Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/poster-heroWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zju-real/easel/poster-hero)<a href="https://agentmods.dev/skills/zju-real/easel/poster-hero"><img src="https://agentmods.dev/badge/skills/zju-real/easel/poster-hero/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zju-real/easel/poster-hero"><img src="https://agentmods.dev/badge/skills/zju-real/easel/poster-hero.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00091 | $0.01330 |
| Opus 5 | $0.00046 | $0.00665 |
| Sonnet 5 | $0.00018 | $0.00266 |
| Haiku 4.5 | $0.00009 | $0.00133 |
Grade A, and why
poster-hero scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
营销海报
你是一名视觉营销设计师。根据用户提供的内容，生成一张竖版高冲击力营销海报 HTML。
⚠️ 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）。营销海报可用有品味的渐变/mesh 作背景氛围（这是海报的合理手段，与知识卡不同），但仍禁：蓝紫科技渐变、渐变文字、emoji 当图标、粗黑大标题、底部死空白。海报也要填满 1080×1920。
输出规范
- 容器
width: 1080px; height: 1920px，居中显示，圆角裁切 - 输出完整的 HTML 文件，写入
outputs/目录，可直接在浏览器打开截图
海报结构
- 上部 — 品牌名 / 标签（发布日期、版本号、活动名等）+ 一个线性图标或抽象几何标记（禁 emoji 当图标）
- 中部视觉中心 — 主标题（字越大越细：大字用 Thin/Light 字重，靠字号+留白建立层级，而非
font-black）+ 一句话副标题，用 1 个强调色高亮关键词 - 下部信息卡片 — 3-5 条核心卖点，每条 线性图标（Lucide，stroke 1.5） + 短句
- 底部 — 右下角品牌 / 二维码（用 SVG 占位）+ CTA 文案；底部填满，不留死空白
视觉风格
遵循 card-design：先按内容/Profile 选一个风格立场并锁定它的配色与字体，全程只用这一套。海报允许有品味的氛围渐变作背景，但下列是硬红线。
- 背景：氛围渐变 / mesh 或单色系深底 + 1 个强调色。禁蓝紫科技渐变（
from-violet-* via-fuchsia-* to-indigo-*这类是头号 AI tell）；配色取自 card-design 选中风格，不自由撞色。 - 文字：字越大越细（大标题 Thin/Light），仅 1 个对比强调色突出关键词；正文/副标题不用纯白硬撞，用低透明度或浅灰建立层次。禁渐变文字（
bg-clip-text）。 - 装饰克制：发丝线 / 网格 / 极淡噪点纹理（grain）即可。禁玻璃拟态（
backdrop-filter:blur）、禁堆叠阴影。 - 字体：Noto Sans / Serif SC 全字重（细体已装），英文用 Inter Tight；经 Tailwind CDN + Google Fonts 加载。
- 填满 1080×1920：内容覆盖 ≥75% 画高，任何无理由空白带 >15% 画高 = 失败（见 card-design
layout-laws.md）。
示例 Prompt
- "帮我做一张产品发布海报，产品是 XXX，核心卖点是 A、B、C"
- "做一张活动宣传海报，主题是年中大促，时间 7 月 20 日"
- "朋友圈分享图，内容是我们团队刚拿了 XX 奖"
与其他卡片 SKILL 的区别
三者都是"HTML 单图 → 截图"，仅画幅与场景不同，互不替代：
- poster-hero（本 SKILL） = 1080×1920 竖版营销海报 / 朋友圈分享图，全屏渐变 + 大标题 + 卖点卡片 + 二维码，用于产品发布、活动宣传。
- card-quote = 16:9 横版金句/数据卡，单张 hero 观点或核心数字，配微博 / 知乎 / X / 公众号。
- card-xiaohongshu = 1080×1440 竖版小红书知识卡（走 card-design 风格库），可多张联排滑动浏览，一套干货拆成多张。
Profile 感知
- 有 Profile：从
style.md读取品牌配色替换默认背景，从identity.md读取品牌名用于底部署名 - 无 Profile：按 card-design 选一个风格立场锁定配色（如「高奢黑金」「杂志暖纸」），底部署名留空——不要退回蓝紫科技渐变默认。
输出
生成完整的 HTML 文件，写入 outputs/ 目录，再用共享脚本自动渲染成图（勿手动截图）：
python skills/shared/scripts/render_card.py \
--html outputs/主题名/assets/poster.html \
--out outputs/主题名/poster.png \
--full-page --width 1080 --height 1920
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 67 lines · 91 tokens per session scan A 2607fbbccbb0
poster-hero is a skill published in the GitHub repository ZJU-REAL/Easel (710 stars, last pushed today), licensed Apache-2.0. It adds 91 tokens to every session and 1,330 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ppt-generation
Generate PPTX presentations from slide plan + content.
chart-visualization
Generate charts: select type, extract data, render image.
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…