发现优质的 AI Agent 技能

Manage Docker containers, images, and system resources.

Generate beautiful hand-drawn style diagrams rendered as PNG images.

Generate 3D models from images or text prompts for 3D printing.

Deploy complete NFT collections with permanent on-chain image storage on MegaETH mainnet.

Deploy complete NFT collections with **permanent on-chain image storage** on MegaETH testnet. All images are stored using SSTORE2 bytecode storage in a WarrenContainer, and each collection gets its own NFT contract with minting support.

``` ```python from PIL import Image from mflux.models.flux2.variants import Flux2Klein

Detect, extract, clean, and output structured tabular data from PDFs, images, HTML, and text documents as CSV, JSON, or Markdown. Handle merged cells, multi-level headers, footnotes, and multi-table documents.

Extract a complete structured professional profile from any resume or CV (PDF, image, plain text, Word/DOCX screenshot), perform a quality assessment, and optionally score it against a job description.

Extract every data point from a receipt or invoice (image, photo, PDF, or scan), categorize the expense, flag tax deductibility, detect anomalies, support multi-receipt batching, and log to an expense CSV.

Read any form (PDF, image, screenshot, printed scan), extract every fillable field, match them against the user's profile data, and produce a complete fill table with validation, missing-field prompts, and export options.

Convert a photo of a document (printed page, form, receipt, whiteboard, handwritten note, book page, ID card, etc.) into a clean, flat, professional-looking scanned image — as if produced by a real flatbed scanner. Works by detecting the document's edges, applying a perspective warp to flatten it, removing shadows, and applying scan-quality enhancement.

This skill provides a persistent, high-performance Emacs environment designed specifically for AI agents. It replaces fragmented CLI tools with a unified "Living Image" workflow.