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 balabalabalading/huuuuuuho-skills --skill ardot-style-guidegit clone --depth 1 https://github.com/balabalabalading/huuuuuuho-skillsWrote 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/balabalabalading/huuuuuuho-skills/ardot-style-guide)<a href="https://agentmods.dev/skills/balabalabalading/huuuuuuho-skills/ardot-style-guide"><img src="https://agentmods.dev/badge/skills/balabalabalading/huuuuuuho-skills/ardot-style-guide/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/balabalabalading/huuuuuuho-skills/ardot-style-guide"><img src="https://agentmods.dev/badge/skills/balabalabalading/huuuuuuho-skills/ardot-style-guide.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 | $0.00123 | $0.01657 |
| Opus 5.5 | $0.00049 | $0.00663 |
| Sonnet 5.5 | $0.00025 | $0.00331 |
| Haiku 4.5 | $0.00012 | $0.00166 |
Grade A, and why
ardot-style-guide 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 2mo 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ardot-style-guide — 样式指南搜索与构建
通过 search_style_guide → build_style_guide 工具链发现和应用完整的设计系统。Ardot 独有的能力,Figma 没有等效功能。
技能边界
- 当用户想要从头建立视觉风格时使用此技能
- 在任何创建带样式 UI(颜色、排版)的
batch_edit之前使用此技能 - 如果用户已有已建立的设计系统和已知令牌,可跳过此技能
build_style_guide的输出是权威性的 — 所有下游工具必须严格遵循其值
前置条件
- 必须已调用
fetch_editor_state(includeSchema: true) - 应为目标设计类型加载
fetch_guidelines(topic)
search_style_guide — 三轮回退协议
第一轮:关键词搜索
提供特定关键词以定位用户意图。
search_style_guide({
"topic": "landing-page", // 或 web-app、mobile-app、slides、table
"designKeywords": "SaaS dashboard modern clean professional",
"colorKeywords": "dark mode cool blue professional",
"typographyKeywords": "modern sans-serif clean readable",
"layoutKeywords": "dashboard analytics cards grid"
})
收到结果后,逐一审查每个领域:
- style:样式类别是否与请求的视觉风格匹配?
- color:检查背景、卡片和前景值。如果用户想要深色模式但所有背景值都是浅色(#F_xxxx 范围),则此领域没有合适匹配。
- typography:情绪是否匹配?字体是否可用(使用
get_available_fonts检查)? - layout:模式是否适合页面类型?
如果某个领域的所有候选都合适 → 继续到 build_style_guide。
第二轮:完整目录(如果任何领域没有合适匹配)
对于第一轮没有合适匹配的领域,再次调用 search_style_guide,对该领域的关键词使用 true 以获取完整目录:
search_style_guide({
"topic": "landing-page",
"designKeywords": "SaaS dashboard",
"colorKeywords": true, // 颜色的完整目录
"typographyKeywords": true // 排版的完整目录
})
第三轮:自身设计知识(仅在第二轮也失败时)
仅对第二轮后仍无合适匹配的领域,你可以使用自己的设计知识。这应该很少见。
build_style_guide — 权威性约束
一旦你在所有领域做出选择,调用 build_style_guide:
build_style_guide({
"selections": {
"style": 2, // 搜索结果中的索引或名称
"color": 1,
"typography": 3,
"layout": 0
}
})
关键:返回的设计系统是权威性的
build_style_guide 响应提供必须使用的精确值:
- 颜色:使用精确的
#HEX或{r, g, b}值 — 不要调整 - 排版:使用精确指定的字体系列、大小、粗细
- 边框半径:使用精确的 px 值
- 间距:使用精确的 px 值
- 效果:使用精确的阴影/模糊参数
硬性关卡:如果设计系统说背景是
#FAF5FF,使用#FAF5FF(转换为 0–1 范围用于 batch_edit)。如果你意识到它与用户意图冲突 (例如,用户想要深色但得到浅色),返回search_style_guide使用更正后的关键词 — 不要静默覆盖值。
将样式指南值转换为 batch_edit
样式指南十六进制颜色 → batch_edit {r, g, b} 0–1 格式:
#FAF5FF → {r: 0.98, g: 0.96, b: 1.0}
#1A1A2E → {r: 0.10, g: 0.10, b: 0.18}
#E8714A → {r: 0.91, g: 0.44, b: 0.29}
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.
- 2mo ago First seen · 156 lines · 123 tokens per session scan A c7caa0224697
ardot-style-guide is a skill published in the GitHub repository balabalabalading/huuuuuuho-skills (118 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 1,657 once invoked, about $0.0005 per session on Opus 5.5. 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.
ardot-style-guide compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ardot-style-guidebalabalabalading/huuuuuuho-skills | Skill | 118 | 1mo ago | MIT | A | 123 | Claude Code |
| web-design-engineerConardLi/garden-skills | Skill | 14k | 12d ago | MIT | A | 96 | Codex |
| yida-data-manage-uiopenyida/openyida | Skill | 231 | yesterday | MIT | A | 100 | Claude Code, Codex |
| webflow-mcp:interactionswebflow/webflow-skills | Skill | 135 | 8d ago | MIT | A | 63 | Cursor |
| webflow-mcp:flowkit-namingwebflow/webflow-skills | Skill | 135 | 8d ago | MIT | A | 81 | Cursor |
| frontend-blueprinttech-leads-club/agent-skills | Skill | 7.1k | yesterday | none | A | 170 | Claude Code, Codex |
| design-optimizerluongnv89/skills | Skill | 145 | yesterday | MIT | B | 63 | Claude Code |