended)\nMonitor API usage logs for unauthorized access\nNever log or commit API keys to repositories or examples" }, { "title": "File Size Limits", "body": "Sync endpoint: Recommended for documents ≤5 pages\nAsync endpoint: Use for documents >5 pages to avoid timeouts\nLarge files: Consider using file_url with publicly accessible URLs instead of uploading large files directly" }, { "title": "Operational Safeguards", "body": "Always use environment variables or secure secret stores for API keys\nNever include real API keys in code examples or documentation\nUse placeholder values like \"your_api_key_here\" in examples\nSet appropriate file permissions on configuration files (600 for JSON configs)\nEnable API key rotation and monitor usage through the dashboard" }, { "title": "Troubleshooting", "body": "400 Bad Request:\n\nProvide exactly one input: file, file_url, or file_base64\nVerify API key is valid\n\nSync Timeout:\n\nUse async for documents >5 pages\nPoll /extract/results/{record_id}\n\nMissing Confidence Scores:\n\nRequires json_options (field list or schema)\nAdd include_metadata=confidence_score\n\nAuthentication Errors:\n\nVerify DOCSTRANGE_API_KEY environment variable is set\nCheck API key hasn't expired or been revoked\nEnsure no extra whitespace in API key value" }, { "title": "Pre-Publish Security Checklist", "body": "Before publishing or updating this skill, verify:\n\npackage.json declares requiredEnv and primaryEnv for DOCSTRANGE_API_KEY\n package.json lists API endpoints in endpoints array\n All code examples use placeholder values (\"your_api_key_here\") not real keys\n No API keys or secrets are embedded in SKILL.md or package.json\n Security & Privacy section documents data handling and risks\n Configuration examples include security warnings for plaintext storage\n File permission guidance is included for config files" }, { "title": "References", "body": "API Docs: https://docstrange.nanonets.com/docs\nGet API Key: https://docstrange.nanonets.com/app\nPrivacy Policy: https://docstrange.nanonets.com/docs (check for privacy/data policy links)" } ], "body": "DocStrange by Nanonets\n\nDocument extraction API — convert PDFs, images, and documents to markdown, JSON, or CSV with per-field confidence scoring.\n\nGet your API key: https://docstrange.nanonets.com/app\n\nQuick Start\ncurl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@document.pdf\" \\\n -F \"output_format=markdown\"\n\n\nResponse:\n\n{\n \"success\": true,\n \"record_id\": \"550e8400-e29b-41d4-a716-446655440000\",\n \"status\": \"completed\",\n \"result\": {\n \"markdown\": {\n \"content\": \"# Invoice\\n\\n**Invoice Number:** INV-2024-001...\"\n }\n }\n}\n\nSetup\n1. Get Your API Key\n# Visit the dashboard\nhttps://docstrange.nanonets.com/app\n\n\nSave your API key:\n\nexport DOCSTRANGE_API_KEY=\"your_api_key_here\"\n\n2. OpenClaw Configuration (Optional)\n\nRecommended: Use environment variables (most secure):\n\n{\n skills: {\n entries: {\n \"docstrange\": {\n enabled: true,\n // API key loaded from environment variable DOCSTRANGE_API_KEY\n },\n },\n },\n}\n\n\nAlternative: Store in config file (use with caution):\n\n{\n skills: {\n entries: {\n \"docstrange\": {\n enabled: true,\n env: {\n DOCSTRANGE_API_KEY: \"your_api_key_here\",\n },\n },\n },\n },\n}\n\n\nSecurity Note: If storing API keys in ~/.openclaw/openclaw.json:\n\nSet file permissions: chmod 600 ~/.openclaw/openclaw.json\nNever commit this file to version control\nPrefer environment variables or your agent's secret store when possible\nRotate keys regularly and limit API key permissions if supported\nCommon Tasks\nExtract to Markdown\ncurl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@document.pdf\" \\\n -F \"output_format=markdown\"\n\n\nAccess content: response[\"result\"][\"markdown\"][\"content\"]\n\nExtract JSON Fields\n\nSimple field list:\n\ncurl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@invoice.pdf\" \\\n -F \"output_format=json\" \\\n -F 'json_options=[\"invoice_number\", \"date\", \"total_amount\", \"vendor\"]' \\\n -F \"include_metadata=confidence_score\"\n\n\nWith JSON schema:\n\ncurl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@invoice.pdf\" \\\n -F \"output_format=json\" \\\n -F 'json_options={\"type\": \"object\", \"properties\": {\"invoice_number\": {\"type\": \"string\"}, \"total_amount\": {\"type\": \"number\"}}}'\n\n\nResponse with confidence scores:\n\n{\n \"result\": {\n \"json\": {\n \"content\": {\n \"invoice_number\": \"INV-2024-001\",\n \"total_amount\": 500.00\n },\n \"metadata\": {\n \"confidence_score\": {\n \"invoice_number\": 98,\n \"total_amount\": 99\n }\n }\n }\n }\n}\n\nExtract Tables to CSV\ncurl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/sync\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@table.pdf\" \\\n -F \"output_format=csv\" \\\n -F \"csv_options=table\"\n\nAsync Extraction (Large Documents)\n\nFor documents >5 pages, use async and poll:\n\nQueue the document:\n\ncurl -X POST \"https://extraction-api.nanonets.com/api/v1/extract/async\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\" \\\n -F \"file=@large-document.pdf\" \\\n -F \"output_format=markdown\"\n\n# Returns: {\"record_id\": \"12345\", \"status\": \"processing\"}\n\n\nPoll for results:\n\ncurl -X GET \"https://extraction-api.nanonets.com/api/v1/extract/results/12345\" \\\n -H \"Authorization: Bearer $DOCSTRANGE_API_KEY\"\n\n# Returns: {\"status\": \"completed\", \"result\": {...