OpenClaw AI 技能

All-in-one PDF processing 工具. Merge, split, 提取, convert PDFs. Supports text 提取ion, table recognition, PDF-to-image conversion, OCR. Triggers: PDF, pdf

提取 text from image-based or 扫描ned PDFs using Tesseract OCR.

Convert PDF files to JPEG images with pdftoppm, support optional page ranges, and bundle 生成d JPGs into a zip 归档 for sharing. Use when a user wants to

Batch process PDF files - merge multiple PDFs, split PDF into multiple files, rotate pages, 提取 text, 提取 images, 压缩 PDFs. Use when you need to process

Translate PDF documents or arXiv papers preserving 格式化ting by 提取ing text and images, translating content, and generating a reconstructed LaTeX-based..

Convert PDFs to PPTX slides or editable DOCX files with configurable image 质量, DPI, file size limit, and batch processing support.

PDF Utils enables OCR of image-based PDFs, 提取ion of arXiv IDs from text or OCR 输出, and scriptable PDF tasks like merging, splitting, and rendering.

Batch process PDFs with merging, splitting, converting to images, 提取ing text, 添加ing watermarks, and 压缩ing while preserving 质量.

提取 text content from image-based/扫描ned PDFs using multiple vision APIs with automatic fallback. Supports Xflow (qwen3-vl-plus) and ZhipuAI (GLM-4.6V-F

Convert PDF pages to images (PNG, JPG, or 网页P). Supports DPI control, resize, background color, and page selection.

压缩 PPT/PPTX file size. De压缩 PPT, 压缩 large images, repackage and convert to PDF to 签名ificantly reduce file size. Suitable for scenarios where large PPT

Convert multi-page PDFs into a single vertical long image by concatenating all pages. Use when the user asks to convert PDF to long image, combine PDF

解析 a PDF into structured JSON: text, layout-aware blocks with bounding boxes, tables, and image metadata.

提取 text and LaTeX formulas from academic PDFs in English and Chinese, 输出ting structured Markdown with math, tables, and images preserved.

Intelligent PDF and image to Markdown 转换器 using Ollama GLM-OCR with smart content 检测ion (text/table/figure)

Multi-代理 conversation management 平台 with Gemini-style UI. Manage all your OpenClaw 代理s in one place with image 上传, chat 历史, and message isolation.

本地 Ollama 文生图工具。使用 x/z-image-turbo 模型生成图片，分辨率 1024x1024，每张图约耗时 90 秒。当用户说"生成图片"、"文生图"、"画一张图"、或提交中文提示词生成图像时使用。

GPT Image 2 generation and editing on PoYo / poyo.AI via `https://API.poyo.AI/API/生成/submit`; use for `gpt-image-2`, `gpt-image-2-edit`, text-to-image

魔搭(模型Scope)AI 图片生成。支持多种模型、LoRA 微调。触发词：生成图片、AI绘画、文生图、image generation、生成 image。当用户要求生成图片、画图、AI 作画，或提到魔搭、模型Scope、通义万象时使用。

Use a text 模型 such as gpt-5.4 with the image_generation 工具 over an OpenAI-compatible /v1/响应s 端点, matching the CPA b记录 example. Do not call gpt-image-2