ziguishian/xhs-visual-director-skill is an agent skill for planning and generating multi-page Xiaohongshu image posts, including their visual style, layouts, image prompts, publishing copy, and quality checks. It is aimed at creators, product teams, designers, and personal brands that want to turn topics, drafts, screenshots, or product material into coordinated social-media graphics.
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.
npx skills add ziguishian/xhs-visual-director-skill --skill skillgit clone --depth 1 https://github.com/ziguishian/xhs-visual-director-skillWrote 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.
[](https://agentmods.dev/skills/ziguishian/xhs-visual-director-skill/skill)<a href="https://agentmods.dev/skills/ziguishian/xhs-visual-director-skill/skill"><img src="https://agentmods.dev/badge/skills/ziguishian/xhs-visual-director-skill/skill.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.05522 |
| Opus 5 | $0.00038 | $0.02761 |
| Sonnet 5 | $0.00015 | $0.01104 |
| Haiku 4.5 | $0.00008 | $0.00552 |
Grade A, and why
xhs-visual-director 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
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。
使用资源
按任务需要读取项目内资源,不要一次性加载全部文档:
- 需要选择风格或解释风格依据时,读取
docs/style_system.md。 - 需要规划封面、内页、结尾页结构时,读取
docs/page_structure_rules.md。 - 需要生成图像提示词时,读取
templates/image_prompt_template.md和docs/prompt_rules.md。 - 需要审查页面高级感和可读性时,读取
templates/visual_review_checklist.md和docs/anti_patterns.md。 - 需要快速套用完整输出格式时,读取
templates/xhs_carousel_plan_template.md。 - 需要生成多页图文或多张图片时,必须先读取
docs/visual_consistency_protocol.md,并为整套图文生成“统一视觉母版”。 - 用户要求“生成图文”“开始生成”“做成小红书图片”时,默认最终交付物是图片文件,不是仅输出模板或提示词;必须先生成 1 张视觉确认图,确认后再批量生成最终图。
- 用户要求完整图文规划、生成多页图文、生成小红书图片或做视觉导演时,必须先读取
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。 - 需要参考真实案例时,优先读取
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。
触发场景
当用户提出以下请求时,应使用本 Skill:
- “帮我规划一篇小红书图文”
- “生成 8 页小红书图文”
- “把这个选题做成小红书”
- “给我封面提示词”
- “这页排版怎么优化”
- “把这个图文做得更高级”
- “按照我之前的风格生成”
- “帮我做一套 3:4 图文”
- “给我小红书标题和文案”
- “把这个内容做成图文卡片”
- “生成每一页的图像提示词”
- “帮我分析这个图文风格”
- “帮我重做这个小红书页面”
- “把这个 PPT 内容改成小红书图文”
- “把这个产品做成电商详情页图文”
- “帮我为这个选题选一种适合的风格”
默认审美规则
画幅比例
- 默认使用 3:4 竖版图文比例。
- 多页图文必须锁定同一画布比例,推荐明确写作
1080x1440px, 3:4 vertical portrait canvas。 - 每一页提示词都必须重复画幅约束:
strict 3:4 vertical portrait, not square, not landscape, no extra border, no crop。 - 适合小红书封面与内页。
- 页面不能像普通 PPT 截图,必须像社交媒体图文卡片。
- 手机端阅读优先,字不能太小,重点信息必须一眼能读懂。
整体气质
- 高级感、设计师审美、科技感、杂志感。
- 极简但有冲击力。
- 有信息架构,有内容节奏。
- 不要廉价模板感、土味营销感、默认 AI 生成图的俗气感。
常用视觉倾向
- 黑色 / 深灰 / 暗色背景。
- 白色、灰色、银色文字。
- 少量高亮色点缀,例如荧光绿、薄荷绿、电光蓝、亮橙、低饱和红。
- 玻璃拟态、液态玻璃、弥散极光、高级网格、科技线条。
- 卡片式排版、Notion-like card、深色杂志封面、现代软件官网感、高端 AI 产品发布会风格。
排版偏好
- 信息层级必须清楚。
- 标题必须有视觉冲击力。
- 不要把所有内容平均摆放。
- 要有主视觉、主标题、副标题、注释、角标、标签、结构线。
- 封面要强视觉钩子。
- 内页要递进,不要每一页长得一样。
- 使用大标题 + 小模块 + 结构图 + 视觉符号。
- 文案要短、狠、清晰。
- 避免大段文字堆积。
- 允许页面节奏变化,但色彩、字体和信息层级必须统一。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 560 lines · 76 tokens per session scan A cc85ce9a3b21
xhs-visual-director is a skill published in the GitHub repository ziguishian/xhs-visual-director-skill (1,326 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 5,522 once invoked, about $0.0004 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.