Borrowing it
Nothing to install: this file belongs to Peiiii/nextclaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Peiiii/nextclaw/master/.agents/wiki/skills/frontend/replicating-reference-skins/SKILL.mdgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/replicating-reference-skins)<a href="https://agentmods.dev/skills/peiiii/nextclaw/replicating-reference-skins"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/replicating-reference-skins/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/peiiii/nextclaw/replicating-reference-skins"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/replicating-reference-skins.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 | $0.00052 | $0.01105 |
| Opus 5.5 | $0.00021 | $0.00442 |
| Sonnet 5.5 | $0.00010 | $0.00221 |
| Haiku 4.5 | $0.00005 | $0.00111 |
Grade A, and why
replicating-reference-skins 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 2mo 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
参考皮肤复刻验收
参考图代表一套视觉系统,不是壁纸。完成意味着应用壳、共享原语、真实内容、页面配方和交互状态都像原生采用该语言;统一换色或 selector 覆盖率高但仍像默认产品,均不通过。
五层模型
- Token:颜色、字体、密度、圆角、边框、阴影、动效、透明材质。
- 语义表面:壳、导航、工具栏、内容、列表、卡片、输入、弹层和快捷栏;优先语义/可访问属性,类名仅作受控补充。
- 组件配方:同一角色的 default/hover/focus/active/selected/disabled 和异步状态共享合同。
- 页面配方:首页、会话、数据列表、市场和设置保持同一语言,但密度与装饰强度可不同。
- 独立资产:背景、人物、纹样、签名和贴纸分层渲染,不烘焙假 UI,不遮挡真实内容。
不修改产品源码时由一个注入 owner 维护五层,禁止多套补丁互相覆盖。
工作流
- 固定参考版本、原图、目标视口,并区分可用素材与概念方向。
- 提供稳定本地预览 URL,后续保持地址不变。
- 主验收选择有真实数据的页面;需要本地真实数据时复用 data home、隔离 run home,不复制少量样本冒充。空首页仅作补充。
- 开始前建立覆盖台账:组件/role、页面证据、状态、通过/失败/不适用。未检查即未覆盖。
- 先实现共享 token、语义表面和 primitive,再做页面结构与主题装饰。
- 同视口并排比较参考与实机截图,按应用壳、左右栏、顶部栏、内容、列表/卡片、表单、弹层和装饰分区收敛。
- 补查有数据、空、loading、error、disabled、selected、hover、focus-visible、滚动、窄窗口和无横向溢出。
覆盖台账
必须覆盖或以页面证据标记不适用:
- 基础:正文、标题、辅助文案、链接、图标、分隔、badge、头像、快捷键;
- 操作:主/次/危险/icon button、tabs、segment、dropdown、分页、悬浮动作;
- 表单:input、textarea、select、checkbox、radio、switch、slider、搜索、上传、校验;
- 数据:卡片、列表、表格、树、筛选、统计、骨架、空态、错误;
- 导航:品牌、分组、会话列表、breadcrumb、header、右栏、移动导航;
- 会话:各类消息、Markdown、表格、代码、工具、附件、流式、失败/重试、composer 与模型/skill 选择;
- 弹层:dialog、sheet、dropdown、popover、tooltip、command、toast、confirm、overlay;
- 页面:真实会话、市场/数据列表、设置/表单、首页和窄屏。
动态运行时差量维护标记,保留仍有效的 role,支持 SPA、懒加载和 portal;禁止每轮全删重加导致动画、焦点和状态抖动。宽泛 selector 错配组件同样算未通过。
画布与动效
- 背景归应用壳或页面共同父容器;header、内容、滚动区和输入器处于同一画布。主视觉不能无理由缩在角落以回避遮挡。
- 阅读保护用渐变、mask、透明度和内容表面完成;检查顶部、首屏内容后、输入器后方和底部淡出。
- 微型图标按实际 CSS 像素验收,关键识别特征在 1× 截图仍可见。
- 循环动效连续采样超过一个周期,确认状态持续变化且 DOM 角色身份稳定;单帧和测试不能证明不会被 hydration/observer 重启。
完成门
最终附参考图、稳定预览、有数据页截图、分区结果、组件/状态台账、实际尺寸动效证据和剩余差异。共享组件、真实会话、市场/列表、设置页、完整画布或完整动效周期任一未检查,或存在未披露高显著度差异时,不得称“全覆盖”“对齐”或“复刻完成”。
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.
- 2mo ago First seen · 55 lines · 52 tokens per session scan A 3f38e3fe98e6
replicating-reference-skins is a skill published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,105 once invoked, about $0.0002 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 2026-08-30.
replicating-reference-skins compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| replicating-reference-skinsPeiiii/nextclaw | Skill | 263 | yesterday | MIT | A | 52 | Codex |
| brand-tokenstianemon/EasyMint | Skill | 86 | yesterday | MIT | A | 62 | Claude Code, Codex |
| ui-aesthetictianemon/EasyMint | Skill | 86 | yesterday | MIT | A | 97 | Claude Code, Codex |
| aetox-shadcnMikedev115/Aetox | Skill | 48 | 29d ago | none | A | 130 | Claude Code, Codex |
| shadcnMikedev115/Aetox | Skill | 48 | 29d ago | none | A | 94 | Claude Code, Codex, Cursor |
| aetox-design-systemMikedev115/Aetox | Skill | 48 | 29d ago | none | A | 132 | Claude Code, Codex |
| frontend-designPM-Shawn/Abu-Cowork | Skill | 419 | 3d ago | Apache-2.0 | A | 77 | Claude Code, Codex |