baoyu-compress-image
baoyu-compress-image
Auto-compresses images using the best available CLI tool on the system (sips, cwebp, convert, or sharp).
This has been specifically adapted for the Obsidian Creator Vault:
- Fast Web-focused: Defaults to generating
.jpgwith65quality (perfect for most platform limits < 1MB). - Clean Vault: When run in default mode (replace), it doesn't clutter your
Assets/with_originalfiles. Instead, it backs up the original unmodified file toArchive/Original-Images/. - Dependency Sandboxing: All runtime is wrapped through
bunand isolated inside.agents/skills.
Installation & System Requirements
This script automatically detects your OS and uses the fastest and highest quality image engine it can find in this order:
-
macOS
sips(Built-in, Highly Recommended)
macOS ships withsipsnatively. No installation required.
(Under the hood:sips -s format jpeg -s formatOptions 65 <input> --out <output>) -
cwebp(Best for webp targets)- macOS:
brew install webp
- macOS:
More from tentacle-pro/skills
baoyu-post-to-wechat
Posts content to WeChat Official Account draft box via official API. Supports HTML/Markdown input, cover image upload, inline image upload, and draft saving. Use when user asks to publish article draft to WeChat.
46baoyu-markdown-to-html
Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, infographics, and optional bottom citations for external links. Use when user asks for "markdown to html", "convert md to html", "md转html", "微信外链转底部引用", or needs styled HTML output from markdown.
25baoyu-article-illustrator
Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".
24baoyu-image-gen
AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.
21baoyu-cover-image
Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".
21redbookskills
|
19