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 SimpleEve/eo-skills --skill eo-designgit clone --depth 1 https://github.com/SimpleEve/eo-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/simpleeve/eo-skills/eo-design)<a href="https://agentmods.dev/skills/simpleeve/eo-skills/eo-design"><img src="https://agentmods.dev/badge/skills/simpleeve/eo-skills/eo-design/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/simpleeve/eo-skills/eo-design"><img src="https://agentmods.dev/badge/skills/simpleeve/eo-skills/eo-design.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 | $0.00077 | $0.02718 |
| Opus 5 | $0.00039 | $0.01359 |
| Sonnet 5 | $0.00015 | $0.00544 |
| Haiku 4.5 | $0.00008 | $0.00272 |
Grade A, and why
eo-design 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 5d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
eo-design — 设计系统与高保真预览
以仓库根 DESIGN.md 为项目级设计真相源的四模式技能。姿态是设计顾问，不是表单向导：主动提出完整连贯的提案让用户挑剔，而不是逐项让用户填空。
模式路由
| 模式 | 触发 | 职责 |
|---|---|---|
init |
设计系统 / 从头定设计 / DESIGN.md 不存在时的默认 | 0→1 建立设计系统 → DESIGN.md + 约束注入 |
variants |
出几版看看 / 对比方案 / 某屏幕的视觉发散 | 多变体 HTML 对比 → 结论进 DESIGN.md 决策日志 |
apply |
落地 / 做成页面 / 生产级实现 | 选中方向 → 生产级 HTML/组件 |
audit |
检查设计一致性 / 设计审计 | 实现 vs DESIGN.md 的偏差报告 |
无法判断时问一句。variants/apply/audit 在 DESIGN.md 不存在时提示先跑 init（用户可拒绝，则以当次对话约定为准并提示结论不会被沉淀约束）。
通用规则（四模式共用）
- DESIGN.md 优先级最高：存在即为默认约束，高于任何临时发挥与从 mockup 反推的值；偏离必须经用户批准并记入 Decisions Log
- 上游 brief 握手：上游材料（brainstorming 记录的「设计 brief」节 / 所服务 change 的 change.md §1）只用于预填五维（给谁 / 核心任务 / 现状 / 所处流程 / 边界情况）——已钉项不重问，缺维照常采集；无可读引用（给不出路径）一律按无上游处理；方向说不清 → 按各模式的上下文门槛升级 /eo-brainstorming，不硬着头皮设计
- 预览一律自包含 HTML：内联全部 CSS/JS、不依赖外部服务；候选字体可用字体服务 link 标签加载。质量要求见 references/visual-craft.md
- 真实内容：用产品真实文案/数据渲染，禁 lorem ipsum
- 工件位置：过程产物
tmp/eo/design/<date>-<topic>/（可丢弃，见 ../eo-shared/conventions.md）；服务某个 change 的定稿另存eo-doc/changes/<id>/design/ - 提问纪律：遵循 ../eo-shared/questioning.md；封闭选择按其 §4 协议带推荐项
init — 建立设计系统
- 预填充（静默）：读 README / CLAUDE.md / 已有 DESIGN.md，代码侧现状有
.codegraph/索引则用codegraph explore召回（不存在则目录收敛 + 源码直读）；能推断的（产品是什么、给谁用、项目类型）不问 - 一个合并问题：把预填充结论摆出来让用户确认/纠正，外加一个必问项——「你希望用户第一眼记住这个产品的什么？一句话」（memorable-thing：之后所有设计决策服务于它）
- 上下文门槛（硬性）：至此「产品是什么 / 给谁用 / memorable-thing / 本次设计边界」仍有 ≥2 项说不清（「说不清」= 既无仓库证据、用户也答不出可执行结论；不适用维度标 N/A 不计入）→ 停止出提案，建议先 /eo-brainstorming 钉方向（其记录的「设计 brief」节回来即预填）；用户拒绝升级 → 当场最小 brief（五维合并问，计入 questioning.md §2 预算），2 轮封顶，未答项按合理默认推进并显式标注「（假设）」
- 竞品视觉调研（可选）：用户同意且环境可联网时，搜 3-5 个同类产品提炼品类共识与差异化机会；不可用或用户跳过 → 直接下一步，不阻塞
- 一次性完整提案（SAFE/RISK 拆分）：给出覆盖 Aesthetic / Typography / Color / Spacing / Layout / Motion 的连贯系统，每项带一句 rationale；结构为「2-3 个跟随品类惯例的安全选择 + 至少 2 个刻意冒险（各说得失）」，核心问题问「在哪里冒险」而不是逐项选菜单
- HTML 预览页：候选字体样张 + 色板 + 组件示例（按钮/卡片/表单/告警）+ 1-2 个用真实内容渲染的页面 mockup + 明暗模式切换，写入
tmp/eo/design/<date>-init/，请用户在浏览器确认；反馈迭代（每轮改预览页，不重开） - 落地：按 references/design-md-template.md 写仓库根
DESIGN.md（目标 <90 行）；执行同文件中的约束注入（CLAUDE.md 的<!-- eo-design:start/end -->段，幂等替换） - 速报：DESIGN.md 路径 + 关键决策一句话清单 + 注入状态
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.
- 5d ago First seen · 82 lines · 77 tokens per session scan A 22290b2d60fb
eo-design is a skill published in the GitHub repository SimpleEve/eo-skills (31 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 2,718 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 2026-09-04.
Other skills, from other repositories
design-it
A skill for turning a requirement or feature description into a single, self-contained HTML technical design document. The document follows a fixed layout with diagrams, code examples, decisions, tests, and a code index.
frontend-ui-ux
Designer-turned-developer who crafts stunning UI/UX even without design mockups. Use for any frontend implementation requiring visual design decisions, aesthetic direction, or pixel-perfect UI work.
mini-program-ui-device-skill
Design, preview, implement, and assess mini-program interfaces against an approved prototype, screenshot, visual reference, design system, or bounded UI request while preserving product semantics and existing accepted behavior. Use when users ask to reproduce a mini-program screen, refine visual hierarchy, adapt…
to-design
A design-document generator that turns a product requirements document, or PRD, into a proposal for how to build the feature. It records the background, chosen approach, reasons, trade-offs, compatibility concerns, and implementation plan.
design-before-build-gate
Enforces a design/spec approval gate before production implementation. Use when UI, UX, product flows, architecture, API shape, prototypes, visual direction, or user-facing behaviour need signoff before builders write production code.
accessibility-review
Review user-facing software changes for accessibility barriers across semantics, keyboard and other input, focus, structure, content, feedback, and assistive technology behavior. Use for web, mobile, desktop, CLI, and interactive UI changes; adapt the checks to the platform.