}}\n\nAdvanced Features\nBounding Boxes\n\nGet element coordinates for layout analysis:\n\n-F \"include_metadata=bounding_boxes\"\n\nHierarchy Output\n\nExtract document structure (sections, tables, key-value pairs):\n\n-F \"json_options=hierarchy_output\"\n\nFinancial Documents Mode\n\nEnhanced table and number formatting:\n\n-F \"markdown_options=financial-docs\"\n\nCustom Instructions\n\nGuide extraction with prompts:\n\n-F \"custom_instructions=Focus on financial data. Ignore headers.\"\n-F \"prompt_mode=append\"\n\nMultiple Formats\n\nRequest multiple formats in one call:\n\n-F \"output_format=markdown,json\"\n\nWhen to Use\nUse DocStrange For:\nInvoice and receipt processing\nContract text extraction\nBank statement parsing\nForm digitization\nImage OCR (scanned documents)\nDon't Use For:\nDocuments >5 pages with sync (use async)\nVideo/audio transcription\nNon-document images\nBest Practices\nDocument Size\tEndpoint\tNotes\n<=5 pages\t/extract/sync\tImmediate response\n>5 pages\t/extract/async\tPoll for results\n\nJSON Extraction:\n\nField list: [\"field1\", \"field2\"] — quick extractions\nJSON schema: {\"type\": \"object\", ...} — strict typing, nested data\n\nConfidence Scores:\n\nAdd include_metadata=confidence_score\nScores are 0-100 per field\nReview fields <80 manually\nSchema Templates\nInvoice\n{\n \"type\": \"object\",\n \"properties\": {\n \"invoice_number\": {\"type\": \"string\"},\n \"date\": {\"type\": \"string\"},\n \"vendor\": {\"type\": \"string\"},\n \"total\": {\"type\": \"number\"},\n \"line_items\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"description\": {\"type\": \"string\"},\n \"quantity\": {\"type\": \"number\"},\n \"price\": {\"type\": \"number\"}\n }\n }\n }\n }\n}\n\nReceipt\n{\n \"type\": \"object\",\n \"properties\": {\n \"merchant\": {\"type\": \"string\"},\n \"date\": {\"type\": \"string\"},\n \"total\": {\"type\": \"number\"},\n \"items\": {\n \"type\": \"array\",\n \"items\": {\"type\": \"object\", \"properties\": {\"name\": {\"type\": \"string\"}, \"price\": {\"type\": \"number\"}}}\n }\n }\n}\n\nSecurity & Privacy\nData Handling\n\nImportant: Documents uploaded to DocStrange are transmitted to https://extraction-api.nanonets.com and processed on external servers.\n\nBefore uploading sensitive documents:\n\nReview Nanonets' privacy policy and data retention policies: https://docstrange.nanonets.com/docs\nVerify encryption in transit (HTTPS) and at rest\nConfirm data deletion/retention timelines\nTest with non-sensitive sample documents first\n\nBest practices:\n\nDo not upload highly sensitive PII (SSNs, medical records, financial account numbers) until you've confirmed the service's security and compliance posture\nUse API keys with limited permissions/scopes if available\nRotate API keys regularly (every 90 days recommended)\nMonitor API usage logs for unauthorized access\nNever log or commit API keys to repositories or examples\nFile Size Limits\nSync endpoint: Recommended for documents ≤5 pages\nAsync endpoint: Use for documents >5 pages to avoid timeouts\nLarge files: Consider using file_url with publicly accessible URLs instead of uploading large files directly\nOperational Safeguards\nAlways use environment variables or secure secret stores for API keys\nNever include real API keys in code examples or documentation\nUse placeholder values like \"your_api_key_here\" in examples\nSet appropriate file permissions on configuration files (600 for JSON configs)\nEnable API key rotation and monitor usage through the dashboard\nTroubleshooting\n\n400 Bad Request:\n\nProvide exactly one input: file, file_url, or file_base64\nVerify API key is valid\n\nSync Timeout:\n\nUse async for documents >5 pages\nPoll /extract/results/{record_id}\n\nMissing Confidence Scores:\n\nRequires json_options (field list or schema)\nAdd include_metadata=confidence_score\n\nAuthentication Errors:\n\nVerify DOCSTRANGE_API_KEY environment variable is set\nCheck API key hasn't expired or been revoked\nEnsure no extra whitespace in API key value\nPre-Publish Security Checklist\n\nBefore publishing or updating this skill, verify:\n\n package.json declares requiredEnv and primaryEnv for DOCSTRANGE_API_KEY\n package.json lists API endpoints in endpoints array\n All code examples use placeholder values (\"your_api_key_here\") not real keys\n No API keys or secrets are embedded in SKILL.md or package.json\n Security & Privacy section documents data handling and risks\n Configuration examples include security warnings for plaintext storage\n File permission guidance is included for config files\nReferences\nAPI Docs: https://docstrange.nanonets.com/docs\nGet API Key: https://docstrange.nanonets.com/app\nPrivacy Policy: https://docstrange.nanonets.com/docs (check for privacy/data policy links)" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/shhdwi/docstrange", "publisherUrl": "https://clawhub.ai/shhdwi/docstrange", "owner": "shhdwi", "version": "1.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/docstrange", "downloadUrl": "https://openagent3.xyz/downloads/docstrange", "agentUrl": "https://openagent3.xyz/skills/docstrange/agent", "manifestUrl": "https://openagent3.xyz/skills/docstrange/agent.json", "briefUrl": "https://openagent3.xyz/skills/docstrange/agent.md" } }