XHS Visual Director
A visual-director skill for Xiaohongshu carousels: style choice, page structure, image prompts and the post caption
Low risk
We rate an entry low when it mostly gives the agent instructions and reference material.
Why this level
- The skill consists of instructions, a style library and templates; images are produced by the agent's model
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/xhs-visual-directorDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run in a terminal in the project folder
npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a claude-code -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5c730c6
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .claude/skills
cp -R "$tmp/skill" .claude/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a cursor -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5c730c6
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .agents/skills
cp -R "$tmp/skill" .agents/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a github-copilot -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5c730c6
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .github/skills
cp -R "$tmp/skill" .github/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a codex -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5c730c6
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .agents/skills
cp -R "$tmp/skill" .agents/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a gemini-cli -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5c730c6
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .agents/skills
cp -R "$tmp/skill" .agents/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .devin/skills
cp -R "$tmp/skill" .devin/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Formerly Windsurf.
Run in a terminal in the project folder
npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a cline -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5c730c6
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .cline/skills
cp -R "$tmp/skill" .cline/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a roo -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5c730c6
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .roo/skills
cp -R "$tmp/skill" .roo/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
A fork of Roo Code, same .roo folders.
Run in a terminal in the project folder
npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a opencode -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 5c730c6
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .agents/skills
cp -R "$tmp/skill" .agents/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .agents/skills
cp -R "$tmp/skill" .agents/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/ziguishian/xhs-visual-director-skill.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /skill/
git -C "$tmp" checkout 5c730c688f2c7e64f798d611608997ffba43813d
mkdir -p .agents/skills
cp -R "$tmp/skill" .agents/skills/xhs-visual-directorCommands for macOS and Linux, on Windows run them in Git Bash.
Clone the repository git clone https://github.com/ziguishian/xhs-visual-director-skill.git and register the skill/ folder with its SKILL.md as a skill. Keep the repository in place so the docs, templates and examples folders referenced by SKILL.md stay reachable.
Other ways from the author
git clone https://github.com/ziguishian/xhs-visual-director-skill.gitRegister the repository's skill/ folder, which holds SKILL.md, as a skill. Keep the root docs, templates and examples: SKILL.md references them at runtime.
This is third-party code. Review the repository files before installing.
What it does
The skill turns the agent into a senior visual director for Xiaohongshu image posts rather than a plain copy assistant. It first identifies the content type and the post's goal, then asks ten Socratic clarifying questions to pin down purpose, audience and the core message. After the answers it produces a style-decision report, three style options with a recommended one, then a six-to-eight page structure and a shared visual master. The skill first generates one sample cover for confirmation, and after sign-off assembles the full image set with prompts, a title, caption, tags and a self-check list. The style library, layout rules, anti-patterns and templates live in the docs, templates and examples folders.
Who it is for. For Xiaohongshu creators, designers, marketers and content makers who need readable, non-generic image posts.
Good fit when
- You need to plan a six-to-eight page Xiaohongshu post with a cover and inner pages
- You need to choose a visual style for the topic and explain why it fits
- You need image prompts with a fixed 3:4 frame and readable text
Not a fit when
- You only need a short caption without visual planning
- The format is not Xiaohongshu and vertical 3:4 carousels are not needed
Example request
Make an eight-page Xiaohongshu post about Vibe Coding, high-end with a tech mood, no cheap template lookLimitations
The skill is made of instructions, a style library and templates, while the images are produced by whatever generation model the agent has. Its material and output are aimed at a Chinese audience and Chinese text. If the model renders Chinese characters unreliably, the skill advises preparing a clean visual base and overlaying text separately. Quality depends on how fully the user answers the ten questions.
How to disable. Remove the skill folder from your agent's skills directory and delete the cloned repository.
Security check
- The skill consists of instructions, a style library and templates; images are produced by the agent's model
README in short
The README describes the skill as a visual director for Xiaohongshu image posts that first asks ten Socratic questions, then plans pages and style, shows a sample and, after confirmation, generates the full image set with prompts and the post copy. It shows cover examples, a table of topics and recommended styles, the target audience and the problems the skill solves. The installable skill body lives in the skill/ folder with SKILL.md and agents/openai.yaml, while the root docs, templates and examples are resources for extension and maintenance. It documents the 3:4 frame rules, style preferences, anti-patterns and how to add your own styles. MIT licensed.
SKILL.md
--- name: xhs-visual-director description: Use this skill when planning, redesigning, or reviewing Xiaohongshu carousel visuals, covers, 3:4 image posts, page-by-page visual direction, image-generation prompts, style selection, layout critique, or XHS captions. It acts as a senior visual director for 小红书图文, not a generic copywriting assistant. --- # 小红书高级图文视觉导演 英文名：XHS Visual Director ## Skill 定位 你是“小红书高级图文视觉导演”，不是普通小红书文案助手。你的核心任务是把用户输入的选题、观点、草稿、截图、产品图、参考图、已有页面或排版优化需求，转化为完整的小红书图文视觉方案。 你必须同时处理： - 内容定位 - 选题拆解 - 传播目标判断 - 读者情绪判断 - 风格选择 - 页面结构规划 - 信息层级设计 - 每页视觉构图 - 图像生成提示词 - 风格一致性检查 - 小红书标题、正文、标签和评论区引导 - 页面是否高级、是否可读、是否有收藏价值的审查
FAQ
Do I have to answer the ten questions?
For a full project yes, they drive the style and structure choice. For a small request, such as fixing one page, you can tell it to skip questions and generate directly.
Does the skill deliver images or only prompts?
By default the result is image files. It first makes one sample for confirmation, then assembles the full set.
Related
A skill that strips AI writing tells from text using Wikipedia's list, without adding invented facts
Marketing Skills for AI agents
Marketing Skills for AI Agents
About fifty skills for CRO, copywriting, SEO, analytics, ads and launches, built for coding agents
SendPulse MCP server
SendPulse MCP
SendPulse's official remote MCP server: statistics, campaigns and user data through an agent chat
Yandex Direct MCP generated from a machine-readable schema
yandex-direct-mcp
An MCP server and CLI covering all 113 Yandex Direct API v5 methods generated from WSDL, exposing 9 read tools by default and writes only on demand