polish-pass
Skill1 starsChanged 2 months agoMITView on GitHub
在设计向客户、团队或利益相关者展示或发布前执行最终质量门禁,综合检查无障碍、AI 模板味、视觉层级与节奏、交互状态,并对发现去重和分级。用户提出“最终润色”“发布前检查”“Polish Pass”“能不能交付”时使用;结构仍在大改或内容严重缺失时应先完成设计,不要过早抛光。
2 other projects use a version of this.
Adopted by
Most recently taken up by
- SubliminalCoding/bilbroswagginz-skillstheir own version, first seen Sep 27, 2026
- Onevium/skillsword for word, first seen Sep 4, 2026
Other versions2 projects use a version of this.
Word for word · 1
- Onevium/skills★ 1100% same
Edited · 0
None found.
Wrote their own version · 1
- SubliminalCoding/bilbroswagginz-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- narrative-video-directorSkill
- portrait-shoot-directorSkill
- accessibility-auditSkill
- ai-slop-checkSkill
- component-extractSkill
- design-system-extractSkill
- discovery-questionsSkill
- frontend-aesthetic-directionSkill
- generate-variationsSkill
- hierarchy-rhythm-reviewSkill
- interaction-states-passSkill
- make-a-deckSkill
- make-a-prototypeSkill
- make-tweakableSkill
- wireframeSkill
- code-quality-reviewSkill
The file
Files
最终润色门禁
这是四类专项审查的总入口。重点是发现会阻碍交付的问题,并让用户知道什么已验证、什么仍需决策,而不是产生最长的问题清单。
1. 确认是否适合进入润色
读取最终交付物和相关样式,确认媒介、使用场景、品牌和用户约束。若布局仍破损、主要区块缺失或占位内容仍在重写,说明现在抛光的浪费,并先完成结构。
确认操作模式:只要求审查时不要修改;明确要求“修好并交付”时再实施修复。
2. 执行四个维度
可直接应用以下量表;运行环境支持并且并行不会增加风险时,也可以分别加载同库中的专项 Skill,再统一汇总。
- 无障碍:对比度、颜色信号、语义、标签、键盘、焦点、动效、表单和点击目标。
- AI 模板味:无依据渐变、装饰 emoji、默认卡片、临时插画、静默默认字体、散乱 token 和不合场景的暖色编辑风。
- 层级与节奏:主要与次要信息、5 秒扫描、间距和字号尺度、重复一致性、策略性变化、调色板和对齐。
- 交互状态:适用的 default、hover、active、disabled、focus、loading,以及过渡、成功、失败和当前状态反馈。
专项 Skill 或并行审查不可用时,在当前上下文按四个维度顺序完成,不要把工具缺失当成跳过检查的理由。
3. 去重并分级
- 阻塞:真实无障碍失败、关键路径不可用、缺失键盘支持、表单无法完成等交付前必须修复的问题。
- 质量问题:与品牌或简报冲突的模板化视觉、错误层级、必要状态缺失和明显不一致。
- 润色建议:不阻碍使用的细微节奏、色调和表达改进。
相同根因只保留一条,附上多个受影响位置。低置信度审美意见不得升级成阻塞。
4. 修复与复验
获准修改时依次处理阻塞、质量问题和范围内的润色建议。重新检查关键路径、对比度、焦点、响应式、视觉层级和状态反馈,确认修复没有破坏品牌或其他页面。
5. 结论
结论使用“可以交付”“用户确认标记项后可以交付”或“仍需迭代”。列出各类修复数量、开放决定、未覆盖范围和实际验证方式。
示例
输入:“这个客户落地页准备展示了,做最后一轮检查并修好。”
**输出:**四维审查去重后得到两个无障碍阻塞、三个层级或状态问题和两个润色建议;修复并复验后给出“字体决定确认后可以交付”的结论。
来源与许可
本 Skill 基于 Trystan Sarrade 的 claude-design-system-prompt 进行中文化与 Claude Skill 规范适配。上游与本改编均按 MIT License 发布,详见 LICENSE.txt。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

