Image Director
Jamailar/Beav
A skill your agent uses when the user wants to做一整套图片、组图、卡片图、轮播图、配图包或电商套图.
A skill your agent uses when planning, redesigning, or reviewing Xiaohongshu carousel visuals, covers, 3:4 image posts, page-by-page visual direction, image-generation prompts, style selection…
$ npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ziguishian/xhs-visual-director-skill xhs-visual-director --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ziguishian/xhs-visual-director-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skill .claude/skills/xhs-visual-director && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "xhs-visual-director" agent skill from https://github.com/ziguishian/xhs-visual-director-skill/tree/main/skill into .claude/skills/xhs-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xhs-visual-director", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ziguishian/xhs-visual-director-skill/tree/main/skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ziguishian/xhs-visual-director-skill xhs-visual-director --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ziguishian/xhs-visual-director-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skill .agents/skills/xhs-visual-director && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "xhs-visual-director" agent skill from https://github.com/ziguishian/xhs-visual-director-skill/tree/main/skill into .agents/skills/xhs-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xhs-visual-director", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ziguishian/xhs-visual-director-skill xhs-visual-director --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ziguishian/xhs-visual-director-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skill .cursor/skills/xhs-visual-director && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "xhs-visual-director" agent skill from https://github.com/ziguishian/xhs-visual-director-skill/tree/main/skill into .cursor/skills/xhs-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xhs-visual-director", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ziguishian/xhs-visual-director-skill.git --path skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ziguishian/xhs-visual-director-skill xhs-visual-director --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ziguishian/xhs-visual-director-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skill .gemini/skills/xhs-visual-director && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "xhs-visual-director" agent skill from https://github.com/ziguishian/xhs-visual-director-skill/tree/main/skill into .gemini/skills/xhs-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xhs-visual-director", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ziguishian/xhs-visual-director-skill xhs-visual-directorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ziguishian/xhs-visual-director-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skill .github/skills/xhs-visual-director && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "xhs-visual-director" agent skill from https://github.com/ziguishian/xhs-visual-director-skill/tree/main/skill into .github/skills/xhs-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xhs-visual-director", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ziguishian/xhs-visual-director-skill xhs-visual-director --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ziguishian/xhs-visual-director-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skill .opencode/skills/xhs-visual-director && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "xhs-visual-director" agent skill from https://github.com/ziguishian/xhs-visual-director-skill/tree/main/skill into .opencode/skills/xhs-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xhs-visual-director", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
xhs-visual-directorA skill your agent uses when planning, redesigning, or reviewing Xiaohongshu carousel visuals, covers, 3:4 image posts, page-by-page visual direction, image-generation prompts, style selection…
Xhs Visual Director is an agent skill from ziguishian/xhs-visual-director-skill. 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.
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Media & Creative, covering Copywriting and Image generation. It works with Xiaohongshu. The repository describes itself as: 这是一个用于规划小红书图文的 Agent Skill。它不是普通文案助手,而是一个“视觉导演”:先判断内容任务,再选择适合的视觉风格,最后输出完整图文结构、逐页视觉方案、图像生成提示词、发布文案和自检清单。 The licence is MIT.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 5c730c6. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Xhs Visual Director loads about 2.2k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 566 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from ziguishian/xhs-visual-director-skill at commit 5c730c6, republished under its MIT licence (© ziguishian). 566 words, ~2,192 tokens.
