Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mrpulor-gh/nuphus --skill release-postergit clone --depth 1 https://github.com/mrpulor-gh/nuphusWrote 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/mrpulor-gh/nuphus/release-poster)<a href="https://agentmods.dev/skills/mrpulor-gh/nuphus/release-poster"><img src="https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/release-poster/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/mrpulor-gh/nuphus/release-poster"><img src="https://agentmods.dev/badge/skills/mrpulor-gh/nuphus/release-poster.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 | $0.00000 | $0.01481 |
| Opus 5 | $0.00000 | $0.00740 |
| Sonnet 5 | $0.00000 | $0.00296 |
| Haiku 4.5 | $0.00000 | $0.00148 |
Grade A, and why
release-poster 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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
发版宣传图制作规范
版本发布时快速产出社交平台宣传图（抖音等）。模板已固化，填内容即可，禁止每次重新设计。
一、 铁律（血泪教训，不可违反）
- Logo 必须用官方源文件原样嵌入：
src-tauri/icons/icon-source.svg（深紫黑板 #1a1a2e + 白色开口壳暂停键）。禁止凭印象重绘、禁止改色、禁止改路径——模板中 logo 段已固化，直接复用。 - 内容只列更新亮点，内部事故/修复细节一律不入图。
- 禁止 emoji 充当图标，卡片图标用线条 SVG（stroke 配色跟随卡片主题色）。
- 文案以 HTML 源码为准——vision 审查可能误读简繁体/错字，遇 vision 报告文字错误先核对源码再决定改不改。
二、 两版规格
| 版式 | 尺寸 | 用途 | 模板 |
|---|---|---|---|
| 横版 16:9 | 1920×1080 | 封面图/横屏场景 | templates/horizontal.html |
| 竖版 9:16 | 1080×1920 | 抖音全屏视频 | templates/vertical.html |
竖版安全区（上下都有平台 UI 遮挡，均已固化进模板，禁止减小）：
| 区域 | 安全区 | 遮挡源 |
|---|---|---|
| 顶部 | ≥ 200px（stage padding-top:200px） |
抖音状态栏（时间/电量）+ 顶部导航 tab（推荐/关注等）约 150px |
| 底部 | ≥ 260px（footer margin-bottom:190px + padding-bottom:72px ≈ 262px） |
抖音标题/描述/右侧工具栏约 200-250px |
品牌行（logo+名称+徽章）是顶部第一内容，必须落在顶部安全区之下。
三、 设计 Token（模板已固化，理解即可）
- 背景：
#0b0d14+ 三色光斑（#3b5bff 蓝 / #00c2a8 青 / #7a3bff 紫，blur 130-140px, opacity .22-.35） - 三卡片主题色固定顺序：c1 蓝 / c2 青 / c3 紫（顶部横条=横版 / 左侧竖条=竖版）
- 文字：主白 #eef1f8 / 次 #b9c0d6 / 弱 #9aa3bd / 最弱 #6b7490 / hint #8a93ad
- 强调：标题关键词用青蓝渐变
<em>；正文重点<b>纯白 - CTA 按钮：#00e0c2 青底黑字等宽字体
- 卡片数固定 3 个（多了拥挤，少了空洞；更新点 >3 时合并归类）
四、 制作流程（5 步）
1. 复制模板 → 替换 {{占位符}}（版本号/主标题/三卡标题+英文+描述/安装命令/说明）
- 卡片描述 ≤ 40 字，防孤字贴边（长文案先压缩，禁止靠调字号硬塞）
- 卡片图标按内容选线条 SVG，stroke 用卡片主题浅色（c1 #6f8bff / c2 #00e0c2 / c3 #a86fff）
2. headless Chrome 截图（命令见下）
3. desktop_vision 验收：溢出/孤字/贴边/对齐/logo 完整性
4. 竖版加做：像素级安全区复测（vision 坐标估算不可信，见第五节）
5. 删除临时 HTML（Hygiene 纪律），PNG 交付桌面
截图命令（Chrome 路径按 find_chrome 常见顺序探测）：
& "$chrome" --headless --disable-gpu --hide-scrollbars \
--window-size=<宽>,<高> --screenshot='<输出.png>' 'file:///<模板.html>'
五、 验收纪律（vision 会误报，必须有复测手段）
vision 审查适用于发现布局级问题（溢出/空白/对齐），但两类误报已实战确认：
| 误报 | 真相复测法 |
|---|---|
| "文字是繁体/错字" | 读 HTML 源码核对，源码为准 |
| "安全区只有 40-50px" | 像素扫描：在 PNG 中定位目标色（hint 文字 #8a93ad、按钮 #00e0c2）的最低 y 坐标，安全区 = 画布高 − 文字最低 y。⚠️ 不要扫"非背景色"——背景光斑会干扰（底部光斑曾导致误判安全区=1px） |
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.
- 9d ago First seen · 92 lines · 0 tokens per session scan A fd07fd79774f
release-poster is a skill published in the GitHub repository mrpulor-gh/nuphus (61 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,481 tokens. 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
screenclaw
Desktop software automation through screenshots and coordinate grids. It can repeat recorded actions as reusable templates without needing the software to provide an API or command line.
mk:showcase
Create a self-contained, visually polished HTML showcase page for a topic or set of artifacts. Supply a mission (topic summary) and optional artifact paths explicitly — the skill never auto-scans the repo. Writes output to assets/showcase/ /. Screenshots are optional (requires Puppeteer). Publishing is local-only by…
infographic
A guide for creating infographics with only HTML and CSS. Infographics present structured information visually, such as timelines, comparisons, funnels and organisation charts.
social-publisher
Multi-platform social media publishing automation - schedule, post, and track content across TikTok, Instagram, YouTube, LinkedIn, and more.
tweet-card-generator
Given a topic, auto-searches for info, generates a tweet + matching data-card PNG (HTML→screenshot, clean cream-background style, multi-layout + multi-chart).
showreel
Use when the user wants to explain or document something visually — annotated screenshots, feature demos, flow GIFs, terminal recordings, before/after comparisons — or says "take a screenshot", "record this flow", "make a gif of", "show how this works", "annotate this page", "demo this feature", "grava um gif", "tira…