Create shareable comparison cards showing product specifications, differences, or pros and cons. Organize supplied data or research missing details, then produce fixed-size HTML and PNG cards using table, side-by-side, or pros-and-cons layouts with sources and dates.
对比图/一图流：生成 A vs B 参数对比图、优劣势对比表、产品参数一图流。用 HTML+CSS 渲染成可截图的视觉卡片，适合小红书/微博等平台分享。使用时机：用户说"做个对比图"、"A vs B"、"参数对比"、"优劣对比"、 "一图流"、"对比表"、"哪个好"、"对比一下"。
和 chart-visualization 的区别：chart 做数据图表（柱状图/折线图），comparison-card 做对比表/一图流。和 infographic 的区别：infographic 做多维信息图，comparison-card 专注 A vs B 对比。
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
生成 A vs B 可视化对比卡片，一张截图说清楚差异，适合社媒分享。
⚠️ 生成前先读 card-design 设计系统（锁配色/字体层级/填满画幅/去 AI 廉价感）。对比图用「对比表」骨架（左右双栏、≥5 对比行、行高一致），避免渐变、emoji、底部死空白。
| 字段 | 必填 | 说明 |
|---|---|---|
items | 是 | 要对比的 2-4 个对象（名称） |
dimensions | 否 | 对比维度列表（如价格、性能、功能等）；不指定则自动提取 |
data | 否 | 结构化对比数据（JSON/表格）；不提供则由 SKILL 调研填充 |
layout | 否 | 布局模式：table（默认）/ versus / pros_cons |
size | 否 | 尺寸预设：xiaohongshu(1080x1440) / weibo(1080x1080) / wechat(1080x1920) / auto |
style | 否 | 视觉风格：走 card-design 风格库（瑞士极简/杂志编辑/高奢黑金…），不指定则按内容品类/Profile 选一个立场 |
winner | 否 | 是否标注胜出项：true / false（默认 false） |
| 模式 | 描述 | 适用场景 |
|---|---|---|
table | 经典参数对比表，行=维度，列=对象 | 多维度、多参数的产品对比 |
versus | 左右对称 VS 布局，中间分割线 | 两个对象的直观对比 |
pros_cons | 优劣势分栏，绿色优势/红色劣势 | 单一产品的优劣分析 |
outputs/ 目录如果用户提供了完整数据：
如果用户只给了对象名，没给数据：
将数据整理为标准矩阵：
{
"items": ["A", "B"],
"dimensions": [
{"name": "价格", "values": ["¥2999", "¥3499"], "winner": "A"},
{"name": "性能", "values": ["骁龙 8 Gen3", "A17 Pro"], "winner": "B"}
]
}
references/comparison-template.html 作为基础模板layout 模式选择布局结构size 参数）winner 为 true，用视觉标记（高亮/皇冠图标）标注胜出项将 HTML 写入 outputs/ 目录，文件名格式：{A}_vs_{B}_对比_{日期}.html
用共享脚本自动渲染成图：
python skills/shared/scripts/render_card.py \
--html outputs/主题名/assets/A_vs_B_对比.html \
--out outputs/主题名/A_vs_B_对比.png \
--full-page --width 1080 --height 1440
尺寸按 Profile 匹配的平台预设调整（默认小红书 1080×1440）。脚本用 playwright+chromium，对 CDN/字体有界超时不卡死；首次需 pip install playwright && playwright install chromium。
style.md 读取品牌配色，替换模板默认色；从 identity.md 读取账号名作为水印；从 platforms.md 读取主力平台，自动匹配尺寸自研溯源与参考项目见同目录
EASEL-META.md。
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Generate images from written descriptions, transform existing images with editing instructions, or create several variations. Choose image dimensions and quantity, then save the results using an OpenAI-compatible service or apimart with your own API key.
Generate background music for short videos, vlogs, and social posts from descriptions of mood, style, and instruments. Download MP3 audio, optionally include sung lyrics, and use shared scripts to trim tracks, adjust loudness, or add music to videos.
Create new videos from written scene descriptions or still images using external AI services. Set the aspect ratio and duration, animate a character image, and request generated audio when the selected model supports it.
Organize generated images, videos, and text in outputs/ by date, platform, and type. Add tags, search filenames and content, produce asset lists and reports, and preview archive moves before applying them to make past work easier to reuse.
Reduce background noise in audio recordings or video soundtracks with three processing levels. Keep the original file, create a cleaned version, and receive a report of the settings used and file details before and after processing.
Edit audio files by trimming sections, converting formats, matching loudness, or extracting sound from videos. You can also join recordings, add fades, and change playback speed while keeping the original pitch.