.claude/skills/xhs-visual-director/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.英文名:XHS Visual Director
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:
你的价值不在于“会写小红书文案”,而在于把图文审美、页面结构、视觉提示词、排版判断和发布工作流标准化。
按任务需要读取项目内资源,不要一次性加载全部文档:
docs/style_system.md。docs/page_structure_rules.md。templates/image_prompt_template.md 和 docs/prompt_rules.md。templates/visual_review_checklist.md 和 docs/anti_patterns.md。templates/xhs_carousel_plan_template.md。docs/visual_consistency_protocol.md,并为整套图文生成“统一视觉母版”。docs/socratic_questioning_protocol.md,并默认先问 10 个苏格拉底式澄清问题;用户明确说“不要提问,直接生成”时才可跳过。examples/style_reference_notes.md,再按主题读取其他 examples。如果用户只问一个很小的问题,例如“这页排版怎么优化”,不必输出完整 8 页规划;但仍要先用简短方式判断内容任务和适合风格。
当用户提出以下请求时,应使用本 Skill:
1080x1440px, 3:4 vertical portrait canvas。strict 3:4 vertical portrait, not square, not landscape, no extra border, no crop。每次开始规划图文之前,必须先输出“风格判断报告”。不要输出隐藏思考链,要输出用户可读的风格选择说明。
判断顺序:
参考风格库见 docs/style_system.md。
完整图文项目必须严格遵循四段式流程:
不要在用户回答 10 个问题之前输出完整图文规划。不要在用户确认样例图之前批量生成全部图文,除非用户明确说“不用确认,直接生成全套”。
识别用户输入属于哪一类:
同时判断任务类型。只要用户要求完整图文项目、图文规划、多页小红书、成套图片、视觉导演方案或“生成图文”,默认不要直接生成完整方案,先进入 Step 1.5。
完整图文项目必须先向用户提出 10 个苏格拉底式问题,再生成图文方案。提问目标不是收集表面偏好,而是帮助用户想清楚:
必须触发条件:
可跳过条件:
提问规则:
提问输出格式:
# 先做 10 个澄清问题
我先用 10 个问题把需求问清楚,再做多页图文规划和视觉规划。请尽量逐条回答;如果某题不确定,可以写“你来判断”。
## A. 传播目标
1. 这篇图文最想达成什么:点击、收藏、评论、转化、建立专业度,还是塑造个人 IP?
## B. 目标读者
2. 你希望谁看到这篇内容?他们现在最卡在哪里?
...回答后输出:
# 回答摘要与生成假设
- 目标受众:
- 核心观点:
- 传播目标:
- 情绪曲线:
- 推荐风格方向:
- 需要避免:
- 我将按以下假设生成:输出:
必须输出:
用户回答 10 个问题后,作为视觉导演给出多页图文规划和视觉规划。规划阶段默认输出:
然后明确推荐其中一个。
默认给 6-8 页结构。如果用户没有指定页数,默认 8 页。
常见结构:
不要机械套模板,要根据选题变化。
每一页必须同时给出内容规划和视觉规划:
生成多页图文、封面系列或每页图像提示词之前,必须先输出“统一视觉母版”。母版是后续每一页提示词的硬约束,不是可选建议。
统一视觉母版必须包含:
1080x1440px, 3:4 vertical portrait canvas。后续每一页的图像提示词必须以同一段“母版锁定前缀”开头。不要只在总说明里写一次。
在生成整套图片前,默认先生成 1 张“视觉确认图”,通常选择封面 Page 01;如果封面不是最能代表风格的页面,可以选择最关键的内页。
视觉确认图规则:
1080x1440px, strict 3:4 vertical portrait canvas。视觉确认图输出后,必须附上:
用户确认样例图 / 视觉确认图后,直接生成整套最终图片。每一页必须先完成内容字段,再用图像生成工具生成图片文件:
生成规则:
page-01.png、page-02.png 命名。图像提示词仍然必须输出或记录,作为复用和返工依据,但不能替代最终图片。每条提示词必须包含:
1080x1440px, strict 3:4 vertical portrait提示词要偏视觉导演语言,而不是空泛形容词。不要只写“高级、科技、好看”,必须说明怎么高级、怎么科技、怎么好看。
多页图文提示词额外要求:
no square image, no landscape, no inconsistent margins, no different template, no random layout shift。每次输出后,必须附带检查清单:
最后输出:
# 选题判断
# 信息充足度判断
完整图文项目默认先输出“先做 10 个澄清问题”,等待用户回答后再继续。
# 回答摘要与生成假设
# 核心观点
# 风格判断报告
## 内容类型判断
## 传播目标判断
## 读者情绪判断
## 信息密度判断
## 风格匹配结果
# 推荐风格方案
## 方案 A:点击优先
## 方案 B:收藏优先
## 方案 C:高级感 / 个人品牌优先
我的推荐:
选择方案 X。
推荐理由:
# 图文结构总览
| 页码 | 页面任务 | 标题 | 视觉关键词 | 读者情绪 | 使用风格 |
| --- | --- | --- | --- | --- | --- |
# 统一视觉母版
画布:
安全边距:
网格:
标题区:
正文区:
页码 / 角标:
色彩令牌:
字体令牌:
组件语言:
母版锁定前缀:
# 视觉确认图
确认图页面:
确认图路径:
验证点:
请用户确认:
# 逐页详细规划
## Page 01|封面
页面目标:
标题:
副标题:
核心文案:
本页使用风格:
为什么适合:
与上一页关系:
与下一页关系:
本页情绪目标:
本页信息密度:
视觉构图:
主视觉:
辅助元素:
色彩:
字体:
图像生成提示词:
负面提示词:
最终图片路径:
比例检查:
# 统一视觉规范
# 发布文案
# 自检清单最终输出必须做到:
© ziguishian, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skill of ziguishian/xhs-visual-director-skill.
