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-strategygit 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-strategy)<a href="https://agentmods.dev/skills/zju-real/easel/video-strategy"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-strategy/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-strategy"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-strategy.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 | $0.00104 | $0.02266 |
| Opus 5 | $0.00052 | $0.01133 |
| Sonnet 5 | $0.00021 | $0.00453 |
| Haiku 4.5 | $0.00010 | $0.00227 |
Grade A, and why
video-strategy 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 6d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频制作策略
视频制作策略与工具选型。覆盖 AI 视频生成模型对比、程序化视频框架选择、视频脚本结构设计、制作流程规划。
本技能负责策略规划和工具选型。已部署的
video-editing技能可执行实际的 ffmpeg 剪辑操作（裁剪、跳切、文字覆盖、变速等）。
输入
- 视频目标（产品演示 / 解说 / 社媒短视频 / 广告 / 教程）
- 目标平台（抖音 / B站 / 快手 / 视频号 / YouTube / Instagram）
- 现有素材（截图、录屏、脚本、品牌素材）
- 预算和技术栈约束
输出
- 推荐制作方案（工具选型 + 理由）
- 平台适配规格（分辨率、时长、画幅比）
- 制作流程步骤
- 视频脚本结构（如需要）
执行步骤
1. 收集上下文
确认以下信息（未提供则主动询问）：
- 视频类型：产品演示、解说、社媒短视频、广告、教程
- 目标平台：决定画幅比和时长限制（见下方平台规格表）
- 呈现方式：AI 数字人 / 旁白 + 画面 / 纯程序化 / 录屏
- 素材情况：是否有现有素材（截图、录屏、logo）
- 复用需求：一次性还是模板化批量生产
- 预算：部分工具按视频时长计费
2. 选择制作方案
| 方案 | 适用场景 | 工具 | 可用性 |
|---|---|---|---|
| 程序化视频 | 模板化、数据驱动、批量 | Hyperframes, Remotion | ✅ Node.js 可用 |
| AI 视频生成 | 原创画面、B-roll | Veo 3, Sora 2, Runway, Kling, Seedance | ⚠️ 需 API key |
| AI 数字人 | 真人呈现、多语言 | HeyGen, Synthesia | ⚠️ 需 API key |
| 剪辑/二创 | 长视频拆短视频 | ffmpeg (video-editing 技能), CapCut | ✅ ffmpeg 可用 |
3. AI 视频生成模型对比
如用户需要 AI 生成视频画面，参考此表选型：
| 模型 | 分辨率 | 最长时长 | 特长 | 成本 |
|---|---|---|---|---|
| Veo 3 (Google) | 最高 1080p | 可变 | 最高画质 + 同步音频 | API 计费 |
| Sora 2 (OpenAI) | 最高 1080p | ~20s | 电影质感 + 同步音频 | API + ChatGPT |
| Runway Gen-4 | 最高 4K | ~10s/次 | 运动控制、时序一致性 | 订阅制 |
| Kling 2.5/3.0 (快手) | 最高 1080p | 最长 2 分钟 | 长镜头、单位成本低 | 按秒计费（低单价） |
| Seedance (字节跳动) | 最高 1080p | 短片段 | 快速生成、运动保真度高、适合批量 | 按积分 |
| Hailuo / MiniMax (MiniMax) | 最高 1080p | 短片段 | 跨镜头角色一致性 | 按积分 |
| Pika 2.x | 1080p | 短片段 | 快速特效、图生视频 | 按积分 |
| 混元视频 / Wan 2 (腾讯) | 720p-1080p | 可变 | 开源自部署，完全可控，无 API 费 | 免费 (需 GPU) |
快速选型：
- 最高画质 + 音频：Veo 3 或 Sora 2
- 批量 / 低成本：Kling、Seedance
- 跨镜头角色一致性：Hailuo
- 自部署 / 品牌管控：混元视频 或 Wan 2（开源权重）
- 图生视频：Kling、Pika、Runway
上表型号版本号与定价随厂商快速迭代，仅供选型参考，以各厂商官方最新公布为准。
视频 AI 提示词写法详见 references/ai-video-prompting.md
4. 目标平台规格
中国平台
| 平台 | 画幅比 | 推荐分辨率 | 时长限制 | 备注 |
|---|---|---|---|---|
| 抖音 | 9:16 | 1080x1920 | 15s / 60s / 15min | 15s 以内完播率权重最高 |
| B站 | 16:9 | 1920x1080 | 无硬性上限 | 横屏为主，竖屏也支持 |
| 快手 | 9:16 | 1080x1920 | 11min | 竖屏为主 |
| 视频号 | 9:16 / 16:9 | 1080x1920 | 30min | 短视频 < 1min 优先推荐 |
| 小红书 | 9:16 / 3:4 | 1080x1920 | 15min | 3:4 也常用 |
What ships with it
3 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.
- 6d ago First seen · 158 lines · 104 tokens per session scan A b265bc9ff1a3
video-strategy is a skill published in the GitHub repository ZJU-REAL/Easel (710 stars, last pushed today), licensed Apache-2.0. It adds 104 tokens to every session and 2,266 once invoked, about $0.0005 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…