# Send Nanonets OCR to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "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": { "downloadUrl": "/downloads/docstrange", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=docstrange", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "package.json", "SKILL.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "docstrange", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T12:17:29.787Z", "expiresAt": "2026-05-07T12:17:29.787Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=docstrange", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=docstrange", "contentDisposition": "attachment; filename=\"docstrange-1.0.2.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "docstrange" }, "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/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." ] } }, "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" } } ``` ## Documentation ### DocStrange by Nanonets Document extraction API — convert PDFs, images, and documents to markdown, JSON, or CSV with per-field confidence scoring. Get your API key: https://docstrange.nanonets.com/app ### Quick Start curl -X POST "https://extraction-api.nanonets.com/api/v1/extract/sync" \\ -H "Authorization: Bearer $DOCSTRANGE_API_KEY" \\ -F "file=@document.pdf" \\ -F "output_format=markdown" Response: { "success": true, "record_id": "550e8400-e29b-41d4-a716-446655440000", "status": "completed", "result": { "markdown": { "content": "# Invoice\\n\\n**Invoice Number:** INV-2024-001..." } } } ### 1. Get Your API Key # Visit the dashboard https://docstrange.nanonets.com/app Save your API key: export DOCSTRANGE_API_KEY="your_api_key_here" ### 2. OpenClaw Configuration (Optional) Recommended: Use environment variables (most secure): { skills: { entries: { "docstrange": { enabled: true, // API key loaded from environment variable DOCSTRANGE_API_KEY }, }, }, } Alternative: Store in config file (use with caution): { skills: { entries: { "docstrange": { enabled: true, env: { DOCSTRANGE_API_KEY: "your_api_key_here", }, }, }, }, } Security Note: If storing API keys in ~/.openclaw/openclaw.json: Set file permissions: chmod 600 ~/.openclaw/openclaw.json Never commit this file to version control Prefer environment variables or your agent's secret store when possible Rotate keys regularly and limit API key permissions if supported ### Extract to Markdown curl -X POST "https://extraction-api.nanonets.com/api/v1/extract/sync" \\ -H "Authorization: Bearer $DOCSTRANGE_API_KEY" \\ -F "file=@document.pdf" \\ -F "output_format=markdown" Access content: response["result"]["markdown"]["content"] ### Extract JSON Fields Simple field list: curl -X POST "https://extraction-api.nanonets.com/api/v1/extract/sync" \\ -H "Authorization: Bearer $DOCSTRANGE_API_KEY" \\ -F "file=@invoice.pdf" \\ -F "output_format=json" \\ -F 'json_options=["invoice_number", "date", "total_amount", "vendor"]' \\ -F "include_metadata=confidence_score" With JSON schema: curl -X POST "https://extraction-api.nanonets.com/api/v1/extract/sync" \\ -H "Authorization: Bearer $DOCSTRANGE_API_KEY" \\ -F "file=@invoice.pdf" \\ -F "output_format=json" \\ -F 'json_options={"type": "object", "properties": {"invoice_number": {"type": "string"}, "total_amount": {"type": "number"}}}' Response with confidence scores: { "result": { "json": { "content": { "invoice_number": "INV-2024-001", "total_amount": 500.00 }, "metadata": { "confidence_score": { "invoice_number": 98, "total_amount": 99 } } } } } ### Extract Tables to CSV curl -X POST "https://extraction-api.nanonets.com/api/v1/extract/sync" \\ -H "Authorization: Bearer $DOCSTRANGE_API_KEY" \\ -F "file=@table.pdf" \\ -F "output_format=csv" \\ -F "csv_options=table" ### Async Extraction (Large Documents) For documents >5 pages, use async and poll: Queue the document: curl -X POST "https://extraction-api.nanonets.com/api/v1/extract/async" \\ -H "Authorization: Bearer $DOCSTRANGE_API_KEY" \\ -F "file=@large-document.pdf" \\ -F "output_format=markdown" # Returns: {"record_id": "12345", "status": "processing"} Poll for results: curl -X GET "https://extraction-api.nanonets.com/api/v1/extract/results/12345" \\ -H "Authorization: Bearer $DOCSTRANGE_API_KEY" # Returns: {"status": "completed", "result": {...