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 agentmods add skills/tianemon/easymint/creation-flow-prototypenpx skills add tianemon/EasyMint --skill creation-flow-prototypegit clone --depth 1 https://github.com/tianemon/EasyMintWhat 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 | $0.00039 | $0.01146 |
| Opus 5 | $0.00019 | $0.00573 |
| Sonnet 5 | $0.00008 | $0.00229 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
creation-flow-prototype 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 2d 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
快速原型
你(Mint)在创建项目引导的原型阶段,出原型让用户"先看再定"。
原型 Gate(G3/G4)
- 触发条件:有 UI 且中等及以上项目——极简 / 简单 / 无 UI(纯后端 / CLI / API / 库)项目跳过本 skill,直接进入技术方案或编码
- 原型是用户与 AI 对"最终产品是什么"的共同确认,确认后成为开发事实依据
- 用户确认原型后才写完整项目文档(需求文档 + 技术架构 + task.json)
按场景分级
- 商业交付:高保真完整(核心页 + 流程 + 状态 + 异常 + 视觉 + 品牌 + 响应式)
- 实际使用:核心页面 + 核心流程
- 兴趣创作:强调视觉探索与创作
- 想法验证:核心用户路径,快速可交互
- 学习实践:可选(用户参与设计也是学习)
- 技术实验:可跳过(无明显 UI 时)
白话风格选项
- 现代简约(白底卡片)/ 活力彩色(鲜艳渐变)/ 商务专业(深色克制)/ 科技感(暗色光效)
- 配品牌库参考图,不问设计术语
委派前需求确认(必经,先对齐再动手)
出原型前,先和用户确认需求理解,等用户说「开始/可以」再委派,不要跳过此步直接动手:
- 汇总当前已确认的输入:核心功能清单、项目场景、UI 风格方向、完成度/范围(表单已采集 + 对话已确认的)
- 用自己的话复述:"我准备按这个方向做原型:功能 [A/B/C]、风格 [X]、[场景] 场景。你看还有要补充或调整的吗?"
- 等用户确认(或补充调整后再次确认)——确认后才委派 Mint-D
为什么:原型是用户与 AI 对"最终产品是什么"的共同确认,必须先对齐输入再做,否则原型做偏、白做一轮。
调 Mint-D 出原型
- 委派 Mint-D 设计师产出 HTML 原型(种子模板 + 品牌库 + :root 变量)
- 要求视觉四件套:色板 / 字体角色 / 布局线框 / 签名元素(大胆只花一处,其余克制)
- Mint-D 交付前必须做渲染正确性自查(从代码推理,不依赖截图)
交付前渲染正确性审查(必经,Mint 负责)
收到 Mint-D 的原型后,先审读 prototype/index.html 代码,从代码层面确认能正常显示,通过后才调 show_prototype 让用户看:
- 无 CSS 规则覆盖元素显隐(display/visibility 覆盖 hidden,导致弹窗/遮罩默认显示、页面被盖住)
- 无 CSS 变量错误(自引用 var(--x: var(--x))、拼写错误、未定义引用)
- 遮罩/弹窗默认隐藏、定位不盖住首屏;z-index 层级合理
- 标签配对完整、CSS 无无效声明
- 首屏内容可见(无纯白背景配浅色文字、无关键内容被意外隐藏)
审查只从代码推理,不要用 Playwright 渲染、不要启动 http 服务器、不要截图分析——模型不一定支持看图,且审查目的是发现代码级缺陷;打开给用户看(open / show_prototype)与审查是两件事。
若代码审查发现问题,退回 Mint-D 修改,或按下方"原型修改"分档直接改。确认无渲染异常后才 show_prototype。
原型修改(分档)
- 小改(颜色/文案/布局微调):Mint 直接改 prototype/index.html——原型迭代不受"单文件 ≤ 20 行"限制,快速响应用户反馈,不重新委派
- 大改(结构重排/重新设计):重新委派 Mint-D(它掌握设计规范/品牌库/种子模板)
- 每次改动后做一次渲染正确性审查(同上),通过后再展示
确认后(G4 通过)——写完整文档,再问是否开始开发
原型确认后(功能需求、架构可能已随原型调整),此时才写完整项目文档(需求文档 + 技术架构 + task.json),然后 Read creation-flow-techspec 进入技术方案与开发。
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.
- 2d ago First seen · 70 lines · 39 tokens per session scan A 8e9d8d257cc2
creation-flow-prototype is a skill published in the GitHub repository tianemon/EasyMint (21 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 1,146 once invoked, about $0.0002 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
huashu-design
花叔Design(Huashu-Design)——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索、设计方向顾问与专家评审。HTML是工具不是媒介,根据任务embody UX设计师/动画师/幻灯片设计师/原型师,避免web design tropes。触发词:做原型、设计Demo、交互原型、HTML演示、动画Demo、设计变体、hi-fi设计、UI mockup、prototype、设计探索、做个HTML页面、app原型、iOS原型、导出MP4/GIF、60fps视频、设计风格、配色方案、视觉风格、评审、review this…
coss
Give your AI assistant deep knowledge of coss ui components, patterns, and best practices.
mermaid-diagram
Use when the user asks for a flowchart, architecture diagram, sequence diagram, ER diagram, state machine, gantt chart, or any visual that fits Mermaid syntax. Hope Agent's chat renders Mermaid blocks natively, so the diagram appears inline.
nextclaw-product-visual-assets
当 NextClaw 产品更新后需要生成、替换、挑毛病或检查官网、GitHub README、用户文档或社交传播中的真实截图、AI 宣传视觉、整页 HTML 宣传预览、社区二维码等对外视觉资产时使用;也用于“更新截图”“重新截一批图”“做宣传页”“生成 campaign 页面”“视觉审稿”“五星挑刺法”或发布前检查视觉资产。普通站点布局开发或只写文章不触发。.
source-command-audit-whitepapers
Audit version freshness, FR/EN parity, and metadata quality of all whitepapers and recap cards.
self-assessment
Interactive skill assessment with personalized learning path generation.