vibe-interaction

vibe-interaction is a UX design & wireframing skill for AI agents, published by idiotLeoLYJ in the Daliu-Awesome-Skills repository on GitHub. Skillspace rates vibe-interaction D (66/100) and the safety scan flagged it for review; the rating is based on static analysis only.

Vibe Coding 流水线第二步:以 idea.md 为输入,产出一份零歧义的超详细交互文档 interaction.md(第一份 UI 文档:首次定义 页面/模块/元素 ID)。 当用户说"设计交互 / 交互文档 / 页面逻辑 / 跳转逻辑 / 每个按钮点了怎么跳 / 是弹窗还是跳转 / 这个点击之后是弹窗还是新页面 / 弹窗还是新页面 / 把页面流程理清楚 / 把每个元素的交互写清楚 / 每个按钮 / 每个元素 / interaction"等,想把页面与元素的交互行为定义到可实现颗粒度时,必须使用本 skill。 它为每个页面写布局、功能模块、页面级四态(loading/empty/error/forbidden)、每个可交互元素的触发/行为/多状态/门控/边界, 并用呈现方式分类法(navigate/modal/confirm/drawer/popover/bottomsheet/toast/inline-expand/inline-edit/newtab/download) 强制标注每个行为;每页的"数据需求"用功能化方式描述读什么/写什么(供 architecture 据此派生数据模型与接口),本文件不写接口 ID。 反触发(相邻阶段抢入口时主动让路):① 还在澄清产品想法 / 没有 idea.md → 交给 vibe-idea;② 已有 interaction.md 要据其派生技术骨架/数据模型/接口(architecture.md)→ 交给 vibe-architecture;③ 已有 architecture.md 要做视觉设计准则(design.md)→ 交给 vibe-design;④ 要画原型/接 Stitch → 交给 vibe-prototype;⑤ 要写代码/修 bug/跑测试 → 交给 vibe-implement。 前置依赖 idea.md(由 vibe-idea 产出);产物 interaction.md 交给 vibe-architecture(它将照本文件的数据需求派生 architecture.md),其后再到 vibe-design / vibe-prototype。

Grade
D
Quality
66 / 100
Safety
Needs review
GitHub stars
61

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubidiotLeoLYJ/Daliu-Awesome-Skills

Our review

Architecture
84 / 100
Maturity
Structured: ships references or scripts
Security scan
Medium-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • hidden/zero-width/bidi unicode chars
  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in UX design & wireframing

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.