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/slideshow-videoWrote 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/slideshow-video)<a href="https://agentmods.dev/skills/zju-real/easel/slideshow-video"><img src="https://agentmods.dev/badge/skills/zju-real/easel/slideshow-video/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/slideshow-video"><img src="https://agentmods.dev/badge/skills/zju-real/easel/slideshow-video.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 | $0.00166 | $0.01205 |
| Opus 5 | $0.00083 | $0.00602 |
| Sonnet 5 | $0.00033 | $0.00241 |
| Haiku 4.5 | $0.00017 | $0.00120 |
Grade A, and why
slideshow-video 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 8d 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.
What it actually says
图片相册 → 视频
把一组图片拼成一条视频:Ken Burns 缓慢缩放 + 图间转场 + 背景音乐 + 逐图字幕, 自动适配目标画幅。全部走
skills/shared/scripts/slideshow.py,不要手拼 zoompan / xfade——脚本已处理帧数换算、转场偏移、音画时长对齐。
只做"已有图片 → 视频"。从主题自动生成配图/配音的完整流水线见 auto-short-video; 已有视频的剪辑见 video-editing;单张封面/海报见 poster-hero。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 图片 | 是 | 一组图片路径(按顺序),或一个图片目录(按文件名排序) |
| 画幅 | 是 | 用户或上游任务未明确横版/竖版/方形(或具体分辨率)时,制作前必须追问并等确认;不得按平台、Profile 或默认值静默推断,已明确则不重复问 |
| 每图时长 | 否 | 默认每张 3 秒 |
| 转场 | 否 | 默认淡入淡出 fade;none 为硬切 |
| BGM | 否 | 背景音乐文件(自动循环/裁到片长/尾部淡出) |
| 逐图字幕 | 否 | 每张图配一句字幕 |
输出(outputs/主题名/)
- 成片视频(
*.mp4) - 报告:图片数、总时长、画幅、转场方式、是否带 BGM
执行步骤
脚本路径(相对项目根):skills/shared/scripts/slideshow.py(build -h 看全部参数)。
基本用法
python skills/shared/scripts/slideshow.py build \
-i 1.jpg 2.jpg 3.jpg -o outputs/主题名/show.mp4 \
--size 1080x1920 --per 3 --transition fade
带 BGM + 逐图字幕
python skills/shared/scripts/slideshow.py build --images-dir ./photos \
-o outputs/主题名/show.mp4 \
--bgm ./music.mp3 --bgm-volume 0.7 \
--captions "开场一句|第二张说明|第三张说明"
字幕也可用 --captions-file <文件>(每行对应一张图)。
常用变体
- 静止画面(不缩放):
--no-kenburns,配--fit pad(补边)或--fit crop(裁满)。 - 换转场:
--transition可选fade/fadeblack/fadewhite/wipeleft/wiperight/slideup/slidedown/circleopen/dissolve/none。 - 平台画幅:小红书/抖音竖版
1080x1920,朋友圈/ins 方形1080x1080,B站/横版1920x1080。
Profile 感知
- 有 Profile:
platforms.md只用于给出画幅建议,仍须用户确认;字幕语气贴合style.md; BGM 风格建议贴合账号调性(欢快/治愈/燃)。 - 无 Profile:先确认横版/竖版/方形;转场默认 fade + Ken Burns。
规则
- 图片顺序 = 视频顺序;用
--images-dir时按文件名排序,必要时先重命名。 - 转场时长自动限制在每图时长内(不超过
--per)。 - BGM 自动循环补足并裁到成片长度、尾部淡出;无 BGM 时补静音轨方便上传。
- 逐图字幕数量可少于图片数(多出的图不加字幕),不要求一一对应。
- 产物统一进
outputs/主题名/。
参考来源
Ken Burns(缓慢缩放位移)+ 交叉转场 + BGM 是相册/图集视频的标准做法(MoneyPrinterTurbo 等短视频工具同款思路);本 SKILL 复用 auto-short-video 合成器的 zoompan 方案,把帧数换算与 xfade 偏移计算封装成确定性脚本,避免手写滤镜链出错。
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.
- 8d ago First seen · 76 lines · 166 tokens per session scan A cdd931ee0124
slideshow-video is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed yesterday), licensed Apache-2.0. It adds 166 tokens to every session and 1,205 once invoked, about $0.0008 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 2026-09-03.
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…