苍何

32 skills · 36,243 GitHub stars

Sharing thoughtful insights on AI, building cool things along the way.· Founder @ WeSight · Microsoft MVP

Canghe, known on GitHub as 苍何, is the founder of WeSight and a Microsoft MVP whose skills equip AI agents to produce knowledge and educational comics, Xiaohongshu infographic series, formatted Markdown and Obsidian notes, and stylized comic-style videos. The most popular skills also cover Gemini-based image generation, PaddleOCR document parsing, and image compression to WebP or PNG.

Awesome Gpt Image 2

1 skills · 35,529 stars · MIT

Gpt Image 2 Style Library Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gp…

Canghe Skills

29 skills · 475 stars

Canghe Article Illustrator Analyzes article structure, identifies positions requiring visual aids, generates illustrations w…
Canghe Comic Knowledge comic creator supporting multiple art styles and tones.
Canghe Compress Image Compresses images to WebP (default) or PNG with automatic tool selection.
Canghe Cover Image Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining…
Canghe Danger Gemini Web Generates images and text via reverse-engineered Gemini Web API.
Canghe Danger X To Markdown Converts X (Twitter) tweets and articles to markdown with YAML front matter.
Canghe Format Markdown Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists,…
Canghe Image Gen AI image generation with OpenAI, Google, DashScope and Canghe APIs.
Canghe Infographic Generates professional infographics with 20 layout types and 17 visual styles.
Canghe Markdown To Html Converts Markdown to styled HTML with WeChat-compatible themes.
Canghe Post To Wechat Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP.
Canghe Post To X Posts content and articles to X (Twitter).
Canghe Slide Deck Generates professional slide deck images from content.
Canghe Tianyancha Generates Tianyancha-style company and industry insight dashboards from researched enterprise data.
Canghe Url To Markdown Fetch any URL and convert to markdown using Chrome CDP.
Canghe Xhs Images Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts.
Douyin Downloader 抖音无水印视频下载和文案提取工具
Flyworks Avatar Video Generate videos using Flyworks (a.k.a HiFly) Digital Humans.
Json Canvas Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections.
Manga Drama 漫剧生成器 - 基于 Seedance 的漫画风格短剧生成工具。支持以主角图片为基础，自动生成漫剧分镜脚本并生成视频。适用于创作漫画风格的短视频、角色故事、动画短片等。当用户想要生成漫画风格的视…
Manga Style Video 漫画风格视频生成器 - 专门生成日式治愈系、国风水墨、美式卡通等漫画风格的动画视频。内置8种漫画风格模板，支持图生视频，一键生成高质量漫画动画。当用户需要生成漫画风格、动画风格、手绘风格的视频时…
Obsidian Bases Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries.
Obsidian Markdown Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and othe…
Paddleocr Doc Parsing Advanced document parsing with PaddleOCR.
Release Skills Universal release workflow.
Remotion Best Practices Best practices for Remotion - Video creation in React
Seedance Video 使用字节跳动 Seedance 模型生成视频。支持文生视频和图生视频功能，通过 volcengine-ark SDK 调用 API。当用户需要生成视频、创建视频内容或基于文字/图片制作视频时激活…
Seedance Video Generate AI videos using ByteDance Seedance.
Volcengine Video Understanding 火山视频理解 - 使用火山方舟视频理解 API 分析视频内容。通过 Files API 上传视频（推荐），支持大文件（最大512MB），可用于视频内容分析、物体识别、动作理解等。当用户需要分析视…