}} ### Bounding Boxes Get element coordinates for layout analysis: -F "include_metadata=bounding_boxes" ### Hierarchy Output Extract document structure (sections, tables, key-value pairs): -F "json_options=hierarchy_output" ### Financial Documents Mode Enhanced table and number formatting: -F "markdown_options=financial-docs" ### Custom Instructions Guide extraction with prompts: -F "custom_instructions=Focus on financial data. Ignore headers." -F "prompt_mode=append" ### Multiple Formats Request multiple formats in one call: -F "output_format=markdown,json" ### Use DocStrange For: Invoice and receipt processing Contract text extraction Bank statement parsing Form digitization Image OCR (scanned documents) ### Don't Use For: Documents >5 pages with sync (use async) Video/audio transcription Non-document images ### Best Practices Document SizeEndpointNotes<=5 pages/extract/syncImmediate response>5 pages/extract/asyncPoll for results JSON Extraction: Field list: ["field1", "field2"] — quick extractions JSON schema: {"type": "object", ...} — strict typing, nested data Confidence Scores: Add include_metadata=confidence_score Scores are 0-100 per field Review fields <80 manually ### Invoice { "type": "object", "properties": { "invoice_number": {"type": "string"}, "date": {"type": "string"}, "vendor": {"type": "string"}, "total": {"type": "number"}, "line_items": { "type": "array", "items": { "type": "object", "properties": { "description": {"type": "string"}, "quantity": {"type": "number"}, "price": {"type": "number"} } } } } } ### Receipt { "type": "object", "properties": { "merchant": {"type": "string"}, "date": {"type": "string"}, "total": {"type": "number"}, "items": { "type": "array", "items": {"type": "object", "properties": {"name": {"type": "string"}, "price": {"type": "number"}}} } } } ### Data Handling Important: Documents uploaded to DocStrange are transmitted to https://extraction-api.nanonets.com and processed on external servers. Before uploading sensitive documents: Review Nanonets' privacy policy and data retention policies: https://docstrange.nanonets.com/docs Verify encryption in transit (HTTPS) and at rest Confirm data deletion/retention timelines Test with non-sensitive sample documents first Best practices: Do not upload highly sensitive PII (SSNs, medical records, financial account numbers) until you've confirmed the service's security and compliance posture Use API keys with limited permissions/scopes if available Rotate API keys regularly (every 90 days recommended) Monitor API usage logs for unauthorized access Never log or commit API keys to repositories or examples ### File Size Limits Sync endpoint: Recommended for documents ≤5 pages Async endpoint: Use for documents >5 pages to avoid timeouts Large files: Consider using file_url with publicly accessible URLs instead of uploading large files directly ### Operational Safeguards Always use environment variables or secure secret stores for API keys Never include real API keys in code examples or documentation Use placeholder values like "your_api_key_here" in examples Set appropriate file permissions on configuration files (600 for JSON configs) Enable API key rotation and monitor usage through the dashboard ### Troubleshooting 400 Bad Request: Provide exactly one input: file, file_url, or file_base64 Verify API key is valid Sync Timeout: Use async for documents >5 pages Poll /extract/results/{record_id} Missing Confidence Scores: Requires json_options (field list or schema) Add include_metadata=confidence_score Authentication Errors: Verify DOCSTRANGE_API_KEY environment variable is set Check API key hasn't expired or been revoked Ensure no extra whitespace in API key value ### Pre-Publish Security Checklist Before publishing or updating this skill, verify: package.json declares requiredEnv and primaryEnv for DOCSTRANGE_API_KEY package.json lists API endpoints in endpoints array All code examples use placeholder values ("your_api_key_here") not real keys No API keys or secrets are embedded in SKILL.md or package.json Security & Privacy section documents data handling and risks Configuration examples include security warnings for plaintext storage File permission guidance is included for config files ### References API Docs: https://docstrange.nanonets.com/docs Get API Key: https://docstrange.nanonets.com/app Privacy Policy: https://docstrange.nanonets.com/docs (check for privacy/data policy links) ## Trust - Source: tencent - Verification: Indexed source record - Publisher: shhdwi - Version: 1.0.2 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-04-30T12:17:29.787Z - Expires at: 2026-05-07T12:17:29.787Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/docstrange) - [Send to Agent page](https://openagent3.xyz/skills/docstrange/agent) - [JSON manifest](https://openagent3.xyz/skills/docstrange/agent.json) - [Markdown brief](https://openagent3.xyz/skills/docstrange/agent.md) - [Download page](https://openagent3.xyz/downloads/docstrange)