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 agentmods add skills/guanyang/super-publisher/video-tutorial-makernpx skills add guanyang/super-publisher --skill video-tutorial-makergit clone --depth 1 https://github.com/guanyang/super-publisherWrote 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/guanyang/super-publisher/video-tutorial-maker)<a href="https://agentmods.dev/skills/guanyang/super-publisher/video-tutorial-maker"><img src="https://agentmods.dev/badge/skills/guanyang/super-publisher/video-tutorial-maker.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00081 | $0.01329 |
| Opus 5 | $0.00041 | $0.00665 |
| Sonnet 5 | $0.00016 | $0.00266 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
video-tutorial-maker 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 5d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Tutorial Maker
Use this skill to turn a topic, outline, script, or existing video into a finished tutorial video package.
Default assumption: produce a 16:9 landscape MP4 first. Create 9:16 or other platform variants only when requested or clearly useful.
Workflow
-
Define the deliverable.
- Confirm the topic, target audience, tone, duration, language, and required output path when they are unclear.
- If the user does not specify aspect ratio, use
1920x1080landscape video. - For coding or software tutorials, prefer a clear slide/screen sequence over dense narration.
-
Write the video package.
- Create a concise script with one narration block per scene or slide.
- For each scene, define title, subtitle, bullets or screen action, visual style, and narration.
- Keep on-screen text shorter than narration. Do not force full captions into the visual design.
-
Generate speech.
- Prefer
edge-ttswhen available because it is free and more natural than basic system voices. - For Chinese, start with
zh-CN-XiaoxiaoNeural; adjust voice or rate only if the user asks or the result is clearly poor. - Generate audio per scene, not one large narration file. Per-scene audio makes transition sync and subtitle offsetting deterministic.
- Prefer
-
Build subtitles from the same timeline as audio.
- Use the subtitle output from TTS when available.
- Parse both
00:00:01.234and00:00:01,234timestamp formats. - Offset each scene subtitle by the cumulative scene duration.
- Verify the final subtitle file contains real timestamps and no
NaN.
-
Render video.
- Render each scene to a fixed duration equal to its audio duration plus any intended pause.
- If a scene has a trailing pause, pad that scene's audio with silence to the exact scene video duration before concatenating.
- Concatenate padded scene audio, not raw scene audio. Otherwise voice will drift earlier after each transition.
- Mux video, audio, and soft subtitles into MP4 when supported; otherwise output the subtitle file as a sidecar.
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.
- 5d ago First seen · 121 lines · 81 tokens per session scan A 199f8182bd15
video-tutorial-maker is a skill published in the GitHub repository guanyang/super-publisher (29 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,329 once invoked, about $0.0004 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
guidance
回答用户关于 QwenPaw 安装与配置的问题：优先定位并阅读本地文档，再提炼答案；若本地信息不足，兜底访问官网文档。.
edu-math-tutorial
数学题分步讲解视频的领域知识。适用场景：(1) 用户给出一道数学题并要求做讲解/ 解题视频；(2) 用户说"讲解这道题"、"生成解题视频"、"make a math tutorial"； (3) 需要中文数学教学视频，涉及方程、公式或几何图形。本 skill 只提供领域 知识（题目拆解、讲解节奏、旁白文案规范、版式与 KaTeX 排版风格）；画面、 配音与成片一律用 Creator 原生 Element 与工具从源头构建。.
output-format
结构化医学学习产物的统一格式校验。四条硬格式与 validateoutput.py 单次标准输入流程。指南章节、路径图、诊断、备考、医保、更新和每日单元使用；普通医学问答走 clinical-q-and-a 的轻量自检，通用任务不套用。.
clinical-q-and-a
快速回答普通教育性医学问题与常见误区。默认用一份国内现行权威指南/共识完成轻量核验并立即作答；不用于个体诊疗、处方剂量、精确推荐定位、药品高风险事实、医保监管或跨版本比较。.
81-pipecat
Create your Pipecat skill from official documentation, then learn to improve it throughout the chapter.
guideline-section-expansion
用户反馈里最常见的两句话是「指南查到了但展不开」和「能不能把指南总结成流程」。本 skill 处理这两件事，并把它们严格限定为学习产物。.