[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77PCMP4PKCZ0MKBRDMRPC4A":3,"skill-same:01M77PCMP4PKCZ0MKBRDMRPC4A":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":49,"updatedAt":50,"install":51,"resources":63},"01M77PCMP4PKCZ0MKBRDMRPC4A","nutrient-document-processing",null,"Universal (non-OpenClaw) Nutrient DWS document-processing skill for Agent Skills-compatible products. Best for Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, OpenCode, and Copilot environments. Supports full workflows: convert PDF\u002FOffice\u002Fimages, OCR, extract text\u002Ftables\u002Fkey-values, redact PII (pattern + AI), watermark, digitally sign, form fill, merge\u002Fsplit\u002Freorder pages, and API usage\u002Fcredit checks. Prefers MCP server mode, with direct API\u002Fcurl fallback. Activates on keywords: PDF, document, convert, extract, OCR, redact, watermark, sign, merge, split, compress, form fill, document processing, MCP.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fn\u002Fnutrient-document-processing-universal\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: nutrient-document-processing\ndescription: >-\n  Universal (non-OpenClaw) Nutrient DWS document-processing skill for Agent Skills-compatible products.\n  Best for Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, OpenCode, and Copilot environments.\n  Supports full workflows: convert PDF\u002FOffice\u002Fimages, OCR, extract text\u002Ftables\u002Fkey-values, redact PII\n  (pattern + AI), watermark, digitally sign, form fill, merge\u002Fsplit\u002Freorder pages, and API usage\u002Fcredit\n  checks. Prefers MCP server mode, with direct API\u002Fcurl fallback. Activates on keywords: PDF, document,\n  convert, extract, OCR, redact, watermark, sign, merge, split, compress, form fill, document processing, MCP.\nhomepage: https:\u002F\u002Fwww.nutrient.io\u002Fapi\u002F\nrepository: https:\u002F\u002Fgithub.com\u002FPSPDFKit-labs\u002Fnutrient-agent-skill\nlicense: Apache-2.0\ncompatibility: >-\n  Requires Node.js 18+ and an internet connection. Works with Claude Code, Codex CLI, Gemini CLI,\n  OpenCode, Cursor, Windsurf, GitHub Copilot, Amp, or any Agent Skills-compatible product.\n  Alternatively, use curl for direct API access without Node.js.\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"📄\",\n        \"requires\":\n          {\n            \"anyBins\": [\"npx\", \"curl\"],\n            \"env\": [\"NUTRIENT_API_KEY\", \"NUTRIENT_DWS_API_KEY\"],\n          },\n        \"install\":\n          [\n            {\n              \"id\": \"node\",\n              \"kind\": \"node\",\n              \"package\": \"@nutrient-sdk\u002Fdws-mcp-server\",\n              \"label\": \"Install Nutrient DWS MCP Server (optional)\",\n            },\n          ],\n      },\n  }\n---\n\n# Nutrient Document Processing (Universal Agent Skill)\n\nBest for Claude Code\u002FCodex\u002FGemini\u002FCursor\u002FWindsurf and other non-OpenClaw agents. Process, convert, extract, OCR, redact, sign, and manipulate documents using the [Nutrient DWS Processor API](https:\u002F\u002Fwww.nutrient.io\u002Fapi\u002F).\n\n## Setup\n\nYou need a Nutrient DWS API key. Get one free at \u003Chttps:\u002F\u002Fdashboard.nutrient.io\u002Fsign_up\u002F?product=processor>.\n\n### Option 1: MCP Server (Recommended)\n\nIf your agent supports MCP (Model Context Protocol), use the Nutrient DWS MCP Server. It provides all operations as native tools.\n\n**Configure your MCP client** (e.g., `claude_desktop_config.json` or `.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"nutrient-dws\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@nutrient-sdk\u002Fdws-mcp-server\"],\n      \"env\": {\n        \"NUTRIENT_DWS_API_KEY\": \"YOUR_API_KEY\",\n        \"SANDBOX_PATH\": \"\u002Fpath\u002Fto\u002Fworking\u002Fdirectory\"\n      }\n    }\n  }\n}\n```\n\nThen use the MCP tools directly (e.g., `convert_to_pdf`, `extract_text`, `redact`, etc.).\n\n### Option 2: Direct API (curl)\n\nFor agents without MCP support, call the API directly:\n\n```bash\nexport NUTRIENT_API_KEY=\"your_api_key_here\"\n```\n\nAll requests go to `https:\u002F\u002Fapi.nutrient.io\u002Fbuild` as multipart POST with an `instructions` JSON field.\n\n\n## Safety Boundaries\n\n- This skill sends documents to the Nutrient DWS API (`api.nutrient.io`) for processing. Documents may contain sensitive data — ensure your Nutrient account's data handling policies are acceptable.