visual-beautiful
The BEAUTIFUL family of the visual-reasoning stack: data visuals that maximize communication plus beauty, the sibling pole to the CLEAR family's communication plus clarity. Use when the user asks for something beautiful, striking, data art, a poster, a wall or lobby display, an exhibition piece, a screensaver, a hero image, a glowing network, a LiDAR city, a wind or flow animation, or "make it gorgeous"; and when the user wants options, to make both poles plus a combined candidate and rate them (the default when a request names neither pole). Keeps the truth floor (real data, disclosed mapping) while relaxing style rules.
原文 · 译文尚未补齐适用对象:设计与内容创作。自动收录 · 待核查。
原作者说明节选
从固定版本的 SKILL.md 提取,保留原文语言。以下内容属于作者说明,本站尚未验证安装、兼容或运行结果。
查看英文原文
原文涵盖的主题
- Visual Beautiful
- Purpose
- When to use
- Inputs
- Modes
- The communication floor (always on, every mode)
- Style rules
- Procedure
CLEAR and BEAUTIFUL are two poles of one design space. CLEAR maximizes communication and clarity and tends toward sparsity. BEAUTIFUL maximizes communication and beauty and tends toward aesthetics. Communication is the shared floor and is never traded away. The win is a piece that is high on communication, clarity and beauty at once, so this skill always looks for the front between the poles, not just its own pole. Beauty here is not decoration on top of data. The strongest pieces are beautiful because the data is legible in them: colour breaks where the physics changes, marks that look like samples, motion that is the phenomenon. visual-intent handed off here. That is the default: a request that names neither pole gets a CLEAR version, a BEAUTIFUL version and one combined candidate. A request for beauty, art, display or exhibition narrows to this pole alone. A CLEAR figure exists and the user wants a striking companion of the same data. Not alone when the reader must read exact values or the output feeds a decision. Then CLEAR is required and a BEAUTIFUL piece may be a companion, never the sole output. Say so. Not at all when no renderer can draw the data shape honestly (step 3 fi
这里只展示节选,请以完整原文和当前要求为准。
- 来源仓库
- Lmandrake/MandrakeWorkflows
- 源文件
- skills/visual-beautiful/SKILL.md
- 固定版本
- 1874105936272447e2f9c81ba1dac48dae6ed074
准备条件
- 本条仅收录原作者的技能元数据;请阅读完整说明,确认依赖、许可与使用条件。
第一件可以尝试的小事
先阅读原作者说明,再决定是否在自己的 AI 工具中使用。
对应 AI 工具说明
作者有说明不等于本站实机验证。没有证据时,不自动标为兼容、安全或免费。
来源与内容状态
本条为自动发现的元数据,尚未完成人工文档核查;适用性与运行结果待核查。
原作者:Lmandrake/MandrakeWorkflows · 原作者仓库元数据。文档核查:未核查。最近来源检查:2026-11-11T03:01:44.735Z。
分类由名称、说明与路径规则生成,分类不代表已核实适配。
许可与权利归属
MIT。第三方内容及版权归原作者,使用条件以原文为准。
许可原文 ↗本站没有因同步、复制或用户自报成功而将资源标为运行验证通过。
限制与注意事项
- 元数据收录不代表本站已经安装、适配、实测或进行安全审查。