Graphic Content Creation logo

Graphic Content Creation

Community
vivy-yi
graphic-content-creation

Use when creating image-based posts for Xiaohongshu, designing carousel content with multiple images, structuring visual tutorials or guides, or combining photos with text overlays for storytelling

Overview

Publishervivy-yi
Repositoryxiaohongshu-skills
Skill namegraphic-content-creation
Stars
502
Forks
76
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by vivy-yi on GitHub. Read the source before you install it.

Installation

Install the Graphic Content Creation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vivy-yi/xiaohongshu-skills/tree/main/skills/01-内容创作/graphic-content-creation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Graphic Content Creation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Graphic Content Creation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Graphic Content Creation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Graphic Content Creation (图文内容创作)

Overview

Graphic content creation is designing engaging image-based posts for Xiaohongshu - combining visuals, text overlays, and storytelling flow across carousel images to create thumb-stopping content that drives saves and shares.

When to Use

Use when:

  • Creating image-based posts (most common Xiaohongshu format)
  • Designing 3-7 image carousel content
  • Structuring visual tutorials or step-by-step guides
  • Creating before-and-after comparisons
  • Designing product showcases or reviews
  • Building educational listicle content

Do NOT use when:

  • Creating video content (use short-video-production)
  • Just need basic photo editing (use xingtu-tool)
  • Designing complex graphics from scratch (use canva-tool)

Core Pattern

Before (boring single image):

❌ Single product photo with no context
❌ Wall of text, hard to read
❌ No visual hierarchy, cluttered layout
❌ Inconsistent style across images

After (engaging carousel):

✅ 3-7 image carousel with clear story flow
✅ Scannable text with key info highlighted
✅ Strong visual hierarchy and visual rhythm
✅ Consistent branding and color scheme

5 Elements of High-Performing Carousels:

  1. Hook Image - First image grabs attention instantly
  2. Story Flow - Logical progression keeps swiping
  3. Scannable Text - Easy to read at a glance
  4. Visual Hierarchy - Important info stands out
  5. Call to Action - Tells audience exactly what to do

Quick Reference

Content TypeImagesStructureBest For
Tutorial4-7Problem → Steps → ResultEducational value, saves
Product Review3-5Hook → Details → VerdictAffiliate marketing
Before/After2-4Problem → Process → SolutionTransformation content
List/Collection5-7Item 1, 2, 3... with detailsCurated recommendations
Story/Case Study4-6Context → Action → OutcomeAuthentic storytelling

Implementation

Step 1: Choose Format - Single vs Carousel

Use single image when:

  • Simple product showcase
  • Minimalist aesthetic
  • One powerful image tells complete story

Use carousel (3-7 images) when:

  • Telling story or showing process
  • Providing tutorial or step-by-step guide
  • Showing multiple products or options
  • Before-and-after comparison
  • Educational or listicle content

Pro tip: Carousels get 2-3x more engagement than single images because swiping = interaction signal to algorithm.

Step 2: Design Hook Image (Image 1)

Purpose: Stop scroll, entice swipe

Essential elements:

  1. Bold headline (3-5 words)

    • Use numbers: "5个..."
    • Create curiosity: "没想到..."
    • Make promise: "让我...的方法"
    • Ask question: "你知道...吗?"
  2. Eye-catching visual

    • High contrast, bright or warm colors
    • Clear subject (face or product)
    • Minimal clutter and distraction
  3. Text overlay (recommended)

    • Position: top or center third
    • Font: bold, white text with black outline
    • Size: large enough to read in feed without zoom

Examples of effective hooks:

✅ "这个方法让我1个月涨了5000粉" (specific result + curiosity)
✅ "学生党必看的5个平价好物" (target audience + number)
✅ "没想到这个习惯毁了皮肤" (negative curiosity hook)
✅ "坚持了30天,变化惊呆了" (timeframe + promise)

Step 3: Structure Story Flow (Images 2-6/7)

Tutorial Structure (5-7 images):

Image 1: Hook + problem statement
Image 2: Step 1 (visual + brief text)
Image 3: Step 2 (visual + brief text)
Image 4: Step 3 (visual + brief text)
Image 5: Results or before/after
Image 6: Summary + key takeaways
Image 7: Call to action

Product Review Structure (3-5 images):

Image 1: Hook + product hero shot
Image 2: Key features with callouts
Image 3: Real usage/demo photos
Image 4: Pros and cons breakdown
Image 5: Verdict + CTA (price/where to buy)

List/Collection Structure (5-7 images):

Image 1: Hook + "5个..." overview
Image 2: Item 1 with photo + key benefit
Image 3: Item 2 with photo + key benefit
Image 4: Item 3 with photo + key benefit
Image 5: Items 4-5 combined (2-3 per image)
Image 6: Comparison or summary table
Image 7: Where to buy + CTA

Key principle: Each image must add new value, not repeat. Build anticipation across carousel.

