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/frontend-interaction-quality/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/frontend-interaction-quality)<a href="https://agentmods.dev/skills/peiiii/nextclaw/frontend-interaction-quality"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/frontend-interaction-quality/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/frontend-interaction-quality"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/frontend-interaction-quality.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 | $0.00060 | $0.02172 |
| Opus 5.5 | $0.00024 | $0.00869 |
| Sonnet 5.5 | $0.00012 | $0.00434 |
| Haiku 4.5 | $0.00006 | $0.00217 |
Grade A, and why
frontend-interaction-quality 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
前端交互体验质量
重复操作与状态归 shared primitive,宿主不补 CSS。
参考体验
界面以 ChatGPT 成熟度为基线:清晰、稳定、一致、低操作负担;不以可用代替完成。工作台停靠可参考 VS Code、Notion,标准不降级。
- 一致性:同级入口复用语义命名的共享组件和状态样式,不耦合产品名;产品布局留在宿主,通过 surface/token 消费通用反馈。统一密度、圆角、对齐、hover、焦点和选中态,验收不同底色及调用处覆盖。
- 操作顺序:常规操作 → 更多 → 关闭;无关闭时更多最后,DOM/键盘顺序一致。共享工具栏固定槽位,业务不自排。低频布局入二级菜单,危险操作置后;普通设置页不加停靠工具栏。
- 交互完整性:行内更多与内容共用整行反馈,点击互不误触;鼠标、键盘和触控均可达,焦点返回、滚动与窄容器不丢失主任务。
- 成品审阅分级:无呈现影响免审;局部低风险改动定向看改动处及相邻关系;信息层级、主要路径、共享界面或影响不明时读取真实界面审阅,做开放式检查并复验。
每个新交互实现前对照顶级同类产品;复用控件验收组合。新复合交互或无把握时读范式与取证预算,查具体实例;常规小点不重复搜索。
控件合同
- 更多操作默认用竖向三点
MoreVertical,用户指定或平台约定可例外。 - URL、路由、文档和来源使用
<a>/Link/NavLink,状态修改、命令和无稳定 URL 面板使用<button>。站内目标保留真实 href 并由 Router 接管普通左键,避免整页刷新。 - 禁止交互元素嵌套、clickable span 和伪语义。普通文本链接默认态就有链接线索;按钮式链接只用于明确 CTA/下载/鉴权/卡片操作,底层仍保持链接语义。
- 链接图标须增加语义(如 Markdown 类型);否则无图标、无占位。共享导航统一焦点、target/rel 和宿主行为。
- 紧凑操作优先图标配 tooltip,菜单图标加文字;陌生/关键动作保留文字,按空间与任务判断。icon-only 有可访问名称、focus-visible;提示在 portal 可见。disabled 解释用可触发 wrapper。
- 操作 tooltip 默认上方、不足时避让;纵向栏可侧向。标签滚动条固定细度,hover 不增粗。
- modal overlay/content 都高于触发面板,content 高于 overlay,不能只有遮罩可见。
- 标题内边距归共享 Header:
DialogHeader或WorkbenchSurface title/moreActions;不借导航槽、不加竖线。验收窄屏长标题、顺序、命中。 - 紧凑模式保留操作含义或当前值;直接动作优先 tooltip,选项/二级动作优先 popover/menu/select。
- hover、focus-visible、active、disabled、selected 表达一致层级。文本输入框例外:光标和选区已表达焦点,聚焦前后容器背景、边框、阴影和 ring 不变。
- 普通 hover/按下/键盘高亮消费
--interaction-hover,选中消费--interaction-selection,边框消费--interaction-selection-border。主题定义颜色,组件承载状态,业务页不临时调色;反馈轻微,选中略强,不降级、叠加或升高表面层次。 - 统一 owner 而非同色。例外须有理由、owner 与渲染证据:移动会话用
--session-interaction-*,侧栏用--sidebar-interaction-*,分段用--sidebar-segment-selection。主 CTA、危险、状态按语义例外;回归与明暗渲染必验。 - 行级更多悬停整行或焦点进入时显示;隐藏时零视觉、零占位、零命中,菜单展开时保持可见;无 hover 设备常显。全局菜单和工具栏操作常显。浮层提供 hover bridge。
