发现优质的 AI Agent 技能

This file documents processes that repeat. **Rule: After doing something 3 times, document it here.**

**Purpose:** Document tools you use and their quirks. Save future-you hours of rediscovery.

**Purpose:** Document the specialized knowledge your AI Persona needs to do their job well.

This file documents how this AI Persona operates—the rules learned through practice, patterns that work, and lessons that became doctrine.

Some automated security scanners (e.g. VirusTotal Code Insight) may flag this skill due to heuristic pattern matching. This document explains why those flags are **false positives**.

Agentic Document Processing API — convert 10+ file formats (.jpeg, .jpg, .png, .bmp, .tiff, .pdf, .doc, .docx, .xls, .xlsx) to structured JSON/Excel with per-field confidence scores using VLM and LLM.

Best for OpenClaw users. Process documents directly in OpenClaw conversations — PDF conversion, text/table extraction, OCR, PII redaction, digital signatures, and watermarking via native `nutrient_*` tools.

Best for Claude Code/Codex/Gemini/Cursor/Windsurf and other non-OpenClaw agents. Process, convert, extract, OCR, redact, sign, and manipulate documents using the [Nutrient DWS Processor API](https://www.nutrient.io/api/).

Process documents directly in OpenClaw conversations — convert formats, extract text, apply OCR, redact PII, add signatures, and watermark files through natural language.

Supported document formats for upload (input) and download/export (output).

Practical guide for creating well-formatted documents for Nudocs.

Upload documents to Nudocs.ai for rich editing, get shareable links, and pull back the results.