Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Nutrient DWS API を使用してドキュメントの処理、変換、OCR、抽出、編集、署名、フォーム入力を行います。PDF、DOCX、XLSX、PPTX、HTML、画像に対応しています。
.claude/skills/loulanyue-nutrient-document-processing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 153% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 223% | 0% |
> Note: This skill integrates with the Nutrient commercial API. Review their terms before use.
Process documents with the Nutrient DWS Processor API. Convert formats, extract text and tables, OCR scanned documents, redact PII, add watermarks, digitally sign, and fill PDF forms.
Get a free API key at nutrient.io
bashexport NUTRIENT_API_KEY="pdf_live_..."
All requests go to https://api.nutrient.io/build as multipart POST with an instructions JSON field.
bash# DOCX to PDF curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "document.docx=@document.docx" \ -F 'instructions={"parts":[{"file":"document.docx"}]}' \ -o output.pdf # PDF to DOCX curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "document.pdf=@document.pdf" \ -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"docx"}}' \ -o output.docx # HTML to PDF curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "index.html=@index.html" \ -F 'instructions={"parts":[{"html":"index.html"}]}' \ -o output.pdf
Supported inputs: PDF, DOCX, XLSX, PPTX, DOC, XLS, PPT, PPS, PPSX, ODT, RTF, HTML, JPG, PNG, TIFF, HEIC, GIF, WebP, SVG, TGA, EPS.
bash# Extract plain text curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "document.pdf=@document.pdf" \ -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"text"}}' \ -o output.txt # Extract tables as Excel curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "document.pdf=@document.pdf" \ -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"xlsx"}}' \ -o tables.xlsx
bash# OCR to searchable PDF (supports 100+ languages) curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "scanned.pdf=@scanned.pdf" \ -F 'instructions={"parts":[{"file":"scanned.pdf"}],"actions":[{"type":"ocr","language":"english"}]}' \ -o searchable.pdf
Languages: Supports 100+ languages via ISO 639-2 codes (e.g., eng, deu, fra, spa, jpn, kor, chi_sim, chi_tra, ara, hin, rus). Full language names like english or german also work. See the complete OCR language table for all supported codes.
bash# Pattern-based (SSN, email) curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "document.pdf=@document.pdf" \ -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"social-security-number"}},{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"email-address"}}]}' \ -o redacted.pdf # Regex-based curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "document.pdf=@document.pdf" \ -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"regex","strategyOptions":{"regex":"\\b[A-Z]{2}\\d{6}\\b"}}]}' \ -o redacted.pdf
Presets: social-security-number, email-address, credit-card-number, international-phone-number, north-american-phone-number, date, time, url, ipv4, ipv6, mac-address, us-zip-code, vin.
bashcurl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "document.pdf=@document.pdf" \ -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"watermark","text":"CONFIDENTIAL","fontSize":72,"opacity":0.3,"rotation":-45}]}' \ -o watermarked.pdf
bash# Self-signed CMS signature curl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "document.pdf=@document.pdf" \ -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"sign","signatureType":"cms"}]}' \ -o signed.pdf
bashcurl -X POST https://api.nutrient.io/build \ -H "Authorization: Bearer $NUTRIENT_API_KEY" \ -F "form.pdf=@form.pdf" \ -F 'instructions={"parts":[{"file":"form.pdf"}],"actions":[{"type":"fillForm","formFields":{"name":"Jane Smith","email":"jane@example.com","date":"2026-02-06"}}]}' \ -o filled.pdf
For native tool integration, use the MCP server instead of curl:
json{ "mcpServers": { "nutrient-dws": { "command": "npx", "args": ["-y", "@nutrient-sdk/dws-mcp-server"], "env": { "NUTRIENT_DWS_API_KEY": "YOUR_API_KEY", "SANDBOX_PATH": "/path/to/working/directory" } } } }
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 11,657 | 5,940 | -49% | 1 | 1 | 0% | 2,311 | 3,101 | +34% | 0 | 0 | — |
case-02 | fail→pass | 8,296 | 4,754 | -43% | 1 | 1 | 0% | 1,699 | 2,787 | +64% | 0 | 0 | — |
case-03 | fail→pass | 5,835 | 3,907 | -33% | 1 | 1 | 0% | 1,027 | 2,597 | +153% | 0 | 0 | — |
case-04 | pass→pass | 7,529 | 3,711 | -51% | 1 | 1 | 0% | 1,456 | 2,584 | +77% | 0 | 0 | — |
case-05 | fail→pass | 11,555 | 5,795 | -50% | 1 | 1 | 0% | 2,143 | 2,979 | +39% | 0 | 0 | — |
case-06 | fail→pass | 4,398 | 2,551 | -42% | 1 | 1 | 0% | 722 | 2,335 | +223% | 0 | 0 | — |
case-07 | fail→pass | 6,338 | 4,831 | -24% | 1 | 1 | 0% | 1,313 | 2,807 | +114% | 0 | 0 | — |
case-08 | fail→pass | 4,939 | 2,759 | -44% | 1 | 1 | 0% | 853 | 2,315 | +171% | 0 | 0 | — |
case-13 | fail→pass | 7,893 | 3,718 | -53% | 1 | 1 | 0% | 1,521 | 2,585 | +70% | 0 | 0 | — |
case-09 | fail→pass | 13,349 | 4,405 | -67% | 1 | 1 | 0% | 2,615 | 2,632 | +1% | 0 | 0 | — |
case-10 | pass→pass | 3,872 | 2,562 | -34% | 1 | 1 | 0% | 606 | 2,301 | +280% | 0 | 0 | — |
case-11 | pass→pass | 8,847 | 3,142 | -64% | 1 | 1 | 0% | 1,783 | 2,429 | +36% | 0 | 0 | — |
case-12 | fail→pass | 11,213 | 3,204 | -71% | 1 | 1 | 0% | 2,028 | 2,446 | +21% | 0 | 0 | — |
case-14 | pass→pass | 4,697 | 2,877 | -39% | 1 | 1 | 0% | 870 | 2,442 | +181% | 0 | 0 | — |
case-15 | fail→pass | 6,197 | 3,130 | -49% | 1 | 1 | 0% | 1,177 | 2,439 | +107% | 0 | 0 | — |
case-16 | pass→pass | 10,155 | 3,423 | -66% | 1 | 1 | 0% | 1,611 | 2,505 | +55% | 0 | 0 | — |
case-17 | fail→pass | 11,521 | 3,895 | -66% | 1 | 1 | 0% | 2,265 | 2,690 | +19% | 0 | 0 | — |
case-18 | pass→pass | 4,511 | 1,705 | -62% | 1 | 1 | 0% | 801 | 2,124 | +165% | 0 | 0 | — |
case-19 | fail→pass | 6,988 | 2,425 | -65% | 1 | 1 | 0% | 1,267 | 2,310 | +82% | 0 | 0 | — |
case-20 | pass→pass | 14,305 | 7,183 | -50% | 1 | 1 | 0% | 2,410 | 3,025 | +26% | 0 | 0 | — |
case-21 | pass→pass | 14,713 | 6,414 | -56% | 1 | 1 | 0% | 2,463 | 2,878 | +17% | 0 | 0 | — |
case-22 | pass→pass | 11,993 | 8,448 | -30% | 1 | 1 | 0% | 1,812 | 3,103 | +71% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +59 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.