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 video-scriptgit 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/video-script)<a href="https://agentmods.dev/skills/zju-real/easel/video-script"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-script/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/video-script"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-script.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 | $0.00196 | $0.02118 |
| Opus 5 | $0.00098 | $0.01059 |
| Sonnet 5 | $0.00039 | $0.00424 |
| Haiku 4.5 | $0.00020 | $0.00212 |
Grade A, and why
video-script 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.
How it starts
The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频脚本生成
根据目标时长自动适配短视频或中长视频模式，生成留存率优化的结构化脚本。
输入
| 字段 | 必填 | 说明 | 示例 |
|---|---|---|---|
| 主题 | 是 | 视频主题 | "为什么 Rust 正在替代 C++" |
| 目标时长 | 是 | 秒数或分钟数 | 30 秒 / 10 分钟 |
| 平台 | 否 | 抖音/视频号/小红书/B站（默认按时长推断） | 抖音 |
| 内容类型 | 否 | 科普/教程/评测/种草/解说/杂谈 | 科普 |
| 核心要点 | 是 | 要覆盖的关键信息 | 内存安全、性能… |
| 调性 | 否 | 专业/轻松/犀利/对话感（默认：对话感） | 轻松 |
模式自动判定
| 时长 | 模式 | 典型平台 | 关键指标 |
|---|---|---|---|
| 7-15 秒 | 短视频·极速 | 抖音/视频号 | 3 秒完播率 |
| 15-60 秒 | 短视频·标准 | 抖音/视频号/小红书 | 完播率、DM 转发、收藏 |
| 1-5 分钟 | 中视频 | 视频号/抖音/B站 | 5 秒留存、互动率 |
| 5-30 分钟 | 长视频 | B站/YouTube | 30 秒留存、播放完成率 |
语速基准：中文约 250 字/分钟。
短视频模式（≤60 秒）
Step 1 — Hook 设计（3 个变体）
从 5 种 Hook 类型中选 3 个，各生成一个变体：
| 类型 | 适用场景 | 示例 |
|---|---|---|
| 好奇缺口 | 冷知识、反直觉 | "你每天做的这件事其实在伤害你" |
| 模式打断 | 反常规、挑战认知 | "忘掉你以前学的所有XX" |
| 身份触发 | 精准受众 | "如果你是XX，这条一定要看完" |
| 痛点共鸣 | 真实困扰 | "明明很努力了还是没效果？" |
| 权威背书 | 数据/研究支撑 | "最新研究发现：XX 竟然是错的" |
每个 Hook 按 4 维度评分（每项 1-5，满分 20）：好奇强度、打断效果、身份触发、3 秒清晰度。选最高分作为主 Hook。
Step 2 — 分秒脚本
按时长压缩结构：
| 时长 | 结构 |
|---|---|
| 7-15 秒 | Hook(0-2s) + 核心价值(2-10s) + 收尾(10-15s) |
| 15-30 秒 | Hook(0-3s) + 痛点(3-8s) + 方案(8-20s) + 收尾CTA(20-30s) |
| 30-60 秒 | Hook(0-3s) + 痛点(3-8s) + 方案(8-40s) + 洞察+CTA(40-60s) |
脚本格式：
[0-3s] HOOK
口播: "..."
字幕: "..."
画面: [描述]
[3-8s] 痛点
口播: "..."
画面: [描述]
每句 ≤15 字，口语化，加括号注释（停顿/强调/表情）。
Step 3 — caption + 封面
caption：100-300 字，Hook 变体开头（不重复视频 Hook），DM 转发 > 收藏 > 点赞。 hashtags：3-5 个垂直标签，不用泛标签。 封面：3-5 字大标题 + 画面描述 + 表情。
Step 4 — 质量评分（满分 100）
| 维度 | 权重 | 检查点 |
|---|---|---|
| Hook 强度 | 25 | 好奇缺口、打断效果、3 秒清晰度 |
| 内容质量 | 25 | 价值密度、结构、痛点-方案清晰度 |
| caption+CTA | 20 | 长度 100+字、转发型 CTA、Hook 变体 |
| 格式合规 | 15 | 9:16 安全区、时长匹配、封面 |
| 算法信号 | 15 | 收藏/转发优化、原创性 |
≥80 分交付，<60 分返工后重评。
中长视频模式（>60 秒）
留存率优化的详细方法（节奏中断点 / 前向钩子 / 章节结构 / 留存曲线）见
references/retention-scripting-guide.md。
Step 1 — 结构计算
根据目标时长分配各段：
- Hook：0:00-0:30（短视频缩短到 0:00-0:10）
- 开场：0:30-2:00
- 首次 CTA：约 25% 处
- 留存再拉回：约 60% 处
- 结尾：最后 60 秒
- 目标字数 = 时长(分钟) × 250
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.
- 8d ago First seen · 163 lines · 196 tokens per session scan A 3b06a2078a62
video-script is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 196 tokens to every session and 2,118 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 2026-09-03.
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…