\n- It does NOT access local files beyond those explicitly passed for processing.\n- It does NOT store API keys or credentials beyond the current session.\n- MCP server mode (`npx @nutrient-sdk\u002Fdws-mcp-server`) downloads the official Nutrient MCP server package from npm at runtime.\n- All API calls require an explicit API key — no anonymous access is possible.\n\n## Operations\n\n### 1. Convert Documents\n\nConvert between PDF, DOCX, XLSX, PPTX, HTML, and image formats.\n\n**HTML to PDF:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"index.html=@index.html\" \\\n  -F 'instructions={\"parts\":[{\"html\":\"index.html\"}]}' \\\n  -o output.pdf\n```\n\n**DOCX to PDF:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.docx=@document.docx\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.docx\"}]}' \\\n  -o output.pdf\n```\n\n**PDF to DOCX\u002FXLSX\u002FPPTX:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"output\":{\"type\":\"docx\"}}' \\\n  -o output.docx\n```\n\n**Image to PDF:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"image.jpg=@image.jpg\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"image.jpg\"}]}' \\\n  -o output.pdf\n```\n\n### 2. Extract Text and Data\n\n**Extract plain text:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"output\":{\"type\":\"text\"}}' \\\n  -o output.txt\n```\n\n**Extract tables (as JSON, CSV, or Excel):**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"output\":{\"type\":\"xlsx\"}}' \\\n  -o tables.xlsx\n```\n\n**Extract key-value pairs:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"extraction\",\"strategy\":\"key-values\"}]}' \\\n  -o result.json\n```\n\n### 3. OCR Scanned Documents\n\nApply OCR to scanned PDFs or images, producing searchable PDFs with selectable text.\n\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"scanned.pdf=@scanned.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"scanned.pdf\"}],\"actions\":[{\"type\":\"ocr\",\"language\":\"english\"}]}' \\\n  -o searchable.pdf\n```\n\nSupported languages: `english`, `german`, `french`, `spanish`, `italian`, `portuguese`, `dutch`, `swedish`, `danish`, `norwegian`, `finnish`, `polish`, `czech`, `turkish`, `japanese`, `korean`, `chinese-simplified`, `chinese-traditional`, `arabic`, `hebrew`, `thai`, `hindi`, `russian`, and more.\n\n### 4. Redact Sensitive Information\n\n**Pattern-based redaction** (preset patterns):\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"redaction\",\"strategy\":\"preset\",\"preset\":\"social-security-number\"}]}' \\\n  -o redacted.pdf\n```\n\nAvailable presets: `social-security-number`, `credit-card-number`, `email-address`, `north-american-phone-number`, `international-phone-number`, `date`, `url`, `ipv4`, `ipv6`, `mac-address`, `us-zip-code`, `vin`, `time`.\n\n**Regex-based redaction:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"redaction\",\"strategy\":\"regex\",\"regex\":\"\\\\b[A-Z]{2}\\\\d{6}\\\\b\"}]}' \\\n  -o redacted.pdf\n```\n\n**AI-powered PII redaction:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"ai_redaction\",\"criteria\":\"All personally identifiable information\"}]}' \\\n  -o redacted.pdf\n```\n\nThe `criteria` field accepts natural language (e.g., \"Names and phone numbers\", \"Protected health information\", \"Financial account numbers\").\n\n### 5. Add Watermarks\n\n**Text watermark:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"watermark\",\"text\":\"CONFIDENTIAL\",\"fontSize\":48,\"fontColor\":\"#FF0000\",\"opacity\":0.5,\"rotation\":45,\"width\":\"50%\",\"height\":\"50%\"}]}' \\\n  -o watermarked.pdf\n```\n\n**Image watermark:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F \"logo.png=@logo.png\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"watermark\",\"imagePath\":\"logo.png\",\"width\":\"30%\",\"height\":\"30%\",\"opacity\":0.3}]}' \\\n  -o watermarked.pdf\n```\n\n### 6. Digital Signatures\n\n**Sign a PDF with CMS signature:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"sign\",\"signatureType\":\"cms\",\"signerName\":\"John Doe\",\"reason\":\"Approval\",\"location\":\"New York\"}]}' \\\n  -o signed.pdf\n```\n\n**Sign with CAdES-B-LT (long-term validation):**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"sign\",\"signatureType\":\"cades\",\"cadesLevel\":\"b-lt\",\"signerName\":\"Jane Smith\"}]}' \\\n  -o signed.pdf\n```\n\n### 7. Form Filling (Instant JSON)\n\nFill PDF form fields using Instant JSON format:\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"form.pdf=@form.