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 lispking/video-skills --skill manim-video-teachergit clone --depth 1 https://github.com/lispking/video-skillsWrote 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/lispking/video-skills/manim-video-teacher)<a href="https://agentmods.dev/skills/lispking/video-skills/manim-video-teacher"><img src="https://agentmods.dev/badge/skills/lispking/video-skills/manim-video-teacher/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/lispking/video-skills/manim-video-teacher"><img src="https://agentmods.dev/badge/skills/lispking/video-skills/manim-video-teacher.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00065 | $0.01586 |
| Opus 5 | $0.00032 | $0.00793 |
| Sonnet 5 | $0.00013 | $0.00317 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
manim-video-teacher 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 12d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manim 动画教学视频
快速目标
用用户的中文提示语，产出可执行的 Manim 方案：脚本/分镜/代码/渲染命令，并解释关键教学设计选择。
先收集的最少信息
- 主题与受众：讲什么、给谁看
- 时长与节奏：总时长、快慢、是否分章节
- 画面风格：黑板风、简洁线性、是否强调配色
- 数学/代码内容：公式、伪代码或示例数据
若用户未提供，先做合理默认并声明假设。
工作流程
- 把用户提示语改写成教学脚本（结构化段落：引入-核心-总结）。
- 为每段脚本给出分镜（画面目标、关键动画、旁白要点）。
- 设计视觉语言（颜色/字号/对齐/高亮规则），保持一致。
- 生成 Manim 代码（Scene 结构清晰、变量命名明确）。
- 给出渲染命令与参数建议（分辨率、fps、质量）。
- 用脚本生成旁白音频，并可同步产出字幕（SRT）。
- 用脚本合成视频与音频，必要时把字幕嵌入输出。
- 用脚本生成单独封面图（适合传播/分享平台）。
- 简要解释关键教学设计选择（为何这样分镜/过渡/强调）。
教学脚本模板
用短句、可口播的节奏：
- 引入：问题/现象/动机（1-2 句）
- 定义：核心概念（1-3 句）
- 机制：关键步骤或推导（分 2-5 步）
- 示例：用 1 个具体例子验证
- 总结：一句话回扣重点
分镜粒度建议
- 15-30 秒一个镜头块，避免信息密度过高
- 每一步推导或关键结论单独成镜头
- 每个镜头最多 1-2 个主视觉对象
Manim 代码约定
- 使用
Scene或MovingCameraScene，尽量保持单场景可复用。 - 把复杂动画拆成小函数（如
show_definition()）。 - 用
VGroup组织元素，统一对齐与间距。 - 用
FadeIn/FadeOut/Transform/ReplacementTransform传达逻辑过渡。 - 文本尽量用
Tex/MathTex保持数学排版一致，纯中文说明用Text。
默认技术参数
- 分辨率：1920x1080
- fps：30
- 渲染质量：
-qh作为默认 - 输出：MP4
视觉与节奏默认值
- 主色：蓝色或橙色二选一，保持一致
- 强调色：亮黄或红色，仅用于关键结论
- 留白：屏幕边缘留 10-15% 安全区
- 口播节奏：每分钟 120-150 字
脚本优先
优先使用 scripts/ 下的脚本完成语音生成、合成与封面，不要求用户手写命令。
可用脚本：
scripts/tts_generate.py：把旁白文本转为音频（edge-tts），可用--subs-output subs.srt输出字幕scripts/concat_audio.py：合并多段旁白（ffmpeg concat）scripts/mux_av.py：合成视频与音频（ffmpeg），可用--subs subs.srt嵌入字幕scripts/make_cover.py：生成 16:9 封面图（Pillow）scripts/pipeline.py：一键执行语音、合成与封面生成- 可选参数：
--dry-run输出命令不执行，--verbose显示执行命令，--log-file记录命令列表（默认覆盖），--append-log追加记录 - 字幕参数：
--subs-output subs.srt（TTS 生成字幕），--subs subs.srt（使用已有字幕）
- 可选参数：
若脚本报缺依赖，提示用户安装对应依赖即可（edge-tts、ffmpeg、Pillow）。
示例（推荐）：
python scripts/pipeline.py \\
--video manim.mp4 \\
--tts-file narration.txt \\
--subs-output subs.srt \\
--cover-title "二次函数顶点式" \\
--cover-subtitle "60 秒掌握" \\
--output output.mp4
封面图规格与建议
- 比例：16:9
- 尺寸：1920x1080（与正片一致）
- 文字层级：标题 1 行 + 副标题 1 行（可选）
- 信息结构：左大标题，右侧示意图或关键公式
- 颜色：主色 + 强调色，避免超过 3 种主色
- 导出：PNG，保证清晰度
用户可能的触发示例（中文）
- “用 Manim 做一个 60 秒讲解二次函数顶点式的视频。”
- “做一个教学动画解释矩阵乘法，画面简洁。”
- “把这个概念讲给高中生，生成 Manim 代码和渲染命令。”
What ships with it
5 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.
- 12d ago First seen · 137 lines · 65 tokens per session scan A 991acc4b656e
manim-video-teacher is a skill published in the GitHub repository lispking/video-skills (8 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,586 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
html-ppt-zhangzara-daisy-days
A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.
html-ppt-zhangzara-retro-windows
An IT security-awareness training on spotting phishing — the tells, the drill, and what to do in the first 60 seconds. Built as a decision-grade professional training deck for all employees.
sprite-animation
A pixel / sprite-style animated explainer slide — full-bleed cream stage, bold display year, animated pixel-art mascot (e.g. Hanafuda card, mushroom, or 8-bit console), kinetic Japanese display type, ticking timeline ribbon. Reads like a single frame of an educational motion video — looping CSS keyframes, no JS, ready…
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
animation
Author animated technical explainer diagrams as .anim.json files for Nimbalyst's Animation editor. Use when the user wants to animate a diagram, show how a system/protocol/algorithm behaves over time, build a motion explainer, or turn a static architecture diagram into something that plays.