baoyu-image-cards

Generates social media infographic image card series with configurable styles, layouts, and palettes.

Updated May 18, 2026
One-click install
npx skills add https://github.com/fts-pro/FTS-MMIS-AFRIKA --skill baoyu-image-cards-fts-pro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-image-cards
Source: https://github.com/fts-pro/FTS-MMIS-AFRIKA/tree/main/.agent/skills/baoyu-image-cards
Command: npx skills add https://github.com/fts-pro/FTS-MMIS-AFRIKA --skill baoyu-image-cards-fts-pro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Creating a cohesive series of social media infographic cards (for Xiaohongshu, WeChat, and similar platforms) requires consistent visual style, structured content breakdown, and repeated image generation, which is tedious to coordinate manually. ## Core Features & Use Cases - Multi-Dimension Customization: Combines 12 visual styles, 8 information layouts, and 3 color palettes, plus 26 ready-made presets for scenarios like knowledge cards, tutorials, and product reviews. - Structured Workflow: Analyzes source content, generates outlines via three strategies (story-driven, information-dense, visual-first), writes per-image prompt files, and batch-generates 1-10 images with an image-1 anchor chain for visual consistency. - Use Case: Paste a blog post about productivity tools and receive a 6-card Xiaohongshu series with a hook cover, dense knowledge cards, and a CTA ending, all sharing the same notion style and macaron palette. ## Quick Start Ask the assistant to turn your article into a Xiaohongshu image card series using the baoyu-image-cards skill, optionally specifying a preset such as knowledge-card.

Frequently Asked Questions about baoyu-image-cards

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a Xiaohongshu image card series from an article?▼

Provide your source content and invoke the skill; it analyzes the content, recommends a style, layout, and image count, asks for confirmation, then generates 1-10 cards. Use --yes to skip confirmation and run with defaults.

What styles and layouts are available for infographic cards?▼

The skill offers 12 styles (cute, notion, chalkboard, screen-print, sketch-notes, and others), 8 layouts (sparse, balanced, dense, list, comparison, flow, mindmap, quadrant), and 3 palette overrides (macaron, warm, neon), combinable directly or via 26 presets.

How does the skill keep images visually consistent across a series?▼

It generates the cover image first without references, then passes that image as a reference to every subsequent card, optionally combined with a shared session ID. This anchor chain keeps characters, colors, and rendering style aligned.

Which image generation backends does the skill support?▼

It resolves backends in priority order: a user-specified backend, the EXTEND.md preferred_image_backend setting, then auto-selection of a runtime-native tool such as Codex imagegen or an installed skill like baoyu-imagine. It never substitutes SVG or HTML rendering for raster output.

Can I fix wrong text on a generated image card?▼

Yes, but only by editing the saved prompt file and regenerating the image to a new output path. The skill explicitly forbids patching bitmaps with ImageMagick, Pillow, or overlay scripts to correct rendered text.

Where are user preferences like watermark and default style stored?▼

Preferences live in an EXTEND.md file checked at project, XDG config, and home directory paths. It stores watermark settings, preferred style and layout, language, image backend, and batch size, and is created through a first-time setup flow.