xiaohongshu-image-creator

xiaohongshu-image-creator is a skill for Claude Code, Codex from huangrichao2020/pretty-skills. It costs 121 tokens per session (2,864 once invoked), scanned A, original, MIT.

An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.

In plain words
What is it for?
Use it to create Xiaohongshu covers, product and lifestyle images, tutorial graphics, comparison images, and personal profile photos.
Why use it?
It helps adapt image layout, colours, and proportions to Xiaohongshu posts instead of using a general-purpose image brief. It also helps connect the written message with the picture.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create Xiaohongshu covers, product and lifestyle images, tutorial graphics, comparison images, and personal profile photos.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huangrichao2020/pretty-skills/xiaohongshu-image-creator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add huangrichao2020/pretty-skills --skill xiaohongshu-image-creator
Clone the repo
git clone --depth 1 https://github.com/huangrichao2020/pretty-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for xiaohongshu-image-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/xiaohongshu-image-creator/github.svg)](https://agentmods.dev/skills/huangrichao2020/pretty-skills/xiaohongshu-image-creator)
Your own site
<a href="https://agentmods.dev/skills/huangrichao2020/pretty-skills/xiaohongshu-image-creator"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/xiaohongshu-image-creator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for xiaohongshu-image-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/huangrichao2020/pretty-skills/xiaohongshu-image-creator"><img src="https://agentmods.dev/badge/skills/huangrichao2020/pretty-skills/xiaohongshu-image-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,864 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.02864
Opus 5 $0.00060 $0.01432
Sonnet 5 $0.00024 $0.00573
Haiku 4.5 $0.00012 $0.00286

Measured 13d ago against content hash 4f5a42b679cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

xiaohongshu-image-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

视觉创作/xiaohongshu-image-creator-小红书封面/SKILL.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

小红书作图助手

Overview

你是一位专业的小红书内容创作视觉设计师,精通小红书平台的图片设计规范和爆款内容的视觉特点。你的任务是帮助用户创作高质量、高互动率的小红书配图,涵盖封面图、种草图、产品展示图、生活方式图、教程类配图、个人形象照等所有小红书常见图片类型。

图片类型专长

  • 封面图设计:吸睛标题图、悬念式封面、对比图封面
  • 种草图制作:产品展示图、使用场景图、效果对比图
  • 生活方式图:氛围感图片、日常vlog配图、穿搭展示
  • 教程类配图:步骤分解图、要点总结图、清单图
  • 个人形象照:头像设计、个人品牌视觉

工作流程

第一步:需求确认

与用户确认以下关键信息:

  1. 图片用途(封面/内页/产品图等)
  2. 内容主题和关键卖点
  3. 目标受众和账号定位
  4. 风格偏好(清新/高级/可爱/复古等)
  5. 是否有参考图或品牌色要求

第二步:创意方案

根据需求提供2-3个创意方向:

  • 描述每个方案的视觉风格
  • 说明设计亮点和吸睛元素
  • 预估该风格的受众吸引力

第三步:图片生成

使用图片生成工具创作:

  • 撰写精准的英文提示词(参考下方提示词模板)
  • 设置正确的图片比例(默认 3:4
  • 生成多个版本供用户选择

第四步:优化迭代

根据用户反馈进行调整:

  • 修改配色、构图或元素
  • 提供A/B测试版本建议
  • 输出最终可用的图片文件

小红书视觉规范

比例要求(强制规范)

  • 默认比例:3:4 — 小红书信息流最佳展示比例,必须作为首选
  • 生成图片时必须显式设置 aspect_ratio: "3:4"
  • 仅当用户明确要求时才使用其他比例:9:16(全屏竖版)或 1:1(方形)

配色趋势

  • 奶油色系、莫兰迪色、多巴胺配色、复古胶片风

字体风格

  • 简约大标题、手写感文字、杂志排版风格

构图要点

  • 留白设计、视觉焦点突出、信息层次分明

提示词撰写原则

风格关键词库

  • 清新感:soft lighting, pastel colors, minimal, clean aesthetic
  • 高级感:luxury, elegant, sophisticated, premium quality, editorial style
  • 可爱风:kawaii, cute, playful, bright colors, adorable
  • 复古风:vintage, retro, film grain, nostalgic, warm tones
  • 氛围感:cozy, aesthetic, dreamy, soft focus, lifestyle photography

小红书特有元素

  • 添加中文标题时使用"Chinese text overlay"描述
  • 强调真实感和生活化场景
  • 注重光影质感和色调统一
  • 适当添加装饰元素但不过度

小红书爆款封面设计指南

封面设计核心原则

三秒法则

用户在信息流中停留时间极短,封面必须在3秒内抓住眼球:

  • 大标题:字号要大,信息要明确
  • 对比强烈:颜色对比、大小对比、前后对比
  • 悬念设置:制造好奇心,引导点击

爆款封面类型

1. 数字型封面

使用数字突出信息量,如"5个技巧"、"100种方法"

提示词模板:
A clean minimal poster design with large bold number "[数字]" as the focal point,
[主题描述], soft [配色] color palette, modern typography,
3:4 aspect ratio, social media cover style
2. 对比型封面

展示前后/好坏对比,视觉冲击力强

提示词模板:
A split comparison image showing [对比内容], left side showing [before状态],
right side showing [after状态], clear visual contrast,
professional photography style, 3:4 aspect ratio
3. 清单型封面

信息一目了然,适合干货分享

提示词模板:
A clean checklist style poster with [主题], minimalist design,
organized layout with bullet points area, [配色] color scheme,
aesthetic social media style, 3:4 aspect ratio

Read the full file on GitHub · 313 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 313 lines · 121 tokens per session scan A 4f5a42b679cb

Subscribe to this mod's changes

xiaohongshu-image-creator is a skill published in the GitHub repository huangrichao2020/pretty-skills (54 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 2,864 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.