- 危险、不可逆、跨系统或可能丢数据的操作有清晰文案、确认或撤销;普通导航不滥用确认。
常见复合交互
- 高数据量表格与列表:超过单页可读范围须分页或虚拟化。管理员概览优先稳定排序、范围/总数、翻页与每页大小;默认 10 条、常用上限 20,任务或惯例可调整。提供适用的名称/类别/平台/状态搜索筛选,条件或每页大小变化回第 1 页,空结果说明无匹配。持续增长的数据由 API/D1 owner 筛选分页,禁止前端全量加载伪分页。验收多页、筛选有/无结果、翻页、大小变更、刷新恢复条件、窄容器横向阅读及键盘焦点。
- 触发式输入面板:只有用户真实插入
/、@等 marker 才创建 session;Esc、选中、blur 或离开范围后销毁,文本同步/删除/selection change 不得自动复活。active index、键盘高亮和滚动归面板实例。 - 对象操作菜单:更多按钮和右键共享菜单模型、分组和 primitive;右键只是效率入口。disabled、危险态、焦点移交一致,菜单关闭不得抢回已移交焦点。
- 二级菜单:桌面端使用保留父菜单的侧向级联,不把子菜单替换成带返回按钮的导航页。支持悬停、点击和右方向键打开,左方向键/Escape 只关闭当前层并恢复父条目焦点;鼠标跨入子菜单不闪退,边缘自动避让,窄容器不裁切操作。页面不得另建菜单状态机或平行子菜单组件,统一消费
shared/components/ui/context-menu的模型与渲染;不同输入设备的适配也留在同一 owner。 - 可折叠行/卡片:整个 header 是点击目标,箭头只是提示;折叠态保留关键预览。行内独立控件通过稳定隔离合同避免冒泡误展开,并为 hover/展开提供明确反馈。
- 动效:展开/收起、浮层和视图切换默认复用共享过渡;Markdown 折叠用
ChatCollapsibleContent,箭头同步。支持反向打断、动态高度及减少动态效果;首屏不重播、不加装饰循环。真实操作验收中间态。 - 展开与滚动:主动展开不贴底,嵌套动画不重播。工具组限半屏、按溢出渐隐。内部阅读区到顶/底后向外传递,禁用
overscroll-behavior: contain/none或吞滚轮;弹窗/浮层外边界隔离背景、画布缩放除外。验收双向传递和输入框可见,测试后恢复真实视口。
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.
- 1mo ago Changed · +3 tokens per session ecea4e91d254
- 1mo ago Changed · +4 lines 02ee093423e7
- 1mo ago Changed 8a9c1f74933d
- 1mo ago Changed · +11 lines b8c45a0c2c83
- 2mo ago First seen · 45 lines · 57 tokens per session scan A 0dc74cb4d1ce
frontend-interaction-quality is a skill published in the GitHub repository Peiiii/nextclaw (263 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 2,172 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.
frontend-interaction-quality compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| frontend-interaction-qualityPeiiii/nextclaw | Skill | 263 | yesterday | MIT | A | 60 | Claude Code, Codex |
| mermaid-diagramshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 55 | Claude Code, Codex |
| ppt-designerdongsheng123132/u-claw | Skill | 1.8k | 3d ago | MIT | A | 29 | Claude Code, Codex |
| infographicPM-Shawn/Abu-Cowork | Skill | 419 | 3d ago | Apache-2.0 | A | 71 | Claude Code |
| svg-diagramPM-Shawn/Abu-Cowork | Skill | 419 | 3d ago | Apache-2.0 | A | 70 | Claude Code |
| mermaid-diagramPM-Shawn/Abu-Cowork | Skill | 419 | 3d ago | Apache-2.0 | A | 104 | Claude Code |
| brand-tokenstianemon/EasyMint | Skill | 86 | yesterday | MIT | A | 62 | Claude Code, Codex |