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"form.pdf\"}],\"actions\":[{\"type\":\"fillForm\",\"fields\":[{\"name\":\"firstName\",\"value\":\"John\"},{\"name\":\"lastName\",\"value\":\"Doe\"},{\"name\":\"email\",\"value\":\"john@example.com\"}]}]}' \\\n  -o filled.pdf\n```\n\n### 8. Merge and Split PDFs\n\n**Merge multiple PDFs:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"doc1.pdf=@doc1.pdf\" \\\n  -F \"doc2.pdf=@doc2.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"doc1.pdf\"},{\"file\":\"doc2.pdf\"}]}' \\\n  -o merged.pdf\n```\n\n**Extract specific pages:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\",\"pages\":{\"start\":0,\"end\":4}}]}' \\\n  -o pages1-5.pdf\n```\n\n### 9. Render PDF Pages as Images\n\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\",\"pages\":{\"start\":0,\"end\":0}}],\"output\":{\"type\":\"png\",\"dpi\":300}}' \\\n  -o page1.png\n```\n\n### 10. Check Credits\n\n```bash\ncurl -X GET https:\u002F\u002Fapi.nutrient.io\u002Fcredits \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\"\n```\n\n## Best Practices\n\n1. **Use the MCP server** when your agent supports it — it handles file I\u002FO, error handling, and sandboxing automatically.\n2. **Set `SANDBOX_PATH`** to restrict file access to a specific directory.\n3. **Check credit balance** before batch operations to avoid interruptions.\n4. **Use AI redaction** for complex PII detection; use preset\u002Fregex redaction for known patterns (faster, cheaper).\n5. **Chain operations** — the API supports multiple actions in a single call (e.g., OCR then redact).\n\n## Troubleshooting\n\n| Issue | Solution |\n|-------|----------|\n| 401 Unauthorized | Check your API key is valid and has credits |\n| 413 Payload Too Large | Files must be under 100 MB |\n| Slow AI redaction | AI analysis takes 60–120 seconds; this is normal |\n| OCR quality poor | Try a different language parameter or improve scan quality |\n| Missing text in extraction | Run OCR first on scanned documents |\n\n## More Information\n\n- [Full API reference](references\u002FREFERENCE.md) — Detailed endpoints, parameters, and error codes\n- [API Playground](https:\u002F\u002Fdashboard.nutrient.io\u002Fprocessor-api\u002Fplayground\u002F) — Interactive API testing\n- [API Documentation](https:\u002F\u002Fwww.nutrient.io\u002Fguides\u002Fdws-processor\u002F) — Official guides\n- [MCP Server repo](https:\u002F\u002Fgithub.com\u002FPSPDFKit\u002Fnutrient-dws-mcp-server) — Source code and issues\n","# Nutrient Document Processing (Universal Agent Skill)\n\nBest for Claude Code\u002FCodex\u002FGemini\u002FCursor\u002FWindsurf and other non-OpenClaw agents. Process, convert, extract, OCR, redact, sign, and manipulate documents using the [Nutrient DWS Processor API](https:\u002F\u002Fwww.nutrient.io\u002Fapi\u002F).\n\n## Setup\n\nYou need a Nutrient DWS API key. Get one free at \u003Chttps:\u002F\u002Fdashboard.nutrient.io\u002Fsign_up\u002F?product=processor>.\n\n### Option 1: MCP Server (Recommended)\n\nIf your agent supports MCP (Model Context Protocol), use the Nutrient DWS MCP Server. It provides all operations as native tools.\n\n**Configure your MCP client** (e.g., `claude_desktop_config.json` or `.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"nutrient-dws\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@nutrient-sdk\u002Fdws-mcp-server\"],\n      \"env\": {\n        \"NUTRIENT_DWS_API_KEY\": \"YOUR_API_KEY\",\n        \"SANDBOX_PATH\": \"\u002Fpath\u002Fto\u002Fworking\u002Fdirectory\"\n      }\n    }\n  }\n}\n```\n\nThen use the MCP tools directly (e.g., `convert_to_pdf`, `extract_text`, `redact`, etc.).\n\n### Option 2: Direct API (curl)\n\nFor agents without MCP support, call the API directly:\n\n```bash\nexport NUTRIENT_API_KEY=\"your_api_key_here\"\n```\n\nAll requests go to `https:\u002F\u002Fapi.nutrient.io\u002Fbuild` as multipart POST with an `instructions` JSON field.\n\n\n## Safety Boundaries\n\n- This skill sends documents to the Nutrient DWS API (`api.nutrient.io`) for processing. Documents may contain sensitive data — ensure your Nutrient account's data handling policies are acceptable.