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 ShuaiMXu/mv-skills-bundle --skill shaka-design-systemgit clone --depth 1 https://github.com/ShuaiMXu/mv-skills-bundleWrote 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/shuaimxu/mv-skills-bundle/shaka-design-system)<a href="https://agentmods.dev/skills/shuaimxu/mv-skills-bundle/shaka-design-system"><img src="https://agentmods.dev/badge/skills/shuaimxu/mv-skills-bundle/shaka-design-system/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/shuaimxu/mv-skills-bundle/shaka-design-system"><img src="https://agentmods.dev/badge/skills/shuaimxu/mv-skills-bundle/shaka-design-system.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 | $0.00082 | $0.01028 |
| Opus 5.5 | $0.00033 | $0.00411 |
| Sonnet 5.5 | $0.00016 | $0.00206 |
| Haiku 4.5 | $0.00008 | $0.00103 |
Grade A, and why
shaka-design-system 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 1mo 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
Shaka 设计系统 · 单一真相源
本 skill 不主动触发，仅供其他 skill（公众号、PPT、小红书等）在生成 HTML 内容时读取引用。 修改这里的规则 = 修改所有下游 skill 的视觉语言。
为什么存在
- 保持 Shaka 所有内容产出（公众号日报、PPT、小红书、邮件）的设计语言一致性
- 避免在每个 content skill 里重复定义配色 / 字体 / 组件
- 规则升级只需改一处，所有下游 skill 自动受益
- 呼应 [[Design DNA]] 理念——把风格规格从视觉稿解耦出来
引用方式
下游 skill 在生成 HTML 前，先 Read 以下文件拿到设计规则：
shaka-design-system/
├── SKILL.md 本文件（读我就够了解整体）
└── references/
├── themes.md 5 套主题配色（唯一色板真相源）
├── components.md 通用组件（callout / stat / pillar / figure / tag）
├── fonts.md 字体层级（标题 / 正文 / 等宽）
└── principles.md 约束式设计原则（不允许自定义 hex、主题节奏等）
实际挂载路径：
- Skills 通过符号链接发现，实际位置视运行环境而定
- 在 Claude Agent 容器中：
/workspace/user-skills/shaka-design-system/references/* - 在宿主机 admin 模式：
~/.claude/skills/shaka-design-system/references/*
下游 skill 清单
| Skill | 用途 | 输出形态 | 业务特定文件 |
|---|---|---|---|
ai-tech-wechat-writer |
AI 日报公众号 | 纵向长图文 HTML | layouts.md 5 段式 + 公众号模板 |
guizang-ppt-skill（上游） |
杂志风 PPT | 横滑分页 HTML | layouts.md 10 版式 + 横滑模板 |
xhs-poster-writer（规划中） |
小红书封面 | 3:4 单图 HTML → PNG | 小红书封面版式 |
email-newsletter（规划中） |
邮件订阅 | 邮件兼容 HTML | 邮件客户端安全版式 |
每个下游 skill 职责：只维护自己的 layouts.md（业务特定结构）和 template.html（业务特定容器）。所有共享部分统一从本 skill 读取。
核心哲学
引用自 op7418 的 guizang-ppt-skill，经我方验证并吸收：
- 约束式设计：枚举优于自由 —— 5 套主题不允许自定义 hex，因为用户配色 99% 会翻车
- 规则文档化：设计不是品味，是可查询的手册 ——
references/就是给 agent 和设计师共用的手册 - 节奏优于元素：单页漂亮不够，整体节奏才是杂志感的来源 —— 主题交替、视觉呼吸、深浅对比
- 踩坑沉淀：所有"血泪经验"必须进 checklist，不能靠记忆
修改规则的流程
- 提案改哪个文件（themes.md / components.md / etc.）
- 检查所有下游 skill 是否会受影响
- 在改动后的文件底部加
## 变更记录注明日期和原因 - 如果是破坏性变更（删除某个组件 / 重命名变量），同步更新下游 skill
边界
本 skill 不：
- 不生成任何 HTML / 文件
- 不维护任何业务特定结构（5 段式、10 版式等，归下游 skill）
- 不触发任何工作流（只被 Read）
本 skill 是：
- 设计规则的唯一真相源
- 被引用的字典
What ships with it
4 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.
- 1mo ago First seen · 87 lines · 82 tokens per session scan A 9af0293d0ea5
shaka-design-system is a skill published in the GitHub repository ShuaiMXu/mv-skills-bundle (14 stars, last pushed 5mo ago), licensed MIT. It adds 82 tokens to every session and 1,028 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
zhang-yimou-visual-ritual
Use this skill when the user wants Zhang Yimou-inspired visual symbolism, color systems, ritualized blocking, folk texture, mass choreography, ceremonial composition, visual metaphor, or large-image concept design for AI short drama. Apply public-source-backed principles; do not impersonate Zhang Yimou or copy…
higgsfield-moodboard
Use when the user asks about Moodboard, building a moodboard from reference images, curated moodboard presets, Soul Hex color transfer, applying a visual style direction to generations, or named moodboard styles like Y2K studio, Warm ambient, Theatrical light, Swag era, Flash editorial, Street photography, Asian…
higgsfield-canvas
Use when the user mentions Higgsfield Canvas, a node-based or node graph workspace, an infinite board/canvas, chaining generations into a pipeline, or wants to wire prompts → images → videos across models on one surface. Covers what Canvas is, the node categories, the seven models that run inside Canvas, the named…
sketch-correction-worker
Use when doing single-beat sketch quality control and preparing correction labels from a SuperTale project path and episode number. This skill turns one episode's selected sketches plus local script beat data into selectresult.jsonl, selectsummary.json, tasks.jsonl, and labels.jsonl for edit execution. Prefer using…
freezone
Use when the active chat surface is 虾画/Freezone/canvas, or when the user asks about canvas nodes, visual boards, selections, graph edits, canvas actions, layout, or Freezone short-video workflow work.
dramaclaw-workflows
Create, revise, confirm, run, or resume multi-node DramaClaw Freezone canvas workflows. Use for requests involving a workflow, several connected nodes, grouped production stages, storyboards, or text/image/video/audio pipelines; do not use for one standalone canvas operation.