Three tested AI image styles in one free skill. Name a style and a subject, get a copy-ready prompt that works in any image tool.
一整包文件丟進去,吐出一本 Excel:每一格都查得回它出自哪份檔案、原文怎麼寫(PDF 另附頁碼),並附 0 到 1 的信心分數;低分自動隔離進待覆核表,不混進你要直接用的乾淨資料。Drop in a zip of messy documents, get back one spreadsheet where every cell traces back to the file and the sentence it came from — with a page number for paged PDFs — plus a confidence score. Low-confidence rows are quarantined into a review sheet instead of quietly contaminating your clean data.
Plan image enlargement, output dimensions and quality checks for web, print and product listings. Website: https://upscayl.app/ Downloadable planning skill; image processing and API credits are not included.
Drop in a folder of product photos. The local rembg AI model removes the background and saves transparent PNGs, then Pillow crops to the subject, centers it on a 1000x1000 canvas with a set margin, adds a soft ground shadow and composites it over white, ivory, mint, peach or other presets. A summary CSV with subject bbox and file size helps you catch bad crops. Runs fully locally, no API key.
把每一張名片，變成下一筆生意的起點。上傳名片照片或 PDF，自動整理成乾淨、可直接使用的聯絡人清單：中文、英文與中英雙語名片都能處理，正反面與重複聯絡人自動合併，不確定的資訊標記出來等你複查，並直接產出 Excel 與 CSV。想更進一步？切換到分析模式：依產業為公司分類、研究公開資訊、比對你的公司與對方的商務契合度，具體告訴你該聯繫誰、為什麼聯繫、下一步怎麼開口，還附上跟進信件草稿。只分析公司與組織，不側寫個人。
Turn Excel or CSV research data into editable Origin projects, publication-ready figures, reusable templates, and QA reports.
Tidy any folder on your computer. An AI agent reads each file and renames it by real date, type and counterparty, e.g. 2025-02-05_invoice_acme_123.pdf. You review and edit everything in a local browser page before anything changes, can sort files into folders, and find them later by type, counterparty or year. Every session can be undone. Runs on your computer with Claude Code, Codex or OpenClaw; needs Python 3.8+.
Download package that runs on your own computer inside your AI agent (e.g. Claude Code or Codex — its subscription/API costs are yours). Requires Python 3.9+ with pdfplumber, openpyxl and pypdfium2. No third-party services or API keys; PDFs are never uploaded. Turns PDF tables into a clean Excel/CSV with real numbers, stitches multi-page tables, then re-checks every cell, column sum and total row against the PDF. Scanned pages are read by your agent.