cover-independent-review
Skill27 starsChanged 41 days agoMITView on GitHub
Independently inspect actual cover masters and platform exports for content payoff, visual quality, typography and mobile readability.
In this repository10 other files it gives its agents.
- cover-art-directionSkill
- evidence-story-scriptSkill
- explainer-motionSkill
- generated-brollSkill
- video-reference-studySkill
- video-release-qaSkill
- video-shot-plannerSkill
- video-source-indexSkill
- video-workflowSkill
- voice-subtitle-syncSkill
The file
Files
English instructions · 简体中文
For English-language tasks, read SKILL.en.md and its English reference templates before proceeding. Both editions use the same tools and authorization boundaries.
独立封面审查
要求设计任务之外的审阅者或新隔离上下文。不同上下文不等于不同模型;如实记录角色和实际模型,设计者自己的总结不能当独立报告。
输入与观察
获取当前正文、承诺兑现位置、必要来源限定、品牌规则、实际参考图、无字 master、发布比例图与文件哈希。用图像能力实际打开;只有路径/文案/模型自述时可检查文字,视觉保持待审。 按 审图模板 先说明一眼看到谁、发生什么、为何值得看,再按实际手机缩略图检查:
- 一个清楚主体与核心关系,画面焦点不分散。
- 主视觉质感、真实比例、手脸/物体结构与明显生成瑕疵。
- 完整主标题、必要归因和正文兑现,不把“拟”等限制变已实现。
- 字形、中文完整、层级、对比、换行与缩略图可读。
- 信息量与视觉关系,主标题/标签/装饰没有互相争抢。
- 留白、边缘、平台安全区、人物裁切与品牌署名。
- 各比例真正重排,主视觉与文字没有机械截断。
- 素材许可与生成性质,不因“引用”或“看起来真实”自动确认权利。
大标题、对象对抗关系、黑白配亮色和较完整文案可成立;不机械套审美禁用表。判断要附真实文件、问题位置、影响和最小修复。
结论与失效
P0 为核心失实或严重不可用;P1 为明显读不懂、事实限定缺失、信息过载或视觉缺陷;P2 为细节优化。真实 P0/P1 修复并看过新图后再关闭。 结论可为通过、需修订、待观察,另列权利未知和外发条件。核对当前哈希;图片、标题、正文承诺或比例变化后复查相应部分。 审图通过只覆盖记录范围,不授权上传或发布。输出独立报告、观察范围、逐比例结果、重要意见处理与当前文件版本。
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.

