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 Lynnouo/yushio --skill yushio-vigit clone --depth 1 https://github.com/Lynnouo/yushioWrote 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/lynnouo/yushio/yushio-vi)<a href="https://agentmods.dev/skills/lynnouo/yushio/yushio-vi"><img src="https://agentmods.dev/badge/skills/lynnouo/yushio/yushio-vi/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/lynnouo/yushio/yushio-vi"><img src="https://agentmods.dev/badge/skills/lynnouo/yushio/yushio-vi.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 | $0.00253 | $0.12039 |
| Opus 5 | $0.00127 | $0.06019 |
| Sonnet 5 | $0.00051 | $0.02408 |
| Haiku 4.5 | $0.00025 | $0.01204 |
Grade A, and why
yushio-vi 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.
How it starts
The opening of the file, as written. The whole thing — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VI 专项 · 完整品牌视觉识别系统的生产方法论
这不是"怎么画一个 logo"。是"怎么从一份 Brief，产出一份篇幅、广度、深度都达到画册级的完整 VI 提案"。 它和美术总监夕潮的关系：美术总监给判断力（方向对不对、好不好看、像不像 AI 做的），本文件给生产流程（12 章骨架怎么搭、工艺链怎么跑、怎么交付）。两者叠加：没有美术总监的判断力，这套流程会产出"结构完整但没有灵魂"的空壳 VI。 它的存在理由：一份好 VI 提案的质量，70% 来自有没有走完整套流程，30% 来自单点灵感。这份文件把那 70% 固化成可复跑的 SOP。
§0 启动脚本（你读到这里立即执行）
1. 前提确认
- 美术总监夕潮是否已加载？没有 → 先激活（判断力来源，本流程依赖它的 §3 信条 + §4 视觉推导）。VI 专项是"手"，美术总监是"眼"，缺眼的手会做出 AI slop。
- 基础夕潮：建议同时在场（人格四柱 + 工作纪律 + 记忆系统）。
2. VI 环境探测
- 有无 Brief / 设计需求文档？→ 这是头等大事，充分性判断走 §0.5 闸门（动任何视觉之前必过）。
- 有无 已有视觉资产？（草稿 logo、参考图、吉祥物原型、竞品截图）
- 命名体系：中文名 / 英文名 / 谐音关系 / 社群名 / 吉祥物名 —— 一开始就要锁清楚（命名混乱是后期返工高发区，见美术总监 #DE）。
- 触点清单：这套 VI 要覆盖哪些场景？（线上：App/网站/自媒体；线下：招牌/快闪；实体：服装/周边/包装）—— 决定应用章要做多少样机。
- 技术能力探测 + 问用户：本机有无 SVG 渲染工具（rsvg/cairosvg/headless Chrome）、可商用字体；有没有图像生成 API（Gemini/豆包/本地 SD）或别的出图工具（Midjourney/即梦/可灵/设计师）。→ 对号入座 §4.6 样机降级阶梯（T0 有 API / T1 合成 / T2 纯矢量 / T3 交用户出图）。没 API 不影响开工——VI 只有样机章和海报底图碰 API，其余 11 章零依赖。
3. 第一次 VI 汇报（≤6 行 · 必须先过完 §0.5 Brief 闸门）
品牌一句话： [产品是什么 · 给谁 · 核心矛盾]
VI 覆盖触点： [要做的应用场景清单]
我建议的方向： [灵魂 → 视觉锤 → 三个气质形容词]（有立场，不含糊）
关键方向变量： [需要用户拍板的 2-3 个岔路 —— 配色/字体/吉祥物形态]
铁律：方向变量必须让用户拍板，不能自己假设（美术总监 #DD）。本方法论提炼自的那个案例项目正是因为开了「配色三选一 / 吉祥物双版本」让用户选，才没跑偏。
§0.5 Brief 闸门 —— 动任何视觉之前先过这关
VI ≠ 纯视觉。 它含品牌内核(01)/设计理念(02)/吉祥物人设(07)/创意广告(10)/营销传播(11)——这些章节要的是策略与内容实质，不是视觉方向。一份只写了"赛博朋克+红色"的 brief，能产出好看的 logo，但这些内容章节会是空心的 AI 填充。 三份案例提案之所以扎实，是因为它们共享一份 14KB 的 Brief——里面已经写好 IP 内核、命名体系、吉祥物人设、12 个表情场景、6 支广告概念、slogan 矩阵。那份 Brief 喂饱了内容章节。没有它，01/10/11 章只能瞎编。
所以在定视觉锤（§2）之前，先过这三步闸门。这是 VI 链路真正的第一步。
1. 探测有没有 Brief
- 扫仓库：
*.md / *.txt / *.docx / *.pdf里含 "brief / 需求 / 品牌 / 设计 / 策划" 或品牌名的文档；连竞品截图、参考图、聊天记录转写都收。 - 直接问用户："有没有现成的需求文档 / 品牌资料 / 策划案？哪怕是几段语音转文字、一篇小红书介绍也行。"
2. 判断够不够用（双层 checklist）
合格的 VI Brief 必须同时覆盖两层。只有视觉层 = 只够做半套 VI（好看但空心）。
A · 视觉层（决定 logo / 色 / 字 / 吉祥物长什么样）
- 气质关键词（3-5 个形容词）
- 配色倾向 / 字体倾向 / 风格参考
- 命名体系（中 / 英 / 谐音 / 社群 / 吉祥物名）
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.
- 11d ago First seen · 437 lines · 253 tokens per session scan A b4dd12575bbf
yushio-vi is a skill published in the GitHub repository Lynnouo/yushio (219 stars, last pushed 2mo ago), licensed MIT. It adds 253 tokens to every session and 12,039 once invoked, about $0.0013 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.
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.