Open the folder on GitHubat commit 5c730c6
Xhs Visual Director next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Xhs Visual Director this skillziguishian/xhs-visual-director-skill | 1.4k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Image DirectorJamailar/Beav | 1.8k | — | ~3.6k | Automated safety check: Pass | Custom licence | |
| Xhs Note Creatorcnfjlhj/ai-collab-playbook | 454 | — | ~638 | Automated safety check: Notes | None | |
| Cover Anchor Systemponyodong2026/ponyo-cover-anchor-system | 190 | — | ~1.1k | Automated safety check: Pass | None | |
| Xiaohongshu Cover Image GeneratorSpaceZephyr/creator-buddy | 1.6k | — | ~889 | Automated safety check: Pass | None | |
| Xiaohongshu Cover GeneratorVivixiao980/xhs-cover-skill | 204 | — | ~2.9k | Automated safety check: Pass | None |
Jamailar/Beav
A skill your agent uses when the user wants to做一整套图片、组图、卡片图、轮播图、配图包或电商套图.
cnfjlhj/ai-collab-playbook
A skill your agent uses when the user wants Xiaohongshu note materials such as the note text, cover card, body cards, or publishing-ready assets.
ponyodong2026/ponyo-cover-anchor-system
Designs Xiaohongshu and WeChat article covers around information density and a visual anchor, then writes a complete image prompt, color plan and critique.
SpaceZephyr/creator-buddy
Generates a 3:4 Xiaohongshu post cover from a topic, title and optional portrait or product photo, choosing a layout and color style and keeping the subject's likeness intact.
Vivixiao980/xhs-cover-skill
Creates and edits Xiaohongshu (RedNote) cover images from a portrait photo and text, using GPT Image 2 first and a Gemini CLI script as fallback.
NimaChu/xhs-imagen
Create complete Xiaohongshu image-and-text posts from a topic, article, document, or rough idea, including research, fact checking, post copy, pagination, storyboards, a 3:4 cover, 9:16 content…
Works with
Categories
A skill your agent uses when planning, redesigning, or reviewing Xiaohongshu carousel visuals, covers, 3:4 image posts, page-by-page visual direction, image-generation prompts, style selection…. Xhs Visual Director is an agent skill from ziguishian/xhs-visual-director-skill. 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.
Xhs Visual Director fits situations like: reviewing Xiaohongshu carousel visuals; 3:4 image posts; page-by-page visual direction; image-generation prompts.
Run `npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a claude-code`. Or copy the skill folder (skill in ziguishian/xhs-visual-director-skill) into .claude/skills/xhs-visual-director in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a codex`. Or copy the skill folder (skill in ziguishian/xhs-visual-director-skill) into .agents/skills/xhs-visual-director in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ziguishian/xhs-visual-director-skill --skill xhs-visual-director -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xhs-visual-director, .gemini/skills/xhs-visual-director, .github/skills/xhs-visual-director and .opencode/skills/xhs-visual-director in your project.
SKILL.md names no scripts, command-line tools or credentials: Xhs Visual Director is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Xhs Visual Director is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Xhs Visual Director: Image Director (Jamailar/Beav, 1.8k stars), Xhs Note Creator (cnfjlhj/ai-collab-playbook, 454 stars), Cover Anchor System (ponyodong2026/ponyo-cover-anchor-system, 190 stars) and Xiaohongshu Cover Image Generator (SpaceZephyr/creator-buddy, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ziguishian (a GitHub user) maintains it in ziguishian/xhs-visual-director-skill, which has 1,393 GitHub stars. The repository was last updated on July 3, 2026.
Source: ziguishian/xhs-visual-director-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.