Step 4: Add Text and Annotations

Text Best Practices:

Keep it scannable:

  • Use bullet points or numbered lists
  • Bold or highlight key words
  • 3-5 bullet points maximum per image
  • Leave white space (don't fill every pixel)

Visual hierarchy:

HEADLINE (largest, boldest) - Main point
  ↓
Subheading or key benefit (medium)
  ↓
Details or explanation (small)
  ↓
Call to action (medium, distinct color)

Color and contrast:

  • High contrast = readable
  • White text on dark OR black text on light background
  • Avoid light gray on white (hard to read)
  • Test on phone screen at small size

Text placement principles:

  • Top third: Title or hook question
  • Center: Main content or product
  • Bottom third: Summary, price, or CTA
  • Avoid very edges (can be cut off on some screens)

Step 5: Optimize for Vertical Format

Xiaohongshu image specs:

  • Aspect ratio: 3:4 or 4:5 (vertical portrait)
  • Resolution: Minimum 1080x1440 pixels
  • Format: JPG or PNG
  • File size: Under 5MB for fast loading

Design mobile-first:

  • Test on actual phone screen
  • Text must be readable at small size
  • Large tap targets if any links
  • Vertical layout only (horizontal = cropped)

Common mistakes:

  • ❌ Horizontal landscape images (cut off)
  • ❌ Text too small (<24pt for body)
  • ❌ Too much text (overwhelming)
  • ❌ Low resolution (blurry when zoomed)

Step 6: Maintain Consistent Brand Style

Visual consistency across carousel:

  • Color palette: 2-3 main colors (e.g., coral #FF6B6B + teal #4ECDC4)
  • Fonts: Same 1-2 fonts throughout
  • Layout: Similar header/footer on each image
  • Branding: Logo or watermark in consistent position

Build your brand style template:

Color scheme:
- Primary: [main brand color]
- Secondary: [accent color]
- Background: [consistent background]

Typography:
- Headlines: [bold font]
- Body: [readable font]

Layout template:
- Image 1: Full-bleed + overlay text
- Images 2-6: 80% content + 20% footer
- Final image: Summary + CTA

Pro tip: Create Canva or Xingtu templates for each content type to ensure consistency.

Step 7: Add Strong Call to Action

Final image CTA examples:

  • "关注我,每天分享干货"
  • "点赞❤️收藏🌟,下次想看容易找到"
  • "评论区告诉我你的看法"
  • "试试看,回来告诉我效果如何"
  • "点击主页查看更多" (for driving traffic)

CTA best practices:

  • Clear and specific (not vague "follow for more")
  • Single CTA (not multiple competing actions)
  • Action-oriented verb
  • Benefit-driven (why should they do it)
  • Add emoji for visual appeal

Common Mistakes

MistakeWhy HappensFix
Too many imagesWant to show everythingLimit to 3-7, quality > quantity
Wall of textFear of missing infoUse bullets, highlight keywords only
No visual hierarchyEverything seems importantMake 1-2 things stand out per image
Inconsistent styleCreating in hasteUse templates, predefined colors
Weak hook imageRush through first imageInvest 50% effort in hook image
No story flowJust listing imagesStructure: beginning, middle, end
Text too smallLooks good on desktopTest on phone, use minimum 24pt

Real-World Impact

High-performing carousel examples (real data):

  • "5步 skincare routine" tutorial (5 images) → 50K saves (actionable value)
  • Before-after skin journey (3 images) → 30K shares (dramatic transformation)
  • "Student budget beauty" list (7 images) → 80K likes (curated, relatable)
  • Step-by-step cooking guide (6 images) → 40K saves (educational)

Poor-performing content:

  • Single product photo, no context → 200 views (boring)
  • 10-image random collection → 300 views (too long, no story)
  • Text-heavy tutorial, small font → 150 views (hard to consume)

Key metric: Well-structured carousels with clear story flow get 3-5x more saves than random image collections.


Related Skills:

  • REQUIRED: account-positioning (content must align with positioning)
  • REQUIRED: xingtu-tool (edit and enhance photos)
  • REQUIRED: cover-design (first image is critical)
  • content-planning (plan content topics and calendar)
  • title-writing (compelling title for post)
  • hashtag-optimization (add relevant topic tags)

Frequently asked questions

What does the Graphic Content Creation AI skill do?

Use when creating image-based posts for Xiaohongshu, designing carousel content with multiple images, structuring visual tutorials or guides, or combining photos with text overlays for storytelling

Why use Graphic Content Creation on TypingMind?

Because you install it once and use it with any model. Graphic Content Creation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Graphic Content Creation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vivy-yi/xiaohongshu-skills/tree/main/skills/01-内容创作/graphic-content-creation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Graphic Content Creation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Graphic Content Creation?

As many as you like. As long as a model supports skills, you can use Graphic Content Creation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Graphic Content Creation AI skill free?

It is published on GitHub by vivy-yi. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