Token导航 LogoToken导航TokenDH.com
前端设计只读github未标认证来源可访问许可证需确认审计通过

graphic-content-creation图形内容创建

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

2,685

周安装

113

GitHub Stars

142

下载量

940
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:graphic-content-creation(图形内容创建)
来源仓库:https://github.com/vivy-yi/xiaohongshu-skills
仓库路径:skills/graphic-content-creation
安装命令:
npx skills add https://github.com/vivy-yi/xiaohongshu-skills --skill graphic-content-creation
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/vivy-yi/xiaohongshu-skills --skill graphic-content-creation

简介

用于辅助文档、README、Markdown 和内容稿件的整理与改写,适合提炼结构、补齐章节或统一术语。

  • 适用于需要结构化输出、内容规范化或对外文案撰写的场景,如技术文档编写和产品说明。
  • 使用时需保留项目已有事实和命令路径,避免将未确认信息写成确定结论,对外文案应控制语气避免夸大。
  • 通过 GitHub 安装,支持 Codex、Claude、Cursor 和 Gemini CLI 等宿主环境,建议先验证权限范围。
  • 涉及对外文案时需注意语气把控,避免过度营销或能力夸大,确保信息准确性和客观性。

SKILL.md

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?"

  1. Eye-catching visual

- High contrast, bright or warm colors - Clear subject (face or product) - Minimal clutter and distraction

  1. 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)

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.21%
按下载量换算340

Claude

29.16%
按下载量换算274

Cursor

17.91%
按下载量换算168

Gemini CLI

8.73%
按下载量换算82

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills