baoyu-xhs-images

Generates Xiaohongshu image card series with configurable styles, layouts, and color palettes.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Creating engaging multi-image infographic series for Xiaohongshu (Little Red Book) requires design skills, consistent visual styling across cards, and platform-specific knowledge of hooks, layouts, and engagement patterns. This Skill automates the entire pipeline from content analysis to batch image generation. ## Core Features & Use Cases - Content-to-Cards Pipeline: Analyzes source content, recommends an outline strategy (story-driven, information-dense, or visual-first), and breaks it into 1-10 image cards with cover, content, and ending positions. - 12 Styles, 8 Layouts, 3 Palettes: Combines visual styles (cute, notion, chalkboard, screen-print, sketch-notes, etc.) with layouts (sparse, dense, list, comparison, flow, mindmap, quadrant) and optional palette overrides (macaron, warm, neon), plus 26 ready-made presets. - Visual Consistency & Batch Generation: Uses an image-1 anchor chain where the cover image anchors all subsequent cards, saves every prompt to a reproducible file, and dispatches generation in configurable batches. - Use Case: Paste a blog post about AI tools and receive a 6-card Xiaohongshu series in notion style with dense knowledge-card layouts, complete with hooks, swipe flow, and saved prompts for later edits. ## Quick Start Ask the AI to turn your article into a Xiaohongshu image card series, for example: "Generate XHS image cards from this post about productivity tools using the knowledge-card preset."

Frequently Asked Questions about baoyu-xhs-images

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

FAQPage Schema
How do I generate Xiaohongshu image cards from an article?▼

Provide your source content and the skill analyzes it, recommends a style, layout, and outline strategy, then asks for confirmation before generating. It writes one prompt file per card and renders 1-10 images using your configured image generation backend.

What styles and layouts are available for XHS infographics?▼

There are 12 styles (cute, fresh, warm, bold, minimal, retro, pop, notion, chalkboard, study-notes, screen-print, sketch-notes), 8 layouts (sparse, balanced, dense, list, comparison, flow, mindmap, quadrant), and 3 palette overrides (macaron, warm, neon). Presets like knowledge-card or tutorial combine these for common scenarios.

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 so character design, illustration style, and colors stay consistent. A shared session ID is used when the backend supports it.

Which image generation backends does it support?▼

It resolves backends in priority order: a user-specified backend, a saved preference in EXTEND.md, then auto-selection preferring runtime-native tools like Codex imagegen or Hermes image_generate, falling back to installed skills like baoyu-imagine. It never substitutes SVG or HTML rendering for raster output.

Can I skip the confirmation step and generate images directly?▼

Yes, pass --yes or say phrases like "直接生成" to skip confirmation and use EXTEND.md or built-in defaults. Otherwise the skill always confirms the recommended strategy, style, layout, palette, and image count before generating.

How do I fix wrong or garbled text in a generated card?▼

Edit the card's saved prompt file under prompts/ and regenerate from the corrected prompt with a new output path. The skill explicitly forbids patching rendered text with ImageMagick, Pillow, or other bitmap overlays.