\n- It does NOT access local files beyond those explicitly passed for processing.\n- It does NOT store API keys or credentials beyond the current session.\n- MCP server mode (`npx @nutrient-sdk\u002Fdws-mcp-server`) downloads the official Nutrient MCP server package from npm at runtime.\n- All API calls require an explicit API key — no anonymous access is possible.\n\n## Operations\n\n### 1. Convert Documents\n\nConvert between PDF, DOCX, XLSX, PPTX, HTML, and image formats.\n\n**HTML to PDF:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"index.html=@index.html\" \\\n  -F 'instructions={\"parts\":[{\"html\":\"index.html\"}]}' \\\n  -o output.pdf\n```\n\n**DOCX to PDF:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.docx=@document.docx\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.docx\"}]}' \\\n  -o output.pdf\n```\n\n**PDF to DOCX\u002FXLSX\u002FPPTX:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"output\":{\"type\":\"docx\"}}' \\\n  -o output.docx\n```\n\n**Image to PDF:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"image.jpg=@image.jpg\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"image.jpg\"}]}' \\\n  -o output.pdf\n```\n\n### 2. Extract Text and Data\n\n**Extract plain text:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"output\":{\"type\":\"text\"}}' \\\n  -o output.txt\n```\n\n**Extract tables (as JSON, CSV, or Excel):**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"output\":{\"type\":\"xlsx\"}}' \\\n  -o tables.xlsx\n```\n\n**Extract key-value pairs:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"extraction\",\"strategy\":\"key-values\"}]}' \\\n  -o result.json\n```\n\n### 3. OCR Scanned Documents\n\nApply OCR to scanned PDFs or images, producing searchable PDFs with selectable text.\n\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"scanned.pdf=@scanned.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"scanned.pdf\"}],\"actions\":[{\"type\":\"ocr\",\"language\":\"english\"}]}' \\\n  -o searchable.pdf\n```\n\nSupported languages: `english`, `german`, `french`, `spanish`, `italian`, `portuguese`, `dutch`, `swedish`, `danish`, `norwegian`, `finnish`, `polish`, `czech`, `turkish`, `japanese`, `korean`, `chinese-simplified`, `chinese-traditional`, `arabic`, `hebrew`, `thai`, `hindi`, `russian`, and more.\n\n### 4. Redact Sensitive Information\n\n**Pattern-based redaction** (preset patterns):\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"redaction\",\"strategy\":\"preset\",\"preset\":\"social-security-number\"}]}' \\\n  -o redacted.pdf\n```\n\nAvailable presets: `social-security-number`, `credit-card-number`, `email-address`, `north-american-phone-number`, `international-phone-number`, `date`, `url`, `ipv4`, `ipv6`, `mac-address`, `us-zip-code`, `vin`, `time`.\n\n**Regex-based redaction:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"redaction\",\"strategy\":\"regex\",\"regex\":\"\\\\b[A-Z]{2}\\\\d{6}\\\\b\"}]}' \\\n  -o redacted.pdf\n```\n\n**AI-powered PII redaction:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"ai_redaction\",\"criteria\":\"All personally identifiable information\"}]}' \\\n  -o redacted.pdf\n```\n\nThe `criteria` field accepts natural language (e.g., \"Names and phone numbers\", \"Protected health information\", \"Financial account numbers\").\n\n### 5. Add Watermarks\n\n**Text watermark:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"watermark\",\"text\":\"CONFIDENTIAL\",\"fontSize\":48,\"fontColor\":\"#FF0000\",\"opacity\":0.5,\"rotation\":45,\"width\":\"50%\",\"height\":\"50%\"}]}' \\\n  -o watermarked.pdf\n```\n\n**Image watermark:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F \"logo.png=@logo.png\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"watermark\",\"imagePath\":\"logo.png\",\"width\":\"30%\",\"height\":\"30%\",\"opacity\":0.3}]}' \\\n  -o watermarked.pdf\n```\n\n### 6. Digital Signatures\n\n**Sign a PDF with CMS signature:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"sign\",\"signatureType\":\"cms\",\"signerName\":\"John Doe\",\"reason\":\"Approval\",\"location\":\"New York\"}]}' \\\n  -o signed.pdf\n```\n\n**Sign with CAdES-B-LT (long-term validation):**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\"}],\"actions\":[{\"type\":\"sign\",\"signatureType\":\"cades\",\"cadesLevel\":\"b-lt\",\"signerName\":\"Jane Smith\"}]}' \\\n  -o signed.pdf\n```\n\n### 7. Form Filling (Instant JSON)\n\nFill PDF form fields using Instant JSON format:\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"form.pdf=@form.