agentsclimarketplace

Multimedia accessibility

Skill jrr996shujin-png/openclaw-seo-aeo-skills/seo-aeo-diagnostics/multimedia-accessibility

多媒体可访问性诊断子模块。检查图片 alt 文本覆盖率和质量、视频转录文字/字幕可用性。当用户提到"图片 SEO""alt 标签""视频 SEO""无障碍访问""图片替代文字"时触发。这直接影响 AI 引擎对多媒体内容的理解能力。From its SKILL.md

Install
npx -y skills add jrr996shujin-png/openclaw-seo-aeo-skills --skill multimedia-accessibility

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 10 stars10 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.5 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

多媒体可访问性诊断模块

本模块负责检查网站多媒体内容对搜索引擎和 AI 引擎的可访问性,满分 10 分。AI 引擎无法"看"图片或"听"视频——它们完全依赖文本替代信息(alt 文本、转录稿)来理解多媒体内容。

检查项

1. 图片 Alt 文本(6 分)

检查方法:

  1. 提取所有 <img> 标签
  2. 分类统计:
    • alt 属性且内容非空的图片数
    • alt 属性为空或缺失的图片数
    • 装饰性图片(alt="" 是正确做法,如分隔线、背景图标)
  3. 对有 alt 文本的图片,评估质量:
    • 是否描述性("蓝色登山鞋" 好于 "image1.jpg")
    • 是否过长(建议 < 125 字符)
    • 是否堆砌关键词("SEO 优化 SEO 排名 SEO 工具" 是反模式)
    • 是否与上下文相关
  4. 检查 <figure> + <figcaption> 的使用情况
  5. 检查图片是否有 title 属性(加分项,非必须)

评分:

  • 6 分:alt 覆盖率 > 90% + alt 质量高 + 装饰性图片正确标记
  • 4 分:alt 覆盖率 70-90%,或覆盖率高但质量一般
  • 2 分:alt 覆盖率 40-70%
  • 0 分:alt 覆盖率 < 40% 或全部是低质量 alt(如文件名)

输出格式:

状态:✅/⚠️/❌
图片总数:X 个
Alt 文本覆盖率:X%(Y 个有 alt / Z 个需要 alt)

Alt 文本质量抽样:
| 图片 | Alt 文本 | 评估 |
|------|----------|------|
| logo.png | "公司 Logo" | ✅ 描述性 |
| banner.jpg | "IMG_2024" | ❌ 文件名 |
| icon.svg | "" | ✅ 装饰性,正确留空 |

缺失 alt 的图片:
- src="..." (位于 [上下文])
- ...

figcaption 使用:X 处
修复建议:(具体建议,含改写示例)

2. 视频转录文字(4 分)

检查方法:

  1. 检测页面中的视频嵌入:
    • <video> 标签
    • YouTube iframe(youtube.com/embed/
    • Vimeo iframe
    • 其他视频平台嵌入
  2. 对于 <video> 标签,检查:
    • 是否有 <track kind="captions"><track kind="subtitles">
    • 是否有 WebVTT 或 SRT 字幕文件引用
  3. 检查视频附近是否有:
    • 文字转录稿(transcript)
    • 内容摘要段落
    • 时间戳列表
  4. 如果页面无视频,此项给满分(不适用 = 通过)

评分:

  • 4 分:无视频(N/A)或有视频且有字幕/转录稿
  • 3 分:有视频,有部分文字描述但无完整转录
  • 1 分:有视频,仅有标题无任何文字内容
  • 0 分:有视频但无任何文字替代信息

输出格式:

状态:✅/⚠️/❌(或 N/A 无视频)
视频数量:X 个
视频类型:自托管 / YouTube / Vimeo / 其他

各视频可访问性:
| 视频 | 字幕 | 转录稿 | 摘要 |
|------|------|--------|------|
| [视频1标题/URL] | 有/无 | 有/无 | 有/无 |

修复建议:(具体建议,如添加 YouTube 字幕、在视频下方添加摘要等)

汇总输出

## 多媒体可访问性 — 得分 X/10

| 检查项 | 得分 | 状态 |
|--------|------|------|
| 图片 Alt 文本 | X/6 | ✅/⚠️/❌ |
| 视频转录文字 | X/4 | ✅/⚠️/❌/N/A |

关键发现:(1-2 句总结)
优先修复:(对 AI 可见性影响最大的改进项)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in ~1.2k tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • extract all image tags
  • categorize images by alt attribute status
  • evaluate alt text quality
  • check figure and figcaption usage
  • detect embedded video elements
  • check video tags for track elements

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.