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 ilexlyu/ad-proposal-skills --skill ad-ppt-visual-architectgit clone --depth 1 https://github.com/ilexlyu/ad-proposal-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/ilexlyu/ad-proposal-skills/ad-ppt-visual-architect)<a href="https://agentmods.dev/skills/ilexlyu/ad-proposal-skills/ad-ppt-visual-architect"><img src="https://agentmods.dev/badge/skills/ilexlyu/ad-proposal-skills/ad-ppt-visual-architect/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/ilexlyu/ad-proposal-skills/ad-ppt-visual-architect"><img src="https://agentmods.dev/badge/skills/ilexlyu/ad-proposal-skills/ad-ppt-visual-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00083 | $0.00644 |
| Opus 5 | $0.00042 | $0.00322 |
| Sonnet 5 | $0.00017 | $0.00129 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
ad-ppt-visual-architect 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 11d 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.
What it actually says
PPT 视觉架构
目标：把“高级、大气、科技感”这类模糊需求翻译成可执行视觉系统。不要直接改文案；先建立行业视觉公约、页面规则和设计交接稿。
Before Working
读取 references/style-method-library.md，按客户类型选择风格路径。若用户提供参考图，优先分析参考图而不是凭空想象。
Inputs
- 行业、客户类型、提案文案、逐页蓝图、参考图、品牌色、视觉禁区。
- 若文案还没整理成逐页结构，先建议调用
$ad-proposal-narrative。
Workflow
-
行业视觉公约
- 判断该行业“专业感”来自哪里：色彩、材质、构图、图片类型、信息密度。
- 标注不能碰的风格误区。
-
视觉关键词
- 输出 3-5 个可执行关键词，不要只写抽象词。
- 示例：深色金融终端感、真实工厂纪实图、低饱和城市生活方式，而不是“高级感”。
-
页面系统
- 封面、目录页、章节页、观点页、数据页、案例页、结尾页分别给规则。
- 明确标题位置、内容密度、图文关系、强调方式。
-
配图提示词
- 为每页输出图片描述词或素材方向。
- 区分真实素材、AI 生成图、图标/信息图。
-
设计交接清单
- 给设计师可直接执行的约束：字体倾向、色彩、留白、版式、禁区。
Output Format
## 视觉基调
- 行业视觉公约：
- 风格关键词：
- 禁区：
## 页面规则
| 页面类型 | 版式 | 图片规则 | 字数密度 | 强调方式 |
## 逐页视觉蓝图
| 页码 | 页面目的 | 版式建议 | 配图提示词 | 设计注意 |
## 设计交接清单
Quality Bar
- 文案 100% 不乱改；如需压缩，必须单独标注为建议。
- 不说“高级、大气、科技感”这种不可执行词，除非同时解释视觉表现。
- 视觉建议必须服务客户理解，而不是只追求好看。
- 页面重点必须清晰，不能把所有元素都强调。
What ships with it
2 files 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.
- 11d ago First seen · 63 lines · 83 tokens per session scan A 6e7aaefea9ec
ad-ppt-visual-architect is a skill published in the GitHub repository ilexlyu/ad-proposal-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 644 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 2026-08-31.
Other skills, from other repositories
ai-hive-alt-adobe-firefly-workflow
A migration assessment workflow for testing whether AI-HIVE can provide selected creative assets alongside Adobe Firefly and Adobe's editing tools. Adobe Firefly is Adobe's service for generating images and other creative material from instructions.
ai-hive-alt-canva-magic-studio
A migration-testing guide for using AI-HIVE alongside Canva Magic Studio, Canva's tool for template-based design and AI media creation. It tests generated images and videos while leaving Canva's editor and templates in place.
landing-page-optimization-guide
This skill should be used when the user asks to "optimize my landing page", "improve conversion rate", "audit my landing page for CRO", mentions "message match between ads and pages", "high bounce rate on paid traffic", or "A/B test prioritization". Do NOT use for: ad creative optimization (use platform-specific…
brand-guideline-extraction
Reverse-engineer a comprehensive brand style guide from a corpus of existing design assets (social posts, ad creatives, banners, decks, videos). Produces a structured guideline document plus a reusable "style prompt block" for on-brand AI image generation. Use this whenever the user wants brand guidelines, a style…
award-landing-page
Design and build pages that sell — landing pages, homepages, pricing pages, waitlist and pre-launch pages, signup/registration pages, webinar/event pages, product-launch pages, and marketing-site heroes or sections. Use this whenever the user wants to create, redesign, or rework any page whose job is to persuade…
visual-brand-kit
Create visual identity systems for AI-generated content: colors, typography feel, photography style, composition rules, and prompt presets. Triggers on brand kits, visual guidelines, image style, and brand photography.