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 ZJU-REAL/Easel --skill auto-short-videogit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote 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/auto-short-video)<a href="https://agentmods.dev/skills/zju-real/easel/auto-short-video"><img src="https://agentmods.dev/badge/skills/zju-real/easel/auto-short-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/auto-short-video"><img src="https://agentmods.dev/badge/skills/zju-real/easel/auto-short-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 | $0.00191 | $0.01519 |
| Opus 5 | $0.00096 | $0.00759 |
| Sonnet 5 | $0.00038 | $0.00304 |
| Haiku 4.5 | $0.00019 | $0.00152 |
Grade A, and why
auto-short-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 11d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
一键短视频（端到端编排）
输入一个主题，自动产出一条短视频。本 SKILL 是编排层：把已有制作零件串成流水线—— 文案(video-script) → 逐句配图(ai-image-gen)或片段(ai-video-gen) → 配音(tts-voiceover) → 字幕(auto-subtitle) → BGM(ai-music) → 合成(scripts/assemble.py)。 沉淀自 Pixelle-Video / MoneyPrinterTurbo 的自动短视频引擎思路。
输入
- 主题 / 文案（必填）
- 可选：目标时长、风格、是否要配音/字幕/BGM、配图用 AI 生图还是用户素材
- 画幅确认硬门：用户或上游任务未明确横版/竖版（或 16:9/9:16/具体分辨率）时，制作/付费调用前必须追问并等确认；不得从平台、Profile 或默认值静默推断，已明确则不重复问
输出
成品短视频写入 outputs/主题名/final.mp4；分镜图、配音、字幕和 storyboard 写入 outputs/主题名/assets/。
执行步骤（按需裁剪，缺 API key 的环节自动降级或询问）
-
写脚本分镜：用 video-script 把主题写成口播文案，拆成 N 句（每句一个分镜），每句配一个画面描述。
-
生成画面（每个分镜一张图/一段片）：
- 有图像 API key → ai-image-gen 逐句 text2img（按已确认画幅）
- 要动态 → ai-video-gen text2video/image2video
- 用户自带素材 → 用 image-editing
pad到已确认画幅 - 都没有 → 按已确认画幅选图卡（竖版用 card-xiaohongshu/poster-hero，横版用 card-quote）再 pad，避免画幅错配。
-
配音：tts-voiceover 把文案合成口播（同时出 SRT）。配了
VOICE_PROVIDER默认走闭源好嗓子（有情感、像真人），没 key 才退 edge（机械）——想要口播不"生硬"务必配闭源 key。不需要配音才跳过。 -
字幕：用 TTS 附带的 SRT，或对配音跑 auto-subtitle；也可让 assemble 用各分镜 caption 自动生成。
-
BGM：ai-music 生成，或用用户提供的音乐。可选。
-
合成成片：把上面的素材写成 storyboard JSON，调合成器：
python skills/openclaw/auto-short-video/scripts/assemble.py assemble \ --storyboard outputs/主题名/assets/storyboard.json \ -o outputs/主题名/final.mp4storyboard 结构（图/片二选一，narration/bgm/subtitle 可选，缺 duration 时按配音均分）：
{ "size": "<已确认尺寸，如1080x1920或1920x1080>", "image_motion": "ken-burns", "shots": [ {"image": "outputs/主题名/assets/shot1.png", "duration": 3, "caption": "第一句", "motion": "static"}, {"video": "outputs/主题名/assets/clip2.mp4", "caption": "第二句"} ], "narration": "outputs/主题名/assets/voice.mp3", "bgm": "outputs/主题名/assets/bgm.mp3", "subtitle": "outputs/主题名/assets/voice.srt" }image_motion设整条图片默认运动，单镜motion可覆写：照片用ken-burns，含文字的 slide/图表/界面必须用static（等比缩放 + 补边，不裁切、不平移）。 合成器自动做：按image_motion生成静帧或 Ken Burns、补边到画幅、拼接、配音+BGM 混音（BGM 自动压低）、烧录字幕。
What ships with it
2 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.
- 11d ago First seen · 76 lines · 191 tokens per session scan A b5d4b4dd62d9
auto-short-video is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 191 tokens to every session and 1,519 once invoked, about $0.0010 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…