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 sanhuang520-ship-it/awesome-chinese-ai-tools --skill guochao-visual-cngit clone --depth 1 https://github.com/sanhuang520-ship-it/awesome-chinese-ai-toolsWrote 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/sanhuang520-ship-it/awesome-chinese-ai-tools/guochao-visual-cn)<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/guochao-visual-cn"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/guochao-visual-cn/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.
<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/guochao-visual-cn"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/guochao-visual-cn.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00099 | $0.02300 |
| Opus 5 | $0.00049 | $0.01150 |
| Sonnet 5 | $0.00020 | $0.00460 |
| Haiku 4.5 | $0.00010 | $0.00230 |
Grade A, and why
guochao-visual-cn 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 12d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
国潮视觉助手
解决的问题:想要"中国风",但生成出来是日式和风、或者塑料感的伪国风。
原因通常是提示词里只写了 "Chinese style"——这个词太宽,模型会往日漫或泛东方风格上跑。必须指定具体的美学传统。
什么时候用
国潮插画、古风头像、传统文化海报、国漫风格图、新中式设计、汉服人物、节气配图、品牌国潮联名、公众号国风配图。
第一步:先问清 3 件事
- 用在哪(头像 / 海报 / 公众号配图 / 电商主图 / 短视频封面)—— 决定构图和比例
- 要哪种"中国风"(下面 12 种给他选,或描述感觉让你判断)
- 主体内容(人物?场景?物件?具体是什么)
⚠️ 用户说"就要中国风"时,不要直接生成。先给他看下面的风格对照,让他选—— 这是出图质量的关键分水岭。
12 种中国美学画风配方
一、传统绘画类
1. 水墨写意
- 特征:留白大、笔触洒脱、墨分五色、意到笔不到
- 适合:山水、竹石、禅意、茶文化
- 提示词核心:
Chinese ink wash painting, xieyi freehand style, generous negative space, varied ink tones from pale wash to deep black, expressive brushstrokes, rice paper texture - ⚠️ 避免:过度细节、饱和色彩
2. 工笔重彩
- 特征:线条精细、层层渲染、色彩浓丽、一丝不苟
- 适合:花鸟、仕女、宫廷题材、精致产品图
- 提示词核心:
Chinese gongbi painting, meticulous fine-line brushwork, layered mineral pigments, ornate detail, silk scroll texture - ⚠️ 避免:写意笔触、留白过多
3. 青绿山水
- 特征:石青石绿为主、金线勾勒、装饰性强
- 适合:大场景、国潮海报、文旅宣传
- 提示词核心:
Chinese blue-green landscape painting, azurite and malachite mineral pigments, gold outline, layered mountains, decorative composition - 参考感觉:《千里江山图》的色彩体系
4. 敦煌壁画
- 特征:土红/石青/土黄、飞天飘带、装饰性图案、斑驳质感
- 适合:文化 IP、神话题材、国潮联名
- 提示词核心:
Dunhuang mural style, earthy ochre and azurite palette, flying apsaras with flowing ribbons, weathered wall texture, Tang dynasty decorative patterns
二、民间艺术类
5. 年画
- 特征:色彩鲜艳(大红/明黄/翠绿)、人物饱满、寓意吉祥、平面化
- 适合:春节、喜庆主题、复古国潮
- 提示词核心:
Chinese New Year woodblock print style, vivid red yellow green palette, plump auspicious figures, flat decorative composition, folk art
6. 剪纸
- 特征:单色(多为红)、镂空、对称、线条连续
- 适合:节日、极简设计、图标
- 提示词核心:
Chinese paper-cut art, single red color on white, intricate symmetrical negative space, continuous connected lines, silhouette style
7. 皮影
- 特征:剪影、关节分明、暖光透射感、装饰镂空
- 适合:叙事插画、戏剧感场景
- 提示词核心:
Chinese shadow puppet style, backlit translucent silhouette, jointed figures, ornate cutout patterns, warm amber glow
三、现代国潮类
8. 国潮插画(新国货风)
- 特征:传统元素 + 现代平面设计、高饱和撞色、几何化重构
- 适合:品牌营销、包装、电商主图
- 提示词核心:
modern Chinese guochao illustration, traditional motifs reimagined in flat geometric shapes, bold contrasting colors, contemporary graphic design - ⚠️ 这是最容易做"塑料"的一种,关键是传统元素要具体(不是泛泛的"龙凤祥云")
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.
- 12d ago First seen · 154 lines · 99 tokens per session scan A 8380658a632d
guochao-visual-cn is a skill published in the GitHub repository sanhuang520-ship-it/awesome-chinese-ai-tools (10 stars, last pushed 8d ago), licensed MIT. It adds 99 tokens to every session and 2,300 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
shortfilm-prompt
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell…
prompt-sensei
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.
prompt-engineer
Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other…
shipkit-prompt-audit
Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.
claude-5-best-practice
Route Claude 5 tiers (Haiku/Sonnet 5/Opus 5/Fable 5), effort, and subagents for cost-effective accepted results, and handle Claude 5 prompting, long-running execution, API behavior, refusals, and fallback.
prompt-forge
Engineers and optimizes prompts for LLMs: system prompts, few-shot examples, chain-of-thought structures, agent personas, and evaluation frameworks. Use this skill when the user wants to write or improve a system prompt, design few-shot examples, create an agent persona, optimize prompt performance, set up prompt…