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"form.pdf\"}],\"actions\":[{\"type\":\"fillForm\",\"fields\":[{\"name\":\"firstName\",\"value\":\"John\"},{\"name\":\"lastName\",\"value\":\"Doe\"},{\"name\":\"email\",\"value\":\"john@example.com\"}]}]}' \\\n  -o filled.pdf\n```\n\n### 8. Merge and Split PDFs\n\n**Merge multiple PDFs:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"doc1.pdf=@doc1.pdf\" \\\n  -F \"doc2.pdf=@doc2.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"doc1.pdf\"},{\"file\":\"doc2.pdf\"}]}' \\\n  -o merged.pdf\n```\n\n**Extract specific pages:**\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\",\"pages\":{\"start\":0,\"end\":4}}]}' \\\n  -o pages1-5.pdf\n```\n\n### 9. Render PDF Pages as Images\n\n```bash\ncurl -X POST https:\u002F\u002Fapi.nutrient.io\u002Fbuild \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\" \\\n  -F \"document.pdf=@document.pdf\" \\\n  -F 'instructions={\"parts\":[{\"file\":\"document.pdf\",\"pages\":{\"start\":0,\"end\":0}}],\"output\":{\"type\":\"png\",\"dpi\":300}}' \\\n  -o page1.png\n```\n\n### 10. Check Credits\n\n```bash\ncurl -X GET https:\u002F\u002Fapi.nutrient.io\u002Fcredits \\\n  -H \"Authorization: Bearer $NUTRIENT_API_KEY\"\n```\n\n## Best Practices\n\n1. **Use the MCP server** when your agent supports it — it handles file I\u002FO, error handling, and sandboxing automatically.\n2. **Set `SANDBOX_PATH`** to restrict file access to a specific directory.\n3. **Check credit balance** before batch operations to avoid interruptions.\n4. **Use AI redaction** for complex PII detection; use preset\u002Fregex redaction for known patterns (faster, cheaper).\n5. **Chain operations** — the API supports multiple actions in a single call (e.g., OCR then redact).\n\n## Troubleshooting\n\n| Issue | Solution |\n|-------|----------|\n| 401 Unauthorized | Check your API key is valid and has credits |\n| 413 Payload Too Large | Files must be under 100 MB |\n| Slow AI redaction | AI analysis takes 60–120 seconds; this is normal |\n| OCR quality poor | Try a different language parameter or improve scan quality |\n| Missing text in extraction | Run OCR first on scanned documents |\n\n## More Information\n\n- [Full API reference](references\u002FREFERENCE.md) — Detailed endpoints, parameters, and error codes\n- [API Playground](https:\u002F\u002Fdashboard.nutrient.io\u002Fprocessor-api\u002Fplayground\u002F) — Interactive API testing\n- [API Documentation](https:\u002F\u002Fwww.nutrient.io\u002Fguides\u002Fdws-processor\u002F) — Official guides\n- [MCP Server repo](https:\u002F\u002Fgithub.com\u002FPSPDFKit\u002Fnutrient-dws-mcp-server) — Source code and issues\n",{"name":5,"license":15,"homepage":24,"metadata":25,"repository":40,"description":7,"compatibility":41},"https:\u002F\u002Fwww.nutrient.io\u002Fapi\u002F",{"openclaw":26},{"emoji":27,"install":28,"requires":33},"📄",[29],{"id":30,"kind":30,"label":31,"package":32},"node","Install Nutrient DWS MCP Server (optional)","@nutrient-sdk\u002Fdws-mcp-server",{"env":34,"anyBins":37},[35,36],"NUTRIENT_API_KEY","NUTRIENT_DWS_API_KEY",[38,39],"npx","curl","https:\u002F\u002Fgithub.com\u002FPSPDFKit-labs\u002Fnutrient-agent-skill","Requires Node.js 18+ and an internet connection. Works with Claude Code, Codex CLI, Gemini CLI, OpenCode, Cursor, Windsurf, GitHub Copilot, Amp, or any Agent Skills-compatible product. Alternatively, use curl for direct API access without Node.js.","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fn\u002Fnutrient-document-processing-universal",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":52,"prompt":61,"zipAvailable":62},[53,55,58],{"tool":38,"command":54},"npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill nutrient-document-processing",{"tool":56,"command":57},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill nutrient-document-processing",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill nutrient-document-processing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fn\u002Fnutrient-document-processing-universal\u002FSKILL.md",true,[],[65,73,80